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 +2541 -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-2-13b-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-2-13b-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:f9b639efac89cf87159329b3e67ed766e8c8b8d510778ca3d63b4c73590dabc2
|
| 3 |
+
size 26272202
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3aeea956e91ee8f201de5a46b5da8c8cc551c388e9d256c2552da59040484294
|
| 3 |
+
size 52563258
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:109cb02883a7c17566db5d945e9488d11817a9e7f05895c6535d367e80295a3a
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca8be5379cd4830ca5066c56b3e326ed63f41053626b006010c7346737984784
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2541 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9323536157608032,
|
| 3 |
+
"best_model_checkpoint": "/scratch/czm5kz/llama2-13b_32_1_0.0003_alternate/checkpoint-1400",
|
| 4 |
+
"epoch": 0.9975062344139651,
|
| 5 |
+
"eval_steps": 20,
|
| 6 |
+
"global_step": 1400,
|
| 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": 0.9500238299369812,
|
| 14 |
+
"learning_rate": 0.0002989308624376336,
|
| 15 |
+
"loss": 2.9196,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 1.3018202781677246,
|
| 21 |
+
"learning_rate": 0.00029786172487526725,
|
| 22 |
+
"loss": 2.1494,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 0.9286252856254578,
|
| 28 |
+
"learning_rate": 0.0002967925873129009,
|
| 29 |
+
"loss": 1.7255,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 1.2644277811050415,
|
| 35 |
+
"learning_rate": 0.00029572344975053457,
|
| 36 |
+
"loss": 1.5678,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"eval_loss": 1.4308089017868042,
|
| 42 |
+
"eval_runtime": 429.3923,
|
| 43 |
+
"eval_samples_per_second": 26.151,
|
| 44 |
+
"eval_steps_per_second": 3.27,
|
| 45 |
+
"step": 20
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"grad_norm": 1.486525535583496,
|
| 50 |
+
"learning_rate": 0.00029465431218816815,
|
| 51 |
+
"loss": 1.3281,
|
| 52 |
+
"step": 25
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.02,
|
| 56 |
+
"grad_norm": 1.1946622133255005,
|
| 57 |
+
"learning_rate": 0.00029358517462580184,
|
| 58 |
+
"loss": 1.2098,
|
| 59 |
+
"step": 30
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.02,
|
| 63 |
+
"grad_norm": 0.7685691118240356,
|
| 64 |
+
"learning_rate": 0.0002925160370634355,
|
| 65 |
+
"loss": 1.2045,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.03,
|
| 70 |
+
"grad_norm": 1.084057092666626,
|
| 71 |
+
"learning_rate": 0.0002914468995010691,
|
| 72 |
+
"loss": 1.2187,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.03,
|
| 77 |
+
"eval_loss": 1.1283082962036133,
|
| 78 |
+
"eval_runtime": 429.1606,
|
| 79 |
+
"eval_samples_per_second": 26.165,
|
| 80 |
+
"eval_steps_per_second": 3.272,
|
| 81 |
+
"step": 40
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.03,
|
| 85 |
+
"grad_norm": 0.6618586778640747,
|
| 86 |
+
"learning_rate": 0.00029037776193870275,
|
| 87 |
+
"loss": 1.1625,
|
| 88 |
+
"step": 45
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.04,
|
| 92 |
+
"grad_norm": 0.5745049118995667,
|
| 93 |
+
"learning_rate": 0.0002893086243763364,
|
| 94 |
+
"loss": 1.1622,
|
| 95 |
+
"step": 50
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.04,
|
| 99 |
+
"grad_norm": 0.6866307854652405,
|
| 100 |
+
"learning_rate": 0.00028823948681397,
|
| 101 |
+
"loss": 1.1375,
|
| 102 |
+
"step": 55
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.04,
|
| 106 |
+
"grad_norm": 0.7473587393760681,
|
| 107 |
+
"learning_rate": 0.0002871703492516037,
|
| 108 |
+
"loss": 1.1048,
|
| 109 |
+
"step": 60
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.04,
|
| 113 |
+
"eval_loss": 1.0678260326385498,
|
| 114 |
+
"eval_runtime": 430.0891,
|
| 115 |
+
"eval_samples_per_second": 26.109,
|
| 116 |
+
"eval_steps_per_second": 3.264,
|
| 117 |
+
"step": 60
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.05,
|
| 121 |
+
"grad_norm": 0.5050413012504578,
|
| 122 |
+
"learning_rate": 0.0002861012116892373,
|
| 123 |
+
"loss": 1.082,
|
| 124 |
+
"step": 65
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.05,
|
| 128 |
+
"grad_norm": 0.546146810054779,
|
| 129 |
+
"learning_rate": 0.000285032074126871,
|
| 130 |
+
"loss": 1.0399,
|
| 131 |
+
"step": 70
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.05,
|
| 135 |
+
"grad_norm": 0.6042059659957886,
|
| 136 |
+
"learning_rate": 0.0002839629365645046,
|
| 137 |
+
"loss": 0.9998,
|
| 138 |
+
"step": 75
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.06,
|
| 142 |
+
"grad_norm": 0.5676208734512329,
|
| 143 |
+
"learning_rate": 0.00028289379900213826,
|
| 144 |
+
"loss": 1.0594,
|
| 145 |
+
"step": 80
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.06,
|
| 149 |
+
"eval_loss": 1.0362563133239746,
|
| 150 |
+
"eval_runtime": 429.9585,
|
| 151 |
+
"eval_samples_per_second": 26.116,
|
| 152 |
+
"eval_steps_per_second": 3.265,
|
| 153 |
+
"step": 80
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.06,
|
| 157 |
+
"grad_norm": 0.6432541012763977,
|
| 158 |
+
"learning_rate": 0.0002818246614397719,
|
| 159 |
+
"loss": 1.052,
|
| 160 |
+
"step": 85
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.06,
|
| 164 |
+
"grad_norm": 0.5946438312530518,
|
| 165 |
+
"learning_rate": 0.00028075552387740553,
|
| 166 |
+
"loss": 1.038,
|
| 167 |
+
"step": 90
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.07,
|
| 171 |
+
"grad_norm": 0.6687917113304138,
|
| 172 |
+
"learning_rate": 0.00027968638631503917,
|
| 173 |
+
"loss": 1.0949,
|
| 174 |
+
"step": 95
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.07,
|
| 178 |
+
"grad_norm": 1.521995186805725,
|
| 179 |
+
"learning_rate": 0.0002786172487526728,
|
| 180 |
+
"loss": 1.0393,
|
| 181 |
+
"step": 100
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.07,
|
| 185 |
+
"eval_loss": 1.0224562883377075,
|
| 186 |
+
"eval_runtime": 430.7099,
|
| 187 |
+
"eval_samples_per_second": 26.071,
|
| 188 |
+
"eval_steps_per_second": 3.26,
|
| 189 |
+
"step": 100
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.07,
|
| 193 |
+
"grad_norm": 0.5327974557876587,
|
| 194 |
+
"learning_rate": 0.00027754811119030644,
|
| 195 |
+
"loss": 1.0709,
|
| 196 |
+
"step": 105
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.08,
|
| 200 |
+
"grad_norm": 0.47005364298820496,
|
| 201 |
+
"learning_rate": 0.0002764789736279401,
|
| 202 |
+
"loss": 1.0119,
|
| 203 |
+
"step": 110
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.08,
|
| 207 |
+
"grad_norm": 0.6974779963493347,
|
| 208 |
+
"learning_rate": 0.00027540983606557377,
|
| 209 |
+
"loss": 1.0285,
|
| 210 |
+
"step": 115
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.09,
|
| 214 |
+
"grad_norm": 0.568474531173706,
|
| 215 |
+
"learning_rate": 0.0002743406985032074,
|
| 216 |
+
"loss": 1.085,
|
| 217 |
+
"step": 120
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.09,
|
| 221 |
+
"eval_loss": 1.012302041053772,
|
| 222 |
+
"eval_runtime": 430.9145,
|
| 223 |
+
"eval_samples_per_second": 26.059,
|
| 224 |
+
"eval_steps_per_second": 3.258,
|
| 225 |
+
"step": 120
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.09,
|
| 229 |
+
"grad_norm": 0.4923990070819855,
|
| 230 |
+
"learning_rate": 0.00027327156094084104,
|
| 231 |
+
"loss": 1.0179,
|
| 232 |
+
"step": 125
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.09,
|
| 236 |
+
"grad_norm": 0.4918578565120697,
|
| 237 |
+
"learning_rate": 0.0002722024233784747,
|
| 238 |
+
"loss": 0.982,
|
| 239 |
+
"step": 130
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.1,
|
| 243 |
+
"grad_norm": 0.6147764921188354,
|
| 244 |
+
"learning_rate": 0.0002711332858161083,
|
| 245 |
+
"loss": 1.0864,
|
| 246 |
+
"step": 135
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.1,
|
| 250 |
+
"grad_norm": 0.5552188158035278,
|
| 251 |
+
"learning_rate": 0.00027006414825374195,
|
| 252 |
+
"loss": 1.0125,
|
| 253 |
+
"step": 140
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.1,
|
| 257 |
+
"eval_loss": 1.004356861114502,
|
| 258 |
+
"eval_runtime": 428.4385,
|
| 259 |
+
"eval_samples_per_second": 26.209,
|
| 260 |
+
"eval_steps_per_second": 3.277,
|
| 261 |
+
"step": 140
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1,
|
| 265 |
+
"grad_norm": 0.5992436408996582,
|
| 266 |
+
"learning_rate": 0.00026899501069137564,
|
| 267 |
+
"loss": 1.0427,
|
| 268 |
+
"step": 145
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.11,
|
| 272 |
+
"grad_norm": 0.44927549362182617,
|
| 273 |
+
"learning_rate": 0.0002679258731290092,
|
| 274 |
+
"loss": 0.9857,
|
| 275 |
+
"step": 150
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.11,
|
| 279 |
+
"grad_norm": 0.7258988618850708,
|
| 280 |
+
"learning_rate": 0.0002668567355666429,
|
| 281 |
+
"loss": 1.0241,
|
| 282 |
+
"step": 155
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.11,
|
| 286 |
+
"grad_norm": 0.4783088266849518,
|
| 287 |
+
"learning_rate": 0.00026578759800427654,
|
| 288 |
+
"loss": 0.9954,
|
| 289 |
+
"step": 160
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11,
|
| 293 |
+
"eval_loss": 0.9951605796813965,
|
| 294 |
+
"eval_runtime": 429.3957,
|
| 295 |
+
"eval_samples_per_second": 26.151,
|
| 296 |
+
"eval_steps_per_second": 3.27,
|
| 297 |
+
"step": 160
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.12,
|
| 301 |
+
"grad_norm": 0.547055184841156,
|
| 302 |
+
"learning_rate": 0.0002647184604419102,
|
| 303 |
+
"loss": 1.008,
|
| 304 |
+
"step": 165
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.12,
|
| 308 |
+
"grad_norm": 0.5691074132919312,
|
| 309 |
+
"learning_rate": 0.0002636493228795438,
|
| 310 |
+
"loss": 0.9818,
|
| 311 |
+
"step": 170
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.12,
|
| 315 |
+
"grad_norm": 0.5176872611045837,
|
| 316 |
+
"learning_rate": 0.00026258018531717745,
|
| 317 |
+
"loss": 1.009,
|
| 318 |
+
"step": 175
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.13,
|
| 322 |
+
"grad_norm": 0.469517320394516,
|
| 323 |
+
"learning_rate": 0.0002615110477548111,
|
| 324 |
+
"loss": 1.0347,
|
| 325 |
+
"step": 180
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.13,
|
| 329 |
+
"eval_loss": 0.9926482439041138,
|
| 330 |
+
"eval_runtime": 428.9611,
|
| 331 |
+
"eval_samples_per_second": 26.177,
|
| 332 |
+
"eval_steps_per_second": 3.273,
|
| 333 |
+
"step": 180
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.13,
|
| 337 |
+
"grad_norm": 0.4130084812641144,
|
| 338 |
+
"learning_rate": 0.0002604419101924447,
|
| 339 |
+
"loss": 0.9957,
|
| 340 |
+
"step": 185
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.14,
|
| 344 |
+
"grad_norm": 0.43157169222831726,
|
| 345 |
+
"learning_rate": 0.00025937277263007836,
|
| 346 |
+
"loss": 1.0193,
|
| 347 |
+
"step": 190
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.14,
|
| 351 |
+
"grad_norm": 0.4014897644519806,
|
| 352 |
+
"learning_rate": 0.000258303635067712,
|
| 353 |
+
"loss": 1.0301,
|
| 354 |
+
"step": 195
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.14,
|
| 358 |
+
"grad_norm": 0.4352978765964508,
|
| 359 |
+
"learning_rate": 0.0002572344975053457,
|
| 360 |
+
"loss": 0.9812,
|
| 361 |
+
"step": 200
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.14,
|
| 365 |
+
"eval_loss": 0.9875041246414185,
|
| 366 |
+
"eval_runtime": 429.7836,
|
| 367 |
+
"eval_samples_per_second": 26.127,
|
| 368 |
+
"eval_steps_per_second": 3.267,
|
| 369 |
+
"step": 200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.15,
|
| 373 |
+
"grad_norm": 0.350909948348999,
|
| 374 |
+
"learning_rate": 0.0002561653599429793,
|
| 375 |
+
"loss": 0.9866,
|
| 376 |
+
"step": 205
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.15,
|
| 380 |
+
"grad_norm": 0.48860958218574524,
|
| 381 |
+
"learning_rate": 0.00025509622238061296,
|
| 382 |
+
"loss": 0.9854,
|
| 383 |
+
"step": 210
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.15,
|
| 387 |
+
"grad_norm": 0.5793005228042603,
|
| 388 |
+
"learning_rate": 0.0002540270848182466,
|
| 389 |
+
"loss": 1.0233,
|
| 390 |
+
"step": 215
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.16,
|
| 394 |
+
"grad_norm": 0.4061422646045685,
|
| 395 |
+
"learning_rate": 0.00025295794725588023,
|
| 396 |
+
"loss": 0.9912,
|
| 397 |
+
"step": 220
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.16,
|
| 401 |
+
"eval_loss": 0.9817266464233398,
|
| 402 |
+
"eval_runtime": 428.9163,
|
| 403 |
+
"eval_samples_per_second": 26.18,
|
| 404 |
+
"eval_steps_per_second": 3.273,
|
| 405 |
+
"step": 220
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.16,
|
| 409 |
+
"grad_norm": 0.41655540466308594,
|
| 410 |
+
"learning_rate": 0.00025188880969351387,
|
| 411 |
+
"loss": 0.9682,
|
| 412 |
+
"step": 225
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.16,
|
| 416 |
+
"grad_norm": 0.40418338775634766,
|
| 417 |
+
"learning_rate": 0.00025081967213114756,
|
| 418 |
+
"loss": 0.9841,
|
| 419 |
+
"step": 230
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.17,
|
| 423 |
+
"grad_norm": 0.4219729006290436,
|
| 424 |
+
"learning_rate": 0.00024975053456878114,
|
| 425 |
+
"loss": 0.9733,
|
| 426 |
+
"step": 235
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.17,
|
| 430 |
+
"grad_norm": 0.4193793833255768,
|
| 431 |
+
"learning_rate": 0.00024868139700641483,
|
| 432 |
+
"loss": 1.0167,
|
| 433 |
+
"step": 240
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.17,
|
| 437 |
+
"eval_loss": 0.9779065847396851,
|
| 438 |
+
"eval_runtime": 429.6736,
|
| 439 |
+
"eval_samples_per_second": 26.134,
|
| 440 |
+
"eval_steps_per_second": 3.268,
|
| 441 |
+
"step": 240
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.17,
|
| 445 |
+
"grad_norm": 0.38435232639312744,
|
| 446 |
+
"learning_rate": 0.00024761225944404847,
|
| 447 |
+
"loss": 0.9686,
|
| 448 |
+
"step": 245
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.18,
|
| 452 |
+
"grad_norm": 0.36323386430740356,
|
| 453 |
+
"learning_rate": 0.0002465431218816821,
|
| 454 |
+
"loss": 0.9785,
|
| 455 |
+
"step": 250
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.18,
|
| 459 |
+
"grad_norm": 0.4036902189254761,
|
| 460 |
+
"learning_rate": 0.00024547398431931574,
|
| 461 |
+
"loss": 0.9708,
|
| 462 |
+
"step": 255
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.19,
|
| 466 |
+
"grad_norm": 0.46558523178100586,
|
| 467 |
+
"learning_rate": 0.0002444048467569494,
|
| 468 |
+
"loss": 0.9634,
|
| 469 |
+
"step": 260
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.19,
|
| 473 |
+
"eval_loss": 0.9745126962661743,
|
| 474 |
+
"eval_runtime": 429.4898,
|
| 475 |
+
"eval_samples_per_second": 26.145,
|
| 476 |
+
"eval_steps_per_second": 3.269,
|
| 477 |
+
"step": 260
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.19,
|
| 481 |
+
"grad_norm": 0.5028152465820312,
|
| 482 |
+
"learning_rate": 0.000243335709194583,
|
| 483 |
+
"loss": 0.9661,
|
| 484 |
+
"step": 265
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.19,
|
| 488 |
+
"grad_norm": 0.49994298815727234,
|
| 489 |
+
"learning_rate": 0.00024226657163221665,
|
| 490 |
+
"loss": 1.0082,
|
| 491 |
+
"step": 270
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.2,
|
| 495 |
+
"grad_norm": 0.41407310962677,
|
| 496 |
+
"learning_rate": 0.0002411974340698503,
|
| 497 |
+
"loss": 0.9414,
|
| 498 |
+
"step": 275
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.2,
|
| 502 |
+
"grad_norm": 0.39765608310699463,
|
| 503 |
+
"learning_rate": 0.00024012829650748392,
|
| 504 |
+
"loss": 0.9785,
|
| 505 |
+
"step": 280
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.2,
|
| 509 |
+
"eval_loss": 0.9723387956619263,
|
| 510 |
+
"eval_runtime": 429.7271,
|
| 511 |
+
"eval_samples_per_second": 26.131,
|
| 512 |
+
"eval_steps_per_second": 3.267,
|
| 513 |
+
"step": 280
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.2,
|
| 517 |
+
"grad_norm": 0.36988940834999084,
|
| 518 |
+
"learning_rate": 0.00023905915894511758,
|
| 519 |
+
"loss": 0.9391,
|
| 520 |
+
"step": 285
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.21,
|
| 524 |
+
"grad_norm": 0.4206317365169525,
|
| 525 |
+
"learning_rate": 0.00023799002138275122,
|
| 526 |
+
"loss": 0.9463,
|
| 527 |
+
"step": 290
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.21,
|
| 531 |
+
"grad_norm": 0.45045849680900574,
|
| 532 |
+
"learning_rate": 0.00023692088382038488,
|
| 533 |
+
"loss": 0.9946,
|
| 534 |
+
"step": 295
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.21,
|
| 538 |
+
"grad_norm": 0.39236941933631897,
|
| 539 |
+
"learning_rate": 0.0002358517462580185,
|
| 540 |
+
"loss": 0.976,
|
| 541 |
+
"step": 300
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.21,
|
| 545 |
+
"eval_loss": 0.9704678654670715,
|
| 546 |
+
"eval_runtime": 429.6884,
|
| 547 |
+
"eval_samples_per_second": 26.133,
|
| 548 |
+
"eval_steps_per_second": 3.267,
|
| 549 |
+
"step": 300
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.22,
|
| 553 |
+
"grad_norm": 0.5147037506103516,
|
| 554 |
+
"learning_rate": 0.00023478260869565215,
|
| 555 |
+
"loss": 0.9661,
|
| 556 |
+
"step": 305
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.22,
|
| 560 |
+
"grad_norm": 0.4205746352672577,
|
| 561 |
+
"learning_rate": 0.0002337134711332858,
|
| 562 |
+
"loss": 1.0082,
|
| 563 |
+
"step": 310
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.22,
|
| 567 |
+
"grad_norm": 0.5038707852363586,
|
| 568 |
+
"learning_rate": 0.00023264433357091945,
|
| 569 |
+
"loss": 1.0248,
|
| 570 |
+
"step": 315
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.23,
|
| 574 |
+
"grad_norm": 0.38720741868019104,
|
| 575 |
+
"learning_rate": 0.0002315751960085531,
|
| 576 |
+
"loss": 0.9593,
|
| 577 |
+
"step": 320
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.23,
|
| 581 |
+
"eval_loss": 0.9690603017807007,
|
| 582 |
+
"eval_runtime": 429.2915,
|
| 583 |
+
"eval_samples_per_second": 26.157,
|
| 584 |
+
"eval_steps_per_second": 3.271,
|
| 585 |
+
"step": 320
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.23,
|
| 589 |
+
"grad_norm": 0.37954407930374146,
|
| 590 |
+
"learning_rate": 0.00023050605844618672,
|
| 591 |
+
"loss": 0.9919,
|
| 592 |
+
"step": 325
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.24,
|
| 596 |
+
"grad_norm": 0.9392601251602173,
|
| 597 |
+
"learning_rate": 0.00022943692088382036,
|
| 598 |
+
"loss": 1.003,
|
| 599 |
+
"step": 330
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.24,
|
| 603 |
+
"grad_norm": 0.5109981894493103,
|
| 604 |
+
"learning_rate": 0.00022836778332145402,
|
| 605 |
+
"loss": 0.9723,
|
| 606 |
+
"step": 335
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.24,
|
| 610 |
+
"grad_norm": 0.56329345703125,
|
| 611 |
+
"learning_rate": 0.00022729864575908766,
|
| 612 |
+
"loss": 1.0046,
|
| 613 |
+
"step": 340
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.24,
|
| 617 |
+
"eval_loss": 0.9681074619293213,
|
| 618 |
+
"eval_runtime": 429.1046,
|
| 619 |
+
"eval_samples_per_second": 26.168,
|
| 620 |
+
"eval_steps_per_second": 3.272,
|
| 621 |
+
"step": 340
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.25,
|
| 625 |
+
"grad_norm": 0.3970394730567932,
|
| 626 |
+
"learning_rate": 0.00022622950819672127,
|
| 627 |
+
"loss": 1.0459,
|
| 628 |
+
"step": 345
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.25,
|
| 632 |
+
"grad_norm": 0.33091840147972107,
|
| 633 |
+
"learning_rate": 0.00022516037063435493,
|
| 634 |
+
"loss": 0.959,
|
| 635 |
+
"step": 350
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.25,
|
| 639 |
+
"grad_norm": 0.39255568385124207,
|
| 640 |
+
"learning_rate": 0.00022409123307198857,
|
| 641 |
+
"loss": 0.9297,
|
| 642 |
+
"step": 355
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.26,
|
| 646 |
+
"grad_norm": 0.40491119027137756,
|
| 647 |
+
"learning_rate": 0.00022302209550962223,
|
| 648 |
+
"loss": 0.9573,
|
| 649 |
+
"step": 360
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.26,
|
| 653 |
+
"eval_loss": 0.964959442615509,
|
| 654 |
+
"eval_runtime": 429.8883,
|
| 655 |
+
"eval_samples_per_second": 26.121,
|
| 656 |
+
"eval_steps_per_second": 3.266,
|
| 657 |
+
"step": 360
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.26,
|
| 661 |
+
"grad_norm": 0.3292306065559387,
|
| 662 |
+
"learning_rate": 0.00022195295794725584,
|
| 663 |
+
"loss": 0.9592,
|
| 664 |
+
"step": 365
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.26,
|
| 668 |
+
"grad_norm": 0.38449323177337646,
|
| 669 |
+
"learning_rate": 0.0002208838203848895,
|
| 670 |
+
"loss": 0.9375,
|
| 671 |
+
"step": 370
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.27,
|
| 675 |
+
"grad_norm": 0.4422217309474945,
|
| 676 |
+
"learning_rate": 0.00021981468282252314,
|
| 677 |
+
"loss": 0.9794,
|
| 678 |
+
"step": 375
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.27,
|
| 682 |
+
"grad_norm": 0.5002702474594116,
|
| 683 |
+
"learning_rate": 0.0002187455452601568,
|
| 684 |
+
"loss": 0.9956,
|
| 685 |
+
"step": 380
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.27,
|
| 689 |
+
"eval_loss": 0.9628071188926697,
|
| 690 |
+
"eval_runtime": 429.2302,
|
| 691 |
+
"eval_samples_per_second": 26.161,
|
| 692 |
+
"eval_steps_per_second": 3.271,
|
| 693 |
+
"step": 380
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.27,
|
| 697 |
+
"grad_norm": 0.32773861289024353,
|
| 698 |
+
"learning_rate": 0.0002176764076977904,
|
| 699 |
+
"loss": 0.9852,
|
| 700 |
+
"step": 385
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.28,
|
| 704 |
+
"grad_norm": 0.5032110214233398,
|
| 705 |
+
"learning_rate": 0.00021660727013542407,
|
| 706 |
+
"loss": 0.9525,
|
| 707 |
+
"step": 390
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.28,
|
| 711 |
+
"grad_norm": 0.3590690791606903,
|
| 712 |
+
"learning_rate": 0.0002155381325730577,
|
| 713 |
+
"loss": 0.9591,
|
| 714 |
+
"step": 395
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.29,
|
| 718 |
+
"grad_norm": 0.7039294242858887,
|
| 719 |
+
"learning_rate": 0.00021446899501069137,
|
| 720 |
+
"loss": 0.963,
|
| 721 |
+
"step": 400
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.29,
|
| 725 |
+
"eval_loss": 0.9601727724075317,
|
| 726 |
+
"eval_runtime": 429.5145,
|
| 727 |
+
"eval_samples_per_second": 26.143,
|
| 728 |
+
"eval_steps_per_second": 3.269,
|
| 729 |
+
"step": 400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.29,
|
| 733 |
+
"grad_norm": 0.36725956201553345,
|
| 734 |
+
"learning_rate": 0.00021339985744832498,
|
| 735 |
+
"loss": 0.9859,
|
| 736 |
+
"step": 405
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.29,
|
| 740 |
+
"grad_norm": 0.323743611574173,
|
| 741 |
+
"learning_rate": 0.00021233071988595865,
|
| 742 |
+
"loss": 0.9349,
|
| 743 |
+
"step": 410
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.3,
|
| 747 |
+
"grad_norm": 0.46232929825782776,
|
| 748 |
+
"learning_rate": 0.00021126158232359228,
|
| 749 |
+
"loss": 0.9344,
|
| 750 |
+
"step": 415
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.3,
|
| 754 |
+
"grad_norm": 0.408657044172287,
|
| 755 |
+
"learning_rate": 0.00021019244476122595,
|
| 756 |
+
"loss": 0.9849,
|
| 757 |
+
"step": 420
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.3,
|
| 761 |
+
"eval_loss": 0.9595761299133301,
|
| 762 |
+
"eval_runtime": 428.7767,
|
| 763 |
+
"eval_samples_per_second": 26.188,
|
| 764 |
+
"eval_steps_per_second": 3.274,
|
| 765 |
+
"step": 420
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.3,
|
| 769 |
+
"grad_norm": 0.3261207640171051,
|
| 770 |
+
"learning_rate": 0.00020912330719885958,
|
| 771 |
+
"loss": 0.9458,
|
| 772 |
+
"step": 425
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.31,
|
| 776 |
+
"grad_norm": 0.38089486956596375,
|
| 777 |
+
"learning_rate": 0.0002080541696364932,
|
| 778 |
+
"loss": 0.9789,
|
| 779 |
+
"step": 430
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.31,
|
| 783 |
+
"grad_norm": 0.33345696330070496,
|
| 784 |
+
"learning_rate": 0.00020698503207412685,
|
| 785 |
+
"loss": 0.9492,
|
| 786 |
+
"step": 435
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.31,
|
| 790 |
+
"grad_norm": 0.4079163074493408,
|
| 791 |
+
"learning_rate": 0.0002059158945117605,
|
| 792 |
+
"loss": 0.9628,
|
| 793 |
+
"step": 440
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.31,
|
| 797 |
+
"eval_loss": 0.9577447175979614,
|
| 798 |
+
"eval_runtime": 428.7333,
|
| 799 |
+
"eval_samples_per_second": 26.191,
|
| 800 |
+
"eval_steps_per_second": 3.275,
|
| 801 |
+
"step": 440
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.32,
|
| 805 |
+
"grad_norm": 0.3896418511867523,
|
| 806 |
+
"learning_rate": 0.00020484675694939415,
|
| 807 |
+
"loss": 0.9968,
|
| 808 |
+
"step": 445
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.32,
|
| 812 |
+
"grad_norm": 0.48451879620552063,
|
| 813 |
+
"learning_rate": 0.00020377761938702776,
|
| 814 |
+
"loss": 0.9276,
|
| 815 |
+
"step": 450
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.32,
|
| 819 |
+
"grad_norm": 0.3475559651851654,
|
| 820 |
+
"learning_rate": 0.00020270848182466143,
|
| 821 |
+
"loss": 0.9545,
|
| 822 |
+
"step": 455
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.33,
|
| 826 |
+
"grad_norm": 0.39289623498916626,
|
| 827 |
+
"learning_rate": 0.00020163934426229506,
|
| 828 |
+
"loss": 0.942,
|
| 829 |
+
"step": 460
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.33,
|
| 833 |
+
"eval_loss": 0.9580677151679993,
|
| 834 |
+
"eval_runtime": 429.8733,
|
| 835 |
+
"eval_samples_per_second": 26.122,
|
| 836 |
+
"eval_steps_per_second": 3.266,
|
| 837 |
+
"step": 460
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.33,
|
| 841 |
+
"grad_norm": 0.4262286424636841,
|
| 842 |
+
"learning_rate": 0.00020057020669992872,
|
| 843 |
+
"loss": 0.9626,
|
| 844 |
+
"step": 465
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.33,
|
| 848 |
+
"grad_norm": 0.32213443517684937,
|
| 849 |
+
"learning_rate": 0.00019950106913756233,
|
| 850 |
+
"loss": 0.9654,
|
| 851 |
+
"step": 470
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.34,
|
| 855 |
+
"grad_norm": 0.5463011264801025,
|
| 856 |
+
"learning_rate": 0.000198431931575196,
|
| 857 |
+
"loss": 0.9739,
|
| 858 |
+
"step": 475
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.34,
|
| 862 |
+
"grad_norm": 0.43018388748168945,
|
| 863 |
+
"learning_rate": 0.00019736279401282963,
|
| 864 |
+
"loss": 0.9712,
|
| 865 |
+
"step": 480
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.34,
|
| 869 |
+
"eval_loss": 0.955605149269104,
|
| 870 |
+
"eval_runtime": 430.0606,
|
| 871 |
+
"eval_samples_per_second": 26.11,
|
| 872 |
+
"eval_steps_per_second": 3.265,
|
| 873 |
+
"step": 480
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.35,
|
| 877 |
+
"grad_norm": 0.3303755819797516,
|
| 878 |
+
"learning_rate": 0.0001962936564504633,
|
| 879 |
+
"loss": 0.9799,
|
| 880 |
+
"step": 485
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.35,
|
| 884 |
+
"grad_norm": 0.35282695293426514,
|
| 885 |
+
"learning_rate": 0.0001952245188880969,
|
| 886 |
+
"loss": 0.9797,
|
| 887 |
+
"step": 490
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.35,
|
| 891 |
+
"grad_norm": 0.7973325848579407,
|
| 892 |
+
"learning_rate": 0.00019415538132573057,
|
| 893 |
+
"loss": 0.9733,
|
| 894 |
+
"step": 495
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.36,
|
| 898 |
+
"grad_norm": 0.46459755301475525,
|
| 899 |
+
"learning_rate": 0.0001930862437633642,
|
| 900 |
+
"loss": 0.9368,
|
| 901 |
+
"step": 500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.36,
|
| 905 |
+
"eval_loss": 0.9580536484718323,
|
| 906 |
+
"eval_runtime": 429.9689,
|
| 907 |
+
"eval_samples_per_second": 26.116,
|
| 908 |
+
"eval_steps_per_second": 3.265,
|
| 909 |
+
"step": 500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.36,
|
| 913 |
+
"grad_norm": 0.4230199158191681,
|
| 914 |
+
"learning_rate": 0.00019201710620099787,
|
| 915 |
+
"loss": 0.9822,
|
| 916 |
+
"step": 505
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.36,
|
| 920 |
+
"grad_norm": 0.3397184908390045,
|
| 921 |
+
"learning_rate": 0.00019094796863863148,
|
| 922 |
+
"loss": 0.9522,
|
| 923 |
+
"step": 510
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.37,
|
| 927 |
+
"grad_norm": 0.6563906073570251,
|
| 928 |
+
"learning_rate": 0.0001898788310762651,
|
| 929 |
+
"loss": 1.0053,
|
| 930 |
+
"step": 515
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.37,
|
| 934 |
+
"grad_norm": 0.29375872015953064,
|
| 935 |
+
"learning_rate": 0.00018880969351389878,
|
| 936 |
+
"loss": 0.9623,
|
| 937 |
+
"step": 520
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.37,
|
| 941 |
+
"eval_loss": 0.9542292356491089,
|
| 942 |
+
"eval_runtime": 429.8107,
|
| 943 |
+
"eval_samples_per_second": 26.125,
|
| 944 |
+
"eval_steps_per_second": 3.267,
|
| 945 |
+
"step": 520
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.37,
|
| 949 |
+
"grad_norm": 0.37316498160362244,
|
| 950 |
+
"learning_rate": 0.0001877405559515324,
|
| 951 |
+
"loss": 0.9615,
|
| 952 |
+
"step": 525
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 0.38,
|
| 956 |
+
"grad_norm": 0.447251558303833,
|
| 957 |
+
"learning_rate": 0.00018667141838916605,
|
| 958 |
+
"loss": 0.9654,
|
| 959 |
+
"step": 530
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.38,
|
| 963 |
+
"grad_norm": 0.4220346510410309,
|
| 964 |
+
"learning_rate": 0.00018560228082679968,
|
| 965 |
+
"loss": 0.9912,
|
| 966 |
+
"step": 535
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.38,
|
| 970 |
+
"grad_norm": 0.4119402766227722,
|
| 971 |
+
"learning_rate": 0.00018453314326443335,
|
| 972 |
+
"loss": 0.9884,
|
| 973 |
+
"step": 540
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.38,
|
| 977 |
+
"eval_loss": 0.9527921080589294,
|
| 978 |
+
"eval_runtime": 429.6973,
|
| 979 |
+
"eval_samples_per_second": 26.132,
|
| 980 |
+
"eval_steps_per_second": 3.267,
|
| 981 |
+
"step": 540
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.39,
|
| 985 |
+
"grad_norm": 0.370868057012558,
|
| 986 |
+
"learning_rate": 0.00018346400570206698,
|
| 987 |
+
"loss": 0.9405,
|
| 988 |
+
"step": 545
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.39,
|
| 992 |
+
"grad_norm": 0.3117481768131256,
|
| 993 |
+
"learning_rate": 0.00018239486813970065,
|
| 994 |
+
"loss": 0.951,
|
| 995 |
+
"step": 550
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.4,
|
| 999 |
+
"grad_norm": 0.3839544355869293,
|
| 1000 |
+
"learning_rate": 0.00018132573057733425,
|
| 1001 |
+
"loss": 0.9802,
|
| 1002 |
+
"step": 555
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.4,
|
| 1006 |
+
"grad_norm": 0.28429457545280457,
|
| 1007 |
+
"learning_rate": 0.00018025659301496792,
|
| 1008 |
+
"loss": 0.9313,
|
| 1009 |
+
"step": 560
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.4,
|
| 1013 |
+
"eval_loss": 0.9514893293380737,
|
| 1014 |
+
"eval_runtime": 429.9336,
|
| 1015 |
+
"eval_samples_per_second": 26.118,
|
| 1016 |
+
"eval_steps_per_second": 3.266,
|
| 1017 |
+
"step": 560
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.4,
|
| 1021 |
+
"grad_norm": 0.36404356360435486,
|
| 1022 |
+
"learning_rate": 0.00017918745545260155,
|
| 1023 |
+
"loss": 0.9582,
|
| 1024 |
+
"step": 565
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.41,
|
| 1028 |
+
"grad_norm": 0.33048421144485474,
|
| 1029 |
+
"learning_rate": 0.00017811831789023522,
|
| 1030 |
+
"loss": 0.95,
|
| 1031 |
+
"step": 570
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.41,
|
| 1035 |
+
"grad_norm": 0.3449236750602722,
|
| 1036 |
+
"learning_rate": 0.00017704918032786883,
|
| 1037 |
+
"loss": 0.9765,
|
| 1038 |
+
"step": 575
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.41,
|
| 1042 |
+
"grad_norm": 0.3965567350387573,
|
| 1043 |
+
"learning_rate": 0.0001759800427655025,
|
| 1044 |
+
"loss": 0.9743,
|
| 1045 |
+
"step": 580
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.41,
|
| 1049 |
+
"eval_loss": 0.9508348107337952,
|
| 1050 |
+
"eval_runtime": 429.4982,
|
| 1051 |
+
"eval_samples_per_second": 26.144,
|
| 1052 |
+
"eval_steps_per_second": 3.269,
|
| 1053 |
+
"step": 580
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.42,
|
| 1057 |
+
"grad_norm": 0.491098552942276,
|
| 1058 |
+
"learning_rate": 0.00017491090520313613,
|
| 1059 |
+
"loss": 0.9843,
|
| 1060 |
+
"step": 585
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.42,
|
| 1064 |
+
"grad_norm": 0.3687509298324585,
|
| 1065 |
+
"learning_rate": 0.0001738417676407698,
|
| 1066 |
+
"loss": 0.9936,
|
| 1067 |
+
"step": 590
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.42,
|
| 1071 |
+
"grad_norm": 0.33909574151039124,
|
| 1072 |
+
"learning_rate": 0.0001727726300784034,
|
| 1073 |
+
"loss": 0.9334,
|
| 1074 |
+
"step": 595
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.43,
|
| 1078 |
+
"grad_norm": 0.36044976115226746,
|
| 1079 |
+
"learning_rate": 0.00017170349251603703,
|
| 1080 |
+
"loss": 0.9805,
|
| 1081 |
+
"step": 600
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.43,
|
| 1085 |
+
"eval_loss": 0.9498609900474548,
|
| 1086 |
+
"eval_runtime": 429.1598,
|
| 1087 |
+
"eval_samples_per_second": 26.165,
|
| 1088 |
+
"eval_steps_per_second": 3.272,
|
| 1089 |
+
"step": 600
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.43,
|
| 1093 |
+
"grad_norm": 0.28610169887542725,
|
| 1094 |
+
"learning_rate": 0.0001706343549536707,
|
| 1095 |
+
"loss": 0.9513,
|
| 1096 |
+
"step": 605
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.43,
|
| 1100 |
+
"grad_norm": 0.29482224583625793,
|
| 1101 |
+
"learning_rate": 0.00016956521739130433,
|
| 1102 |
+
"loss": 0.9313,
|
| 1103 |
+
"step": 610
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 0.44,
|
| 1107 |
+
"grad_norm": 0.46972745656967163,
|
| 1108 |
+
"learning_rate": 0.00016849607982893797,
|
| 1109 |
+
"loss": 0.9753,
|
| 1110 |
+
"step": 615
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 0.44,
|
| 1114 |
+
"grad_norm": 0.38324683904647827,
|
| 1115 |
+
"learning_rate": 0.0001674269422665716,
|
| 1116 |
+
"loss": 0.9759,
|
| 1117 |
+
"step": 620
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 0.44,
|
| 1121 |
+
"eval_loss": 0.949146568775177,
|
| 1122 |
+
"eval_runtime": 430.2097,
|
| 1123 |
+
"eval_samples_per_second": 26.101,
|
| 1124 |
+
"eval_steps_per_second": 3.264,
|
| 1125 |
+
"step": 620
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.45,
|
| 1129 |
+
"grad_norm": 0.4306158125400543,
|
| 1130 |
+
"learning_rate": 0.00016635780470420527,
|
| 1131 |
+
"loss": 0.9788,
|
| 1132 |
+
"step": 625
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.45,
|
| 1136 |
+
"grad_norm": 0.49315810203552246,
|
| 1137 |
+
"learning_rate": 0.0001652886671418389,
|
| 1138 |
+
"loss": 0.9636,
|
| 1139 |
+
"step": 630
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.45,
|
| 1143 |
+
"grad_norm": 0.4102541506290436,
|
| 1144 |
+
"learning_rate": 0.00016421952957947254,
|
| 1145 |
+
"loss": 0.9957,
|
| 1146 |
+
"step": 635
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.46,
|
| 1150 |
+
"grad_norm": 0.40014615654945374,
|
| 1151 |
+
"learning_rate": 0.00016315039201710618,
|
| 1152 |
+
"loss": 0.9468,
|
| 1153 |
+
"step": 640
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.46,
|
| 1157 |
+
"eval_loss": 0.9478526711463928,
|
| 1158 |
+
"eval_runtime": 429.5532,
|
| 1159 |
+
"eval_samples_per_second": 26.141,
|
| 1160 |
+
"eval_steps_per_second": 3.269,
|
| 1161 |
+
"step": 640
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.46,
|
| 1165 |
+
"grad_norm": 0.3694494962692261,
|
| 1166 |
+
"learning_rate": 0.00016208125445473984,
|
| 1167 |
+
"loss": 0.9824,
|
| 1168 |
+
"step": 645
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.46,
|
| 1172 |
+
"grad_norm": 0.37701812386512756,
|
| 1173 |
+
"learning_rate": 0.00016101211689237348,
|
| 1174 |
+
"loss": 0.9274,
|
| 1175 |
+
"step": 650
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.47,
|
| 1179 |
+
"grad_norm": 0.3787167966365814,
|
| 1180 |
+
"learning_rate": 0.00015994297933000714,
|
| 1181 |
+
"loss": 0.9719,
|
| 1182 |
+
"step": 655
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.47,
|
| 1186 |
+
"grad_norm": 0.48614123463630676,
|
| 1187 |
+
"learning_rate": 0.00015887384176764075,
|
| 1188 |
+
"loss": 0.9593,
|
| 1189 |
+
"step": 660
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.47,
|
| 1193 |
+
"eval_loss": 0.9467563629150391,
|
| 1194 |
+
"eval_runtime": 430.6789,
|
| 1195 |
+
"eval_samples_per_second": 26.073,
|
| 1196 |
+
"eval_steps_per_second": 3.26,
|
| 1197 |
+
"step": 660
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.47,
|
| 1201 |
+
"grad_norm": 0.35638296604156494,
|
| 1202 |
+
"learning_rate": 0.0001578047042052744,
|
| 1203 |
+
"loss": 0.9862,
|
| 1204 |
+
"step": 665
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 0.48,
|
| 1208 |
+
"grad_norm": 0.27917659282684326,
|
| 1209 |
+
"learning_rate": 0.00015673556664290805,
|
| 1210 |
+
"loss": 0.9504,
|
| 1211 |
+
"step": 670
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.48,
|
| 1215 |
+
"grad_norm": 0.34654778242111206,
|
| 1216 |
+
"learning_rate": 0.0001556664290805417,
|
| 1217 |
+
"loss": 0.9428,
|
| 1218 |
+
"step": 675
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.48,
|
| 1222 |
+
"grad_norm": 0.2783154845237732,
|
| 1223 |
+
"learning_rate": 0.00015459729151817532,
|
| 1224 |
+
"loss": 0.9242,
|
| 1225 |
+
"step": 680
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.48,
|
| 1229 |
+
"eval_loss": 0.9472882151603699,
|
| 1230 |
+
"eval_runtime": 428.9437,
|
| 1231 |
+
"eval_samples_per_second": 26.178,
|
| 1232 |
+
"eval_steps_per_second": 3.273,
|
| 1233 |
+
"step": 680
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.49,
|
| 1237 |
+
"grad_norm": 0.3296685814857483,
|
| 1238 |
+
"learning_rate": 0.00015352815395580896,
|
| 1239 |
+
"loss": 0.9817,
|
| 1240 |
+
"step": 685
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 0.49,
|
| 1244 |
+
"grad_norm": 0.35922589898109436,
|
| 1245 |
+
"learning_rate": 0.00015245901639344262,
|
| 1246 |
+
"loss": 0.904,
|
| 1247 |
+
"step": 690
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 0.5,
|
| 1251 |
+
"grad_norm": 0.33108726143836975,
|
| 1252 |
+
"learning_rate": 0.00015138987883107623,
|
| 1253 |
+
"loss": 0.9537,
|
| 1254 |
+
"step": 695
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 0.5,
|
| 1258 |
+
"grad_norm": 0.3146369457244873,
|
| 1259 |
+
"learning_rate": 0.0001503207412687099,
|
| 1260 |
+
"loss": 0.9594,
|
| 1261 |
+
"step": 700
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.5,
|
| 1265 |
+
"eval_loss": 0.9462445974349976,
|
| 1266 |
+
"eval_runtime": 430.3498,
|
| 1267 |
+
"eval_samples_per_second": 26.093,
|
| 1268 |
+
"eval_steps_per_second": 3.262,
|
| 1269 |
+
"step": 700
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.5,
|
| 1273 |
+
"grad_norm": 0.3020135164260864,
|
| 1274 |
+
"learning_rate": 0.00014925160370634355,
|
| 1275 |
+
"loss": 0.9947,
|
| 1276 |
+
"step": 705
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.51,
|
| 1280 |
+
"grad_norm": 0.33066317439079285,
|
| 1281 |
+
"learning_rate": 0.0001481824661439772,
|
| 1282 |
+
"loss": 0.926,
|
| 1283 |
+
"step": 710
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.51,
|
| 1287 |
+
"grad_norm": 0.3479137420654297,
|
| 1288 |
+
"learning_rate": 0.00014711332858161083,
|
| 1289 |
+
"loss": 0.9388,
|
| 1290 |
+
"step": 715
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.51,
|
| 1294 |
+
"grad_norm": 0.4258211851119995,
|
| 1295 |
+
"learning_rate": 0.00014604419101924446,
|
| 1296 |
+
"loss": 0.9587,
|
| 1297 |
+
"step": 720
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.51,
|
| 1301 |
+
"eval_loss": 0.9459365606307983,
|
| 1302 |
+
"eval_runtime": 429.6711,
|
| 1303 |
+
"eval_samples_per_second": 26.134,
|
| 1304 |
+
"eval_steps_per_second": 3.268,
|
| 1305 |
+
"step": 720
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.52,
|
| 1309 |
+
"grad_norm": 0.33177533745765686,
|
| 1310 |
+
"learning_rate": 0.0001449750534568781,
|
| 1311 |
+
"loss": 0.9466,
|
| 1312 |
+
"step": 725
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.52,
|
| 1316 |
+
"grad_norm": 0.36505717039108276,
|
| 1317 |
+
"learning_rate": 0.00014390591589451173,
|
| 1318 |
+
"loss": 0.9591,
|
| 1319 |
+
"step": 730
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.52,
|
| 1323 |
+
"grad_norm": 0.2933894693851471,
|
| 1324 |
+
"learning_rate": 0.0001428367783321454,
|
| 1325 |
+
"loss": 0.9857,
|
| 1326 |
+
"step": 735
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.53,
|
| 1330 |
+
"grad_norm": 0.30695998668670654,
|
| 1331 |
+
"learning_rate": 0.00014176764076977903,
|
| 1332 |
+
"loss": 0.9311,
|
| 1333 |
+
"step": 740
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.53,
|
| 1337 |
+
"eval_loss": 0.9447991251945496,
|
| 1338 |
+
"eval_runtime": 429.4504,
|
| 1339 |
+
"eval_samples_per_second": 26.147,
|
| 1340 |
+
"eval_steps_per_second": 3.269,
|
| 1341 |
+
"step": 740
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.53,
|
| 1345 |
+
"grad_norm": 0.37066712975502014,
|
| 1346 |
+
"learning_rate": 0.00014069850320741267,
|
| 1347 |
+
"loss": 0.9075,
|
| 1348 |
+
"step": 745
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 0.53,
|
| 1352 |
+
"grad_norm": 0.3553217053413391,
|
| 1353 |
+
"learning_rate": 0.0001396293656450463,
|
| 1354 |
+
"loss": 0.9355,
|
| 1355 |
+
"step": 750
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 0.54,
|
| 1359 |
+
"grad_norm": 0.3907565176486969,
|
| 1360 |
+
"learning_rate": 0.00013856022808267997,
|
| 1361 |
+
"loss": 0.9593,
|
| 1362 |
+
"step": 755
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.54,
|
| 1366 |
+
"grad_norm": 0.35674384236335754,
|
| 1367 |
+
"learning_rate": 0.0001374910905203136,
|
| 1368 |
+
"loss": 0.9485,
|
| 1369 |
+
"step": 760
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.54,
|
| 1373 |
+
"eval_loss": 0.9437533617019653,
|
| 1374 |
+
"eval_runtime": 430.5708,
|
| 1375 |
+
"eval_samples_per_second": 26.079,
|
| 1376 |
+
"eval_steps_per_second": 3.261,
|
| 1377 |
+
"step": 760
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.55,
|
| 1381 |
+
"grad_norm": 0.39057737588882446,
|
| 1382 |
+
"learning_rate": 0.00013642195295794724,
|
| 1383 |
+
"loss": 0.9201,
|
| 1384 |
+
"step": 765
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.55,
|
| 1388 |
+
"grad_norm": 0.2841975688934326,
|
| 1389 |
+
"learning_rate": 0.00013535281539558088,
|
| 1390 |
+
"loss": 0.9466,
|
| 1391 |
+
"step": 770
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.55,
|
| 1395 |
+
"grad_norm": 0.38508614897727966,
|
| 1396 |
+
"learning_rate": 0.00013428367783321454,
|
| 1397 |
+
"loss": 0.9772,
|
| 1398 |
+
"step": 775
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.56,
|
| 1402 |
+
"grad_norm": 0.3465386629104614,
|
| 1403 |
+
"learning_rate": 0.00013321454027084818,
|
| 1404 |
+
"loss": 0.9974,
|
| 1405 |
+
"step": 780
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.56,
|
| 1409 |
+
"eval_loss": 0.9442404508590698,
|
| 1410 |
+
"eval_runtime": 429.5011,
|
| 1411 |
+
"eval_samples_per_second": 26.144,
|
| 1412 |
+
"eval_steps_per_second": 3.269,
|
| 1413 |
+
"step": 780
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.56,
|
| 1417 |
+
"grad_norm": 0.360097199678421,
|
| 1418 |
+
"learning_rate": 0.0001321454027084818,
|
| 1419 |
+
"loss": 0.9725,
|
| 1420 |
+
"step": 785
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.56,
|
| 1424 |
+
"grad_norm": 0.34066542983055115,
|
| 1425 |
+
"learning_rate": 0.00013107626514611545,
|
| 1426 |
+
"loss": 1.0158,
|
| 1427 |
+
"step": 790
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.57,
|
| 1431 |
+
"grad_norm": 0.3403652608394623,
|
| 1432 |
+
"learning_rate": 0.0001300071275837491,
|
| 1433 |
+
"loss": 0.927,
|
| 1434 |
+
"step": 795
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.57,
|
| 1438 |
+
"grad_norm": 0.33237767219543457,
|
| 1439 |
+
"learning_rate": 0.00012893799002138275,
|
| 1440 |
+
"loss": 0.9516,
|
| 1441 |
+
"step": 800
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.57,
|
| 1445 |
+
"eval_loss": 0.9429513216018677,
|
| 1446 |
+
"eval_runtime": 429.3919,
|
| 1447 |
+
"eval_samples_per_second": 26.151,
|
| 1448 |
+
"eval_steps_per_second": 3.27,
|
| 1449 |
+
"step": 800
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.57,
|
| 1453 |
+
"grad_norm": 0.33179551362991333,
|
| 1454 |
+
"learning_rate": 0.00012786885245901638,
|
| 1455 |
+
"loss": 0.922,
|
| 1456 |
+
"step": 805
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.58,
|
| 1460 |
+
"grad_norm": 0.3568633794784546,
|
| 1461 |
+
"learning_rate": 0.00012679971489665002,
|
| 1462 |
+
"loss": 0.9434,
|
| 1463 |
+
"step": 810
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.58,
|
| 1467 |
+
"grad_norm": 0.4287993907928467,
|
| 1468 |
+
"learning_rate": 0.00012573057733428366,
|
| 1469 |
+
"loss": 0.9496,
|
| 1470 |
+
"step": 815
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.58,
|
| 1474 |
+
"grad_norm": 0.3873540461063385,
|
| 1475 |
+
"learning_rate": 0.0001246614397719173,
|
| 1476 |
+
"loss": 0.9476,
|
| 1477 |
+
"step": 820
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.58,
|
| 1481 |
+
"eval_loss": 0.942284107208252,
|
| 1482 |
+
"eval_runtime": 429.6801,
|
| 1483 |
+
"eval_samples_per_second": 26.133,
|
| 1484 |
+
"eval_steps_per_second": 3.268,
|
| 1485 |
+
"step": 820
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.59,
|
| 1489 |
+
"grad_norm": 0.5366536974906921,
|
| 1490 |
+
"learning_rate": 0.00012359230220955095,
|
| 1491 |
+
"loss": 0.9609,
|
| 1492 |
+
"step": 825
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.59,
|
| 1496 |
+
"grad_norm": 0.38116729259490967,
|
| 1497 |
+
"learning_rate": 0.0001225231646471846,
|
| 1498 |
+
"loss": 0.946,
|
| 1499 |
+
"step": 830
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.59,
|
| 1503 |
+
"grad_norm": 0.3352102041244507,
|
| 1504 |
+
"learning_rate": 0.00012145402708481824,
|
| 1505 |
+
"loss": 0.9487,
|
| 1506 |
+
"step": 835
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.6,
|
| 1510 |
+
"grad_norm": 0.314010888338089,
|
| 1511 |
+
"learning_rate": 0.00012038488952245188,
|
| 1512 |
+
"loss": 0.951,
|
| 1513 |
+
"step": 840
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.6,
|
| 1517 |
+
"eval_loss": 0.9439210295677185,
|
| 1518 |
+
"eval_runtime": 429.6236,
|
| 1519 |
+
"eval_samples_per_second": 26.137,
|
| 1520 |
+
"eval_steps_per_second": 3.268,
|
| 1521 |
+
"step": 840
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.6,
|
| 1525 |
+
"grad_norm": 0.359325647354126,
|
| 1526 |
+
"learning_rate": 0.00011931575196008553,
|
| 1527 |
+
"loss": 0.9628,
|
| 1528 |
+
"step": 845
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.61,
|
| 1532 |
+
"grad_norm": 0.5471125841140747,
|
| 1533 |
+
"learning_rate": 0.00011824661439771916,
|
| 1534 |
+
"loss": 0.9581,
|
| 1535 |
+
"step": 850
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.61,
|
| 1539 |
+
"grad_norm": 0.5925132632255554,
|
| 1540 |
+
"learning_rate": 0.00011717747683535281,
|
| 1541 |
+
"loss": 0.9777,
|
| 1542 |
+
"step": 855
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.61,
|
| 1546 |
+
"grad_norm": 0.3140357732772827,
|
| 1547 |
+
"learning_rate": 0.00011610833927298645,
|
| 1548 |
+
"loss": 0.9269,
|
| 1549 |
+
"step": 860
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.61,
|
| 1553 |
+
"eval_loss": 0.9412524700164795,
|
| 1554 |
+
"eval_runtime": 429.1443,
|
| 1555 |
+
"eval_samples_per_second": 26.166,
|
| 1556 |
+
"eval_steps_per_second": 3.272,
|
| 1557 |
+
"step": 860
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.62,
|
| 1561 |
+
"grad_norm": 0.3626731038093567,
|
| 1562 |
+
"learning_rate": 0.0001150392017106201,
|
| 1563 |
+
"loss": 0.9668,
|
| 1564 |
+
"step": 865
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.62,
|
| 1568 |
+
"grad_norm": 0.31055352091789246,
|
| 1569 |
+
"learning_rate": 0.00011397006414825373,
|
| 1570 |
+
"loss": 0.9272,
|
| 1571 |
+
"step": 870
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.62,
|
| 1575 |
+
"grad_norm": 0.3563440144062042,
|
| 1576 |
+
"learning_rate": 0.00011290092658588738,
|
| 1577 |
+
"loss": 0.9574,
|
| 1578 |
+
"step": 875
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.63,
|
| 1582 |
+
"grad_norm": 0.44283735752105713,
|
| 1583 |
+
"learning_rate": 0.00011183178902352102,
|
| 1584 |
+
"loss": 0.9294,
|
| 1585 |
+
"step": 880
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.63,
|
| 1589 |
+
"eval_loss": 0.9413205981254578,
|
| 1590 |
+
"eval_runtime": 430.6763,
|
| 1591 |
+
"eval_samples_per_second": 26.073,
|
| 1592 |
+
"eval_steps_per_second": 3.26,
|
| 1593 |
+
"step": 880
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.63,
|
| 1597 |
+
"grad_norm": 0.41935306787490845,
|
| 1598 |
+
"learning_rate": 0.00011076265146115467,
|
| 1599 |
+
"loss": 0.9551,
|
| 1600 |
+
"step": 885
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.63,
|
| 1604 |
+
"grad_norm": 0.3747510612010956,
|
| 1605 |
+
"learning_rate": 0.00010969351389878829,
|
| 1606 |
+
"loss": 0.9838,
|
| 1607 |
+
"step": 890
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.64,
|
| 1611 |
+
"grad_norm": 0.343944251537323,
|
| 1612 |
+
"learning_rate": 0.00010862437633642194,
|
| 1613 |
+
"loss": 0.9927,
|
| 1614 |
+
"step": 895
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.64,
|
| 1618 |
+
"grad_norm": 0.4465276598930359,
|
| 1619 |
+
"learning_rate": 0.00010755523877405558,
|
| 1620 |
+
"loss": 1.0054,
|
| 1621 |
+
"step": 900
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.64,
|
| 1625 |
+
"eval_loss": 0.9400754570960999,
|
| 1626 |
+
"eval_runtime": 428.8696,
|
| 1627 |
+
"eval_samples_per_second": 26.183,
|
| 1628 |
+
"eval_steps_per_second": 3.274,
|
| 1629 |
+
"step": 900
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.64,
|
| 1633 |
+
"grad_norm": 0.3230556845664978,
|
| 1634 |
+
"learning_rate": 0.00010648610121168923,
|
| 1635 |
+
"loss": 0.9675,
|
| 1636 |
+
"step": 905
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 0.65,
|
| 1640 |
+
"grad_norm": 0.384182333946228,
|
| 1641 |
+
"learning_rate": 0.00010541696364932286,
|
| 1642 |
+
"loss": 0.9806,
|
| 1643 |
+
"step": 910
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 0.65,
|
| 1647 |
+
"grad_norm": 0.3371874690055847,
|
| 1648 |
+
"learning_rate": 0.00010434782608695651,
|
| 1649 |
+
"loss": 0.9508,
|
| 1650 |
+
"step": 915
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 0.66,
|
| 1654 |
+
"grad_norm": 0.3343549370765686,
|
| 1655 |
+
"learning_rate": 0.00010327868852459015,
|
| 1656 |
+
"loss": 0.964,
|
| 1657 |
+
"step": 920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.66,
|
| 1661 |
+
"eval_loss": 0.9393041729927063,
|
| 1662 |
+
"eval_runtime": 429.8253,
|
| 1663 |
+
"eval_samples_per_second": 26.125,
|
| 1664 |
+
"eval_steps_per_second": 3.266,
|
| 1665 |
+
"step": 920
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.66,
|
| 1669 |
+
"grad_norm": 0.35873135924339294,
|
| 1670 |
+
"learning_rate": 0.0001022095509622238,
|
| 1671 |
+
"loss": 0.9702,
|
| 1672 |
+
"step": 925
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 0.66,
|
| 1676 |
+
"grad_norm": 0.34200361371040344,
|
| 1677 |
+
"learning_rate": 0.00010114041339985743,
|
| 1678 |
+
"loss": 0.9559,
|
| 1679 |
+
"step": 930
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 0.67,
|
| 1683 |
+
"grad_norm": 0.37706607580184937,
|
| 1684 |
+
"learning_rate": 0.00010007127583749108,
|
| 1685 |
+
"loss": 0.9392,
|
| 1686 |
+
"step": 935
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 0.67,
|
| 1690 |
+
"grad_norm": 0.37498244643211365,
|
| 1691 |
+
"learning_rate": 9.900213827512472e-05,
|
| 1692 |
+
"loss": 0.8863,
|
| 1693 |
+
"step": 940
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.67,
|
| 1697 |
+
"eval_loss": 0.9388808608055115,
|
| 1698 |
+
"eval_runtime": 428.8283,
|
| 1699 |
+
"eval_samples_per_second": 26.185,
|
| 1700 |
+
"eval_steps_per_second": 3.274,
|
| 1701 |
+
"step": 940
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.67,
|
| 1705 |
+
"grad_norm": 0.29014042019844055,
|
| 1706 |
+
"learning_rate": 9.793300071275837e-05,
|
| 1707 |
+
"loss": 0.9793,
|
| 1708 |
+
"step": 945
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 0.68,
|
| 1712 |
+
"grad_norm": 0.5693466663360596,
|
| 1713 |
+
"learning_rate": 9.686386315039202e-05,
|
| 1714 |
+
"loss": 1.0071,
|
| 1715 |
+
"step": 950
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 0.68,
|
| 1719 |
+
"grad_norm": 0.3804801106452942,
|
| 1720 |
+
"learning_rate": 9.579472558802566e-05,
|
| 1721 |
+
"loss": 1.0006,
|
| 1722 |
+
"step": 955
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.68,
|
| 1726 |
+
"grad_norm": 0.3488084673881531,
|
| 1727 |
+
"learning_rate": 9.47255880256593e-05,
|
| 1728 |
+
"loss": 0.9766,
|
| 1729 |
+
"step": 960
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.68,
|
| 1733 |
+
"eval_loss": 0.9387741684913635,
|
| 1734 |
+
"eval_runtime": 430.4724,
|
| 1735 |
+
"eval_samples_per_second": 26.085,
|
| 1736 |
+
"eval_steps_per_second": 3.262,
|
| 1737 |
+
"step": 960
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.69,
|
| 1741 |
+
"grad_norm": 0.3514138460159302,
|
| 1742 |
+
"learning_rate": 9.365645046329294e-05,
|
| 1743 |
+
"loss": 0.9362,
|
| 1744 |
+
"step": 965
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 0.69,
|
| 1748 |
+
"grad_norm": 0.2945019602775574,
|
| 1749 |
+
"learning_rate": 9.258731290092659e-05,
|
| 1750 |
+
"loss": 0.9354,
|
| 1751 |
+
"step": 970
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 0.69,
|
| 1755 |
+
"grad_norm": 0.41364601254463196,
|
| 1756 |
+
"learning_rate": 9.151817533856021e-05,
|
| 1757 |
+
"loss": 0.9893,
|
| 1758 |
+
"step": 975
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 0.7,
|
| 1762 |
+
"grad_norm": 0.3566943109035492,
|
| 1763 |
+
"learning_rate": 9.044903777619385e-05,
|
| 1764 |
+
"loss": 0.9803,
|
| 1765 |
+
"step": 980
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 0.7,
|
| 1769 |
+
"eval_loss": 0.9385978579521179,
|
| 1770 |
+
"eval_runtime": 429.3426,
|
| 1771 |
+
"eval_samples_per_second": 26.154,
|
| 1772 |
+
"eval_steps_per_second": 3.27,
|
| 1773 |
+
"step": 980
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.7,
|
| 1777 |
+
"grad_norm": 0.3117084503173828,
|
| 1778 |
+
"learning_rate": 8.93799002138275e-05,
|
| 1779 |
+
"loss": 0.9584,
|
| 1780 |
+
"step": 985
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.71,
|
| 1784 |
+
"grad_norm": 0.3447965085506439,
|
| 1785 |
+
"learning_rate": 8.831076265146115e-05,
|
| 1786 |
+
"loss": 0.9283,
|
| 1787 |
+
"step": 990
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.71,
|
| 1791 |
+
"grad_norm": 0.43709927797317505,
|
| 1792 |
+
"learning_rate": 8.724162508909478e-05,
|
| 1793 |
+
"loss": 0.9653,
|
| 1794 |
+
"step": 995
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.71,
|
| 1798 |
+
"grad_norm": 0.30693626403808594,
|
| 1799 |
+
"learning_rate": 8.617248752672843e-05,
|
| 1800 |
+
"loss": 0.9367,
|
| 1801 |
+
"step": 1000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.71,
|
| 1805 |
+
"eval_loss": 0.938434898853302,
|
| 1806 |
+
"eval_runtime": 429.8587,
|
| 1807 |
+
"eval_samples_per_second": 26.123,
|
| 1808 |
+
"eval_steps_per_second": 3.266,
|
| 1809 |
+
"step": 1000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.72,
|
| 1813 |
+
"grad_norm": 0.3513086140155792,
|
| 1814 |
+
"learning_rate": 8.510334996436207e-05,
|
| 1815 |
+
"loss": 0.9486,
|
| 1816 |
+
"step": 1005
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.72,
|
| 1820 |
+
"grad_norm": 0.30035388469696045,
|
| 1821 |
+
"learning_rate": 8.403421240199572e-05,
|
| 1822 |
+
"loss": 0.9253,
|
| 1823 |
+
"step": 1010
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.72,
|
| 1827 |
+
"grad_norm": 0.34532248973846436,
|
| 1828 |
+
"learning_rate": 8.296507483962936e-05,
|
| 1829 |
+
"loss": 0.9817,
|
| 1830 |
+
"step": 1015
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.73,
|
| 1834 |
+
"grad_norm": 0.2752978205680847,
|
| 1835 |
+
"learning_rate": 8.1895937277263e-05,
|
| 1836 |
+
"loss": 0.9092,
|
| 1837 |
+
"step": 1020
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.73,
|
| 1841 |
+
"eval_loss": 0.9372485876083374,
|
| 1842 |
+
"eval_runtime": 429.979,
|
| 1843 |
+
"eval_samples_per_second": 26.115,
|
| 1844 |
+
"eval_steps_per_second": 3.265,
|
| 1845 |
+
"step": 1020
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 0.73,
|
| 1849 |
+
"grad_norm": 0.37310290336608887,
|
| 1850 |
+
"learning_rate": 8.082679971489664e-05,
|
| 1851 |
+
"loss": 0.9679,
|
| 1852 |
+
"step": 1025
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 0.73,
|
| 1856 |
+
"grad_norm": 0.26144835352897644,
|
| 1857 |
+
"learning_rate": 7.975766215253029e-05,
|
| 1858 |
+
"loss": 0.9374,
|
| 1859 |
+
"step": 1030
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 0.74,
|
| 1863 |
+
"grad_norm": 0.442670613527298,
|
| 1864 |
+
"learning_rate": 7.868852459016393e-05,
|
| 1865 |
+
"loss": 0.9386,
|
| 1866 |
+
"step": 1035
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 0.74,
|
| 1870 |
+
"grad_norm": 0.3123500347137451,
|
| 1871 |
+
"learning_rate": 7.761938702779758e-05,
|
| 1872 |
+
"loss": 0.9527,
|
| 1873 |
+
"step": 1040
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 0.74,
|
| 1877 |
+
"eval_loss": 0.9374279975891113,
|
| 1878 |
+
"eval_runtime": 428.7356,
|
| 1879 |
+
"eval_samples_per_second": 26.191,
|
| 1880 |
+
"eval_steps_per_second": 3.275,
|
| 1881 |
+
"step": 1040
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 0.74,
|
| 1885 |
+
"grad_norm": 0.34689196944236755,
|
| 1886 |
+
"learning_rate": 7.655024946543121e-05,
|
| 1887 |
+
"loss": 0.918,
|
| 1888 |
+
"step": 1045
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 0.75,
|
| 1892 |
+
"grad_norm": 0.25890424847602844,
|
| 1893 |
+
"learning_rate": 7.548111190306486e-05,
|
| 1894 |
+
"loss": 0.9131,
|
| 1895 |
+
"step": 1050
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 0.75,
|
| 1899 |
+
"grad_norm": 0.4108467102050781,
|
| 1900 |
+
"learning_rate": 7.44119743406985e-05,
|
| 1901 |
+
"loss": 0.9481,
|
| 1902 |
+
"step": 1055
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 0.76,
|
| 1906 |
+
"grad_norm": 0.3142194151878357,
|
| 1907 |
+
"learning_rate": 7.334283677833213e-05,
|
| 1908 |
+
"loss": 0.9503,
|
| 1909 |
+
"step": 1060
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 0.76,
|
| 1913 |
+
"eval_loss": 0.9363455772399902,
|
| 1914 |
+
"eval_runtime": 429.8697,
|
| 1915 |
+
"eval_samples_per_second": 26.122,
|
| 1916 |
+
"eval_steps_per_second": 3.266,
|
| 1917 |
+
"step": 1060
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.76,
|
| 1921 |
+
"grad_norm": 0.3752140402793884,
|
| 1922 |
+
"learning_rate": 7.227369921596578e-05,
|
| 1923 |
+
"loss": 0.9614,
|
| 1924 |
+
"step": 1065
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 0.76,
|
| 1928 |
+
"grad_norm": 0.3649095892906189,
|
| 1929 |
+
"learning_rate": 7.120456165359942e-05,
|
| 1930 |
+
"loss": 0.9428,
|
| 1931 |
+
"step": 1070
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 0.77,
|
| 1935 |
+
"grad_norm": 0.28237637877464294,
|
| 1936 |
+
"learning_rate": 7.013542409123307e-05,
|
| 1937 |
+
"loss": 0.9698,
|
| 1938 |
+
"step": 1075
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 0.77,
|
| 1942 |
+
"grad_norm": 0.32881519198417664,
|
| 1943 |
+
"learning_rate": 6.90662865288667e-05,
|
| 1944 |
+
"loss": 0.9494,
|
| 1945 |
+
"step": 1080
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.77,
|
| 1949 |
+
"eval_loss": 0.9357610940933228,
|
| 1950 |
+
"eval_runtime": 430.0153,
|
| 1951 |
+
"eval_samples_per_second": 26.113,
|
| 1952 |
+
"eval_steps_per_second": 3.265,
|
| 1953 |
+
"step": 1080
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 0.77,
|
| 1957 |
+
"grad_norm": 0.3415566086769104,
|
| 1958 |
+
"learning_rate": 6.799714896650034e-05,
|
| 1959 |
+
"loss": 0.9501,
|
| 1960 |
+
"step": 1085
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 0.78,
|
| 1964 |
+
"grad_norm": 0.3997558057308197,
|
| 1965 |
+
"learning_rate": 6.692801140413399e-05,
|
| 1966 |
+
"loss": 0.9423,
|
| 1967 |
+
"step": 1090
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 0.78,
|
| 1971 |
+
"grad_norm": 0.3917606472969055,
|
| 1972 |
+
"learning_rate": 6.585887384176763e-05,
|
| 1973 |
+
"loss": 0.9696,
|
| 1974 |
+
"step": 1095
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 0.78,
|
| 1978 |
+
"grad_norm": 0.6566518545150757,
|
| 1979 |
+
"learning_rate": 6.478973627940128e-05,
|
| 1980 |
+
"loss": 0.961,
|
| 1981 |
+
"step": 1100
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 0.78,
|
| 1985 |
+
"eval_loss": 0.936005711555481,
|
| 1986 |
+
"eval_runtime": 430.641,
|
| 1987 |
+
"eval_samples_per_second": 26.075,
|
| 1988 |
+
"eval_steps_per_second": 3.26,
|
| 1989 |
+
"step": 1100
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.79,
|
| 1993 |
+
"grad_norm": 0.2704831063747406,
|
| 1994 |
+
"learning_rate": 6.372059871703493e-05,
|
| 1995 |
+
"loss": 0.9316,
|
| 1996 |
+
"step": 1105
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.79,
|
| 2000 |
+
"grad_norm": 0.3626934885978699,
|
| 2001 |
+
"learning_rate": 6.265146115466856e-05,
|
| 2002 |
+
"loss": 0.942,
|
| 2003 |
+
"step": 1110
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.79,
|
| 2007 |
+
"grad_norm": 0.3050808310508728,
|
| 2008 |
+
"learning_rate": 6.158232359230221e-05,
|
| 2009 |
+
"loss": 0.9681,
|
| 2010 |
+
"step": 1115
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.8,
|
| 2014 |
+
"grad_norm": 0.33575522899627686,
|
| 2015 |
+
"learning_rate": 6.051318602993584e-05,
|
| 2016 |
+
"loss": 0.9675,
|
| 2017 |
+
"step": 1120
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.8,
|
| 2021 |
+
"eval_loss": 0.9356703758239746,
|
| 2022 |
+
"eval_runtime": 430.1349,
|
| 2023 |
+
"eval_samples_per_second": 26.106,
|
| 2024 |
+
"eval_steps_per_second": 3.264,
|
| 2025 |
+
"step": 1120
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.8,
|
| 2029 |
+
"grad_norm": 0.47601962089538574,
|
| 2030 |
+
"learning_rate": 5.9444048467569485e-05,
|
| 2031 |
+
"loss": 0.9837,
|
| 2032 |
+
"step": 1125
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.81,
|
| 2036 |
+
"grad_norm": 0.3533668518066406,
|
| 2037 |
+
"learning_rate": 5.837491090520313e-05,
|
| 2038 |
+
"loss": 0.9234,
|
| 2039 |
+
"step": 1130
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.81,
|
| 2043 |
+
"grad_norm": 0.32863783836364746,
|
| 2044 |
+
"learning_rate": 5.730577334283677e-05,
|
| 2045 |
+
"loss": 0.9773,
|
| 2046 |
+
"step": 1135
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.81,
|
| 2050 |
+
"grad_norm": 0.3788212835788727,
|
| 2051 |
+
"learning_rate": 5.6236635780470413e-05,
|
| 2052 |
+
"loss": 0.9704,
|
| 2053 |
+
"step": 1140
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.81,
|
| 2057 |
+
"eval_loss": 0.9352059364318848,
|
| 2058 |
+
"eval_runtime": 430.5021,
|
| 2059 |
+
"eval_samples_per_second": 26.083,
|
| 2060 |
+
"eval_steps_per_second": 3.261,
|
| 2061 |
+
"step": 1140
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.82,
|
| 2065 |
+
"grad_norm": 0.5751201510429382,
|
| 2066 |
+
"learning_rate": 5.5167498218104056e-05,
|
| 2067 |
+
"loss": 0.9367,
|
| 2068 |
+
"step": 1145
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.82,
|
| 2072 |
+
"grad_norm": 0.4319859445095062,
|
| 2073 |
+
"learning_rate": 5.40983606557377e-05,
|
| 2074 |
+
"loss": 0.9558,
|
| 2075 |
+
"step": 1150
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.82,
|
| 2079 |
+
"grad_norm": 0.35112935304641724,
|
| 2080 |
+
"learning_rate": 5.302922309337134e-05,
|
| 2081 |
+
"loss": 0.9123,
|
| 2082 |
+
"step": 1155
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.83,
|
| 2086 |
+
"grad_norm": 0.31719475984573364,
|
| 2087 |
+
"learning_rate": 5.196008553100499e-05,
|
| 2088 |
+
"loss": 0.9511,
|
| 2089 |
+
"step": 1160
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.83,
|
| 2093 |
+
"eval_loss": 0.9346606135368347,
|
| 2094 |
+
"eval_runtime": 429.4307,
|
| 2095 |
+
"eval_samples_per_second": 26.149,
|
| 2096 |
+
"eval_steps_per_second": 3.269,
|
| 2097 |
+
"step": 1160
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 0.83,
|
| 2101 |
+
"grad_norm": 0.3528451919555664,
|
| 2102 |
+
"learning_rate": 5.089094796863862e-05,
|
| 2103 |
+
"loss": 0.9789,
|
| 2104 |
+
"step": 1165
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 0.83,
|
| 2108 |
+
"grad_norm": 0.29251405596733093,
|
| 2109 |
+
"learning_rate": 4.9821810406272264e-05,
|
| 2110 |
+
"loss": 0.9271,
|
| 2111 |
+
"step": 1170
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 0.84,
|
| 2115 |
+
"grad_norm": 0.3118594288825989,
|
| 2116 |
+
"learning_rate": 4.875267284390591e-05,
|
| 2117 |
+
"loss": 0.9356,
|
| 2118 |
+
"step": 1175
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 0.84,
|
| 2122 |
+
"grad_norm": 0.2919027805328369,
|
| 2123 |
+
"learning_rate": 4.7683535281539556e-05,
|
| 2124 |
+
"loss": 0.9042,
|
| 2125 |
+
"step": 1180
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 0.84,
|
| 2129 |
+
"eval_loss": 0.9343792200088501,
|
| 2130 |
+
"eval_runtime": 429.6874,
|
| 2131 |
+
"eval_samples_per_second": 26.133,
|
| 2132 |
+
"eval_steps_per_second": 3.267,
|
| 2133 |
+
"step": 1180
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 0.84,
|
| 2137 |
+
"grad_norm": 0.3041454553604126,
|
| 2138 |
+
"learning_rate": 4.66143977191732e-05,
|
| 2139 |
+
"loss": 0.9366,
|
| 2140 |
+
"step": 1185
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 0.85,
|
| 2144 |
+
"grad_norm": 0.42262208461761475,
|
| 2145 |
+
"learning_rate": 4.554526015680684e-05,
|
| 2146 |
+
"loss": 0.954,
|
| 2147 |
+
"step": 1190
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 0.85,
|
| 2151 |
+
"grad_norm": 0.4994548559188843,
|
| 2152 |
+
"learning_rate": 4.4476122594440485e-05,
|
| 2153 |
+
"loss": 0.9125,
|
| 2154 |
+
"step": 1195
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 0.86,
|
| 2158 |
+
"grad_norm": 0.506973385810852,
|
| 2159 |
+
"learning_rate": 4.340698503207413e-05,
|
| 2160 |
+
"loss": 0.9359,
|
| 2161 |
+
"step": 1200
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 0.86,
|
| 2165 |
+
"eval_loss": 0.9343673586845398,
|
| 2166 |
+
"eval_runtime": 429.7828,
|
| 2167 |
+
"eval_samples_per_second": 26.127,
|
| 2168 |
+
"eval_steps_per_second": 3.267,
|
| 2169 |
+
"step": 1200
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 0.86,
|
| 2173 |
+
"grad_norm": 0.3126988112926483,
|
| 2174 |
+
"learning_rate": 4.2337847469707764e-05,
|
| 2175 |
+
"loss": 0.9643,
|
| 2176 |
+
"step": 1205
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 0.86,
|
| 2180 |
+
"grad_norm": 0.33700090646743774,
|
| 2181 |
+
"learning_rate": 4.1268709907341407e-05,
|
| 2182 |
+
"loss": 0.9809,
|
| 2183 |
+
"step": 1210
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 0.87,
|
| 2187 |
+
"grad_norm": 0.27363497018814087,
|
| 2188 |
+
"learning_rate": 4.019957234497505e-05,
|
| 2189 |
+
"loss": 0.9519,
|
| 2190 |
+
"step": 1215
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 0.87,
|
| 2194 |
+
"grad_norm": 0.2861486077308655,
|
| 2195 |
+
"learning_rate": 3.913043478260869e-05,
|
| 2196 |
+
"loss": 0.9131,
|
| 2197 |
+
"step": 1220
|
| 2198 |
+
},
|
| 2199 |
+
{
|
| 2200 |
+
"epoch": 0.87,
|
| 2201 |
+
"eval_loss": 0.9337981343269348,
|
| 2202 |
+
"eval_runtime": 429.8829,
|
| 2203 |
+
"eval_samples_per_second": 26.121,
|
| 2204 |
+
"eval_steps_per_second": 3.266,
|
| 2205 |
+
"step": 1220
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 0.87,
|
| 2209 |
+
"grad_norm": 0.6844860911369324,
|
| 2210 |
+
"learning_rate": 3.8061297220242335e-05,
|
| 2211 |
+
"loss": 0.996,
|
| 2212 |
+
"step": 1225
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 0.88,
|
| 2216 |
+
"grad_norm": 0.4049902558326721,
|
| 2217 |
+
"learning_rate": 3.699215965787598e-05,
|
| 2218 |
+
"loss": 0.9593,
|
| 2219 |
+
"step": 1230
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 0.88,
|
| 2223 |
+
"grad_norm": 0.3516334295272827,
|
| 2224 |
+
"learning_rate": 3.592302209550962e-05,
|
| 2225 |
+
"loss": 0.9,
|
| 2226 |
+
"step": 1235
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 0.88,
|
| 2230 |
+
"grad_norm": 0.3603789508342743,
|
| 2231 |
+
"learning_rate": 3.485388453314326e-05,
|
| 2232 |
+
"loss": 0.9674,
|
| 2233 |
+
"step": 1240
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 0.88,
|
| 2237 |
+
"eval_loss": 0.9333547353744507,
|
| 2238 |
+
"eval_runtime": 428.501,
|
| 2239 |
+
"eval_samples_per_second": 26.205,
|
| 2240 |
+
"eval_steps_per_second": 3.277,
|
| 2241 |
+
"step": 1240
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 0.89,
|
| 2245 |
+
"grad_norm": 0.3410665690898895,
|
| 2246 |
+
"learning_rate": 3.3784746970776906e-05,
|
| 2247 |
+
"loss": 0.9335,
|
| 2248 |
+
"step": 1245
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 0.89,
|
| 2252 |
+
"grad_norm": 0.34668412804603577,
|
| 2253 |
+
"learning_rate": 3.271560940841055e-05,
|
| 2254 |
+
"loss": 0.9618,
|
| 2255 |
+
"step": 1250
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 0.89,
|
| 2259 |
+
"grad_norm": 0.361831396818161,
|
| 2260 |
+
"learning_rate": 3.164647184604419e-05,
|
| 2261 |
+
"loss": 0.9524,
|
| 2262 |
+
"step": 1255
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 0.9,
|
| 2266 |
+
"grad_norm": 0.4450233280658722,
|
| 2267 |
+
"learning_rate": 3.057733428367783e-05,
|
| 2268 |
+
"loss": 0.9855,
|
| 2269 |
+
"step": 1260
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 0.9,
|
| 2273 |
+
"eval_loss": 0.9331775307655334,
|
| 2274 |
+
"eval_runtime": 430.3503,
|
| 2275 |
+
"eval_samples_per_second": 26.093,
|
| 2276 |
+
"eval_steps_per_second": 3.262,
|
| 2277 |
+
"step": 1260
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.9,
|
| 2281 |
+
"grad_norm": 0.38541775941848755,
|
| 2282 |
+
"learning_rate": 2.950819672131147e-05,
|
| 2283 |
+
"loss": 0.9691,
|
| 2284 |
+
"step": 1265
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.9,
|
| 2288 |
+
"grad_norm": 0.43870338797569275,
|
| 2289 |
+
"learning_rate": 2.8439059158945114e-05,
|
| 2290 |
+
"loss": 0.9514,
|
| 2291 |
+
"step": 1270
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.91,
|
| 2295 |
+
"grad_norm": 0.3042528033256531,
|
| 2296 |
+
"learning_rate": 2.736992159657876e-05,
|
| 2297 |
+
"loss": 0.9099,
|
| 2298 |
+
"step": 1275
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.91,
|
| 2302 |
+
"grad_norm": 0.28177541494369507,
|
| 2303 |
+
"learning_rate": 2.63007840342124e-05,
|
| 2304 |
+
"loss": 0.9201,
|
| 2305 |
+
"step": 1280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.91,
|
| 2309 |
+
"eval_loss": 0.9329990744590759,
|
| 2310 |
+
"eval_runtime": 430.5216,
|
| 2311 |
+
"eval_samples_per_second": 26.082,
|
| 2312 |
+
"eval_steps_per_second": 3.261,
|
| 2313 |
+
"step": 1280
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.92,
|
| 2317 |
+
"grad_norm": 0.31207114458084106,
|
| 2318 |
+
"learning_rate": 2.5231646471846042e-05,
|
| 2319 |
+
"loss": 0.9388,
|
| 2320 |
+
"step": 1285
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.92,
|
| 2324 |
+
"grad_norm": 0.39428967237472534,
|
| 2325 |
+
"learning_rate": 2.4162508909479685e-05,
|
| 2326 |
+
"loss": 0.9827,
|
| 2327 |
+
"step": 1290
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.92,
|
| 2331 |
+
"grad_norm": 0.35494768619537354,
|
| 2332 |
+
"learning_rate": 2.3093371347113328e-05,
|
| 2333 |
+
"loss": 0.9094,
|
| 2334 |
+
"step": 1295
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.93,
|
| 2338 |
+
"grad_norm": 0.5314223766326904,
|
| 2339 |
+
"learning_rate": 2.2024233784746968e-05,
|
| 2340 |
+
"loss": 0.9453,
|
| 2341 |
+
"step": 1300
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.93,
|
| 2345 |
+
"eval_loss": 0.9329606294631958,
|
| 2346 |
+
"eval_runtime": 429.558,
|
| 2347 |
+
"eval_samples_per_second": 26.141,
|
| 2348 |
+
"eval_steps_per_second": 3.268,
|
| 2349 |
+
"step": 1300
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 0.93,
|
| 2353 |
+
"grad_norm": 0.3589262366294861,
|
| 2354 |
+
"learning_rate": 2.095509622238061e-05,
|
| 2355 |
+
"loss": 0.9202,
|
| 2356 |
+
"step": 1305
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 0.93,
|
| 2360 |
+
"grad_norm": 0.3077951967716217,
|
| 2361 |
+
"learning_rate": 1.9885958660014253e-05,
|
| 2362 |
+
"loss": 0.9741,
|
| 2363 |
+
"step": 1310
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 0.94,
|
| 2367 |
+
"grad_norm": 0.3348515033721924,
|
| 2368 |
+
"learning_rate": 1.8816821097647896e-05,
|
| 2369 |
+
"loss": 0.933,
|
| 2370 |
+
"step": 1315
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 0.94,
|
| 2374 |
+
"grad_norm": 0.34439706802368164,
|
| 2375 |
+
"learning_rate": 1.774768353528154e-05,
|
| 2376 |
+
"loss": 0.9476,
|
| 2377 |
+
"step": 1320
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 0.94,
|
| 2381 |
+
"eval_loss": 0.932703971862793,
|
| 2382 |
+
"eval_runtime": 428.8979,
|
| 2383 |
+
"eval_samples_per_second": 26.181,
|
| 2384 |
+
"eval_steps_per_second": 3.274,
|
| 2385 |
+
"step": 1320
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 0.94,
|
| 2389 |
+
"grad_norm": 0.28818029165267944,
|
| 2390 |
+
"learning_rate": 1.6678545972915182e-05,
|
| 2391 |
+
"loss": 0.9288,
|
| 2392 |
+
"step": 1325
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 0.95,
|
| 2396 |
+
"grad_norm": 0.2997274696826935,
|
| 2397 |
+
"learning_rate": 1.560940841054882e-05,
|
| 2398 |
+
"loss": 0.9418,
|
| 2399 |
+
"step": 1330
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 0.95,
|
| 2403 |
+
"grad_norm": 0.3139705955982208,
|
| 2404 |
+
"learning_rate": 1.4540270848182466e-05,
|
| 2405 |
+
"loss": 0.9732,
|
| 2406 |
+
"step": 1335
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 0.95,
|
| 2410 |
+
"grad_norm": 0.32881295680999756,
|
| 2411 |
+
"learning_rate": 1.3471133285816107e-05,
|
| 2412 |
+
"loss": 0.9166,
|
| 2413 |
+
"step": 1340
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 0.95,
|
| 2417 |
+
"eval_loss": 0.9325681328773499,
|
| 2418 |
+
"eval_runtime": 429.5609,
|
| 2419 |
+
"eval_samples_per_second": 26.141,
|
| 2420 |
+
"eval_steps_per_second": 3.268,
|
| 2421 |
+
"step": 1340
|
| 2422 |
+
},
|
| 2423 |
+
{
|
| 2424 |
+
"epoch": 0.96,
|
| 2425 |
+
"grad_norm": 0.6226952075958252,
|
| 2426 |
+
"learning_rate": 1.240199572344975e-05,
|
| 2427 |
+
"loss": 1.0029,
|
| 2428 |
+
"step": 1345
|
| 2429 |
+
},
|
| 2430 |
+
{
|
| 2431 |
+
"epoch": 0.96,
|
| 2432 |
+
"grad_norm": 0.3391931354999542,
|
| 2433 |
+
"learning_rate": 1.1332858161083391e-05,
|
| 2434 |
+
"loss": 0.9522,
|
| 2435 |
+
"step": 1350
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 0.97,
|
| 2439 |
+
"grad_norm": 0.37440812587738037,
|
| 2440 |
+
"learning_rate": 1.0263720598717034e-05,
|
| 2441 |
+
"loss": 0.9362,
|
| 2442 |
+
"step": 1355
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 0.97,
|
| 2446 |
+
"grad_norm": 0.3198889493942261,
|
| 2447 |
+
"learning_rate": 9.194583036350677e-06,
|
| 2448 |
+
"loss": 0.9523,
|
| 2449 |
+
"step": 1360
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 0.97,
|
| 2453 |
+
"eval_loss": 0.9325061440467834,
|
| 2454 |
+
"eval_runtime": 429.5538,
|
| 2455 |
+
"eval_samples_per_second": 26.141,
|
| 2456 |
+
"eval_steps_per_second": 3.269,
|
| 2457 |
+
"step": 1360
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 0.97,
|
| 2461 |
+
"grad_norm": 0.4025633931159973,
|
| 2462 |
+
"learning_rate": 8.12544547398432e-06,
|
| 2463 |
+
"loss": 0.9422,
|
| 2464 |
+
"step": 1365
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"epoch": 0.98,
|
| 2468 |
+
"grad_norm": 0.38235458731651306,
|
| 2469 |
+
"learning_rate": 7.0563079116179615e-06,
|
| 2470 |
+
"loss": 1.0052,
|
| 2471 |
+
"step": 1370
|
| 2472 |
+
},
|
| 2473 |
+
{
|
| 2474 |
+
"epoch": 0.98,
|
| 2475 |
+
"grad_norm": 0.3941135108470917,
|
| 2476 |
+
"learning_rate": 5.9871703492516035e-06,
|
| 2477 |
+
"loss": 0.9714,
|
| 2478 |
+
"step": 1375
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 0.98,
|
| 2482 |
+
"grad_norm": 0.31835320591926575,
|
| 2483 |
+
"learning_rate": 4.9180327868852455e-06,
|
| 2484 |
+
"loss": 0.9615,
|
| 2485 |
+
"step": 1380
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"epoch": 0.98,
|
| 2489 |
+
"eval_loss": 0.9324172735214233,
|
| 2490 |
+
"eval_runtime": 431.2711,
|
| 2491 |
+
"eval_samples_per_second": 26.037,
|
| 2492 |
+
"eval_steps_per_second": 3.255,
|
| 2493 |
+
"step": 1380
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 0.99,
|
| 2497 |
+
"grad_norm": 0.3852035105228424,
|
| 2498 |
+
"learning_rate": 3.848895224518888e-06,
|
| 2499 |
+
"loss": 0.9238,
|
| 2500 |
+
"step": 1385
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 0.99,
|
| 2504 |
+
"grad_norm": 0.33982229232788086,
|
| 2505 |
+
"learning_rate": 2.7797576621525303e-06,
|
| 2506 |
+
"loss": 0.9401,
|
| 2507 |
+
"step": 1390
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 0.99,
|
| 2511 |
+
"grad_norm": 0.31724292039871216,
|
| 2512 |
+
"learning_rate": 1.7106200997861725e-06,
|
| 2513 |
+
"loss": 0.9274,
|
| 2514 |
+
"step": 1395
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 1.0,
|
| 2518 |
+
"grad_norm": 0.35556310415267944,
|
| 2519 |
+
"learning_rate": 6.414825374198146e-07,
|
| 2520 |
+
"loss": 0.9633,
|
| 2521 |
+
"step": 1400
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 1.0,
|
| 2525 |
+
"eval_loss": 0.9323536157608032,
|
| 2526 |
+
"eval_runtime": 430.5102,
|
| 2527 |
+
"eval_samples_per_second": 26.083,
|
| 2528 |
+
"eval_steps_per_second": 3.261,
|
| 2529 |
+
"step": 1400
|
| 2530 |
+
}
|
| 2531 |
+
],
|
| 2532 |
+
"logging_steps": 5,
|
| 2533 |
+
"max_steps": 1403,
|
| 2534 |
+
"num_input_tokens_seen": 0,
|
| 2535 |
+
"num_train_epochs": 1,
|
| 2536 |
+
"save_steps": 20,
|
| 2537 |
+
"total_flos": 5.2878011087683584e+17,
|
| 2538 |
+
"train_batch_size": 4,
|
| 2539 |
+
"trial_name": null,
|
| 2540 |
+
"trial_params": null
|
| 2541 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dce18d7d0cf66d95aba38df7dbd7d6e32bc52a8b64b4505635ad54131966772
|
| 3 |
+
size 4984
|