Upload 8 files
Browse files- README.md +202 -3
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +3562 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,202 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-2-2b-it
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.13.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-2-2b-it",
|
| 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": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dca70e7da3e22517d629a4cc9f94e74b8fdb06aa31ecf65f42035739b7ed923
|
| 3 |
+
size 83115256
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea5ad42ca9a4d5efa4f3a7ddfaa27e7a8598125c71125c3ce0a38ad23c7764ab
|
| 3 |
+
size 166439638
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3620f29a4c68b69c07c64da4388bcb86d3d4109d5dd86521e41c35c959b83c8c
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0c90b5dc09a301a9a1bd157525ecddc093451aa2523b7333d2a68445375e230
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3562 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4824,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0020730759264058047,
|
| 14 |
+
"grad_norm": 0.9091788530349731,
|
| 15 |
+
"learning_rate": 0.0001996268656716418,
|
| 16 |
+
"loss": 2.3429805755615236,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.004146151852811609,
|
| 21 |
+
"grad_norm": 1.014137625694275,
|
| 22 |
+
"learning_rate": 0.000199212271973466,
|
| 23 |
+
"loss": 2.083993911743164,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.006219227779217414,
|
| 28 |
+
"grad_norm": 0.9813042283058167,
|
| 29 |
+
"learning_rate": 0.00019879767827529022,
|
| 30 |
+
"loss": 2.0440767288208006,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.008292303705623219,
|
| 35 |
+
"grad_norm": 0.8600534200668335,
|
| 36 |
+
"learning_rate": 0.00019838308457711444,
|
| 37 |
+
"loss": 2.0040666580200197,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.010365379632029024,
|
| 42 |
+
"grad_norm": 0.9713129997253418,
|
| 43 |
+
"learning_rate": 0.00019796849087893865,
|
| 44 |
+
"loss": 1.8833141326904297,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.012438455558434827,
|
| 49 |
+
"grad_norm": 0.8239923119544983,
|
| 50 |
+
"learning_rate": 0.00019755389718076287,
|
| 51 |
+
"loss": 1.9487165451049804,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.014511531484840632,
|
| 56 |
+
"grad_norm": 0.970037579536438,
|
| 57 |
+
"learning_rate": 0.00019713930348258708,
|
| 58 |
+
"loss": 1.8362905502319335,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.016584607411246437,
|
| 63 |
+
"grad_norm": 0.8923717141151428,
|
| 64 |
+
"learning_rate": 0.0001967247097844113,
|
| 65 |
+
"loss": 1.8545101165771485,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.01865768333765224,
|
| 70 |
+
"grad_norm": 1.0183212757110596,
|
| 71 |
+
"learning_rate": 0.0001963101160862355,
|
| 72 |
+
"loss": 1.8110658645629882,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.020730759264058048,
|
| 77 |
+
"grad_norm": 0.8115273118019104,
|
| 78 |
+
"learning_rate": 0.0001958955223880597,
|
| 79 |
+
"loss": 1.8285026550292969,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.02280383519046385,
|
| 84 |
+
"grad_norm": 0.9811990857124329,
|
| 85 |
+
"learning_rate": 0.0001954809286898839,
|
| 86 |
+
"loss": 1.8877086639404297,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.024876911116869654,
|
| 91 |
+
"grad_norm": 0.9637799859046936,
|
| 92 |
+
"learning_rate": 0.00019506633499170815,
|
| 93 |
+
"loss": 1.767138671875,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.02694998704327546,
|
| 98 |
+
"grad_norm": 0.8544086217880249,
|
| 99 |
+
"learning_rate": 0.00019465174129353234,
|
| 100 |
+
"loss": 1.8863643646240233,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.029023062969681265,
|
| 105 |
+
"grad_norm": 0.8133947253227234,
|
| 106 |
+
"learning_rate": 0.00019423714759535655,
|
| 107 |
+
"loss": 1.763634490966797,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.031096138896087068,
|
| 112 |
+
"grad_norm": 0.8301745057106018,
|
| 113 |
+
"learning_rate": 0.00019382255389718077,
|
| 114 |
+
"loss": 1.7863468170166015,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.033169214822492875,
|
| 119 |
+
"grad_norm": 1.0789601802825928,
|
| 120 |
+
"learning_rate": 0.00019340796019900498,
|
| 121 |
+
"loss": 1.7523063659667968,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.03524229074889868,
|
| 126 |
+
"grad_norm": 0.9485411047935486,
|
| 127 |
+
"learning_rate": 0.0001929933665008292,
|
| 128 |
+
"loss": 1.782190704345703,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.03731536667530448,
|
| 133 |
+
"grad_norm": 0.9296794533729553,
|
| 134 |
+
"learning_rate": 0.0001925787728026534,
|
| 135 |
+
"loss": 1.7600175857543945,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.03938844260171029,
|
| 140 |
+
"grad_norm": 0.8409883379936218,
|
| 141 |
+
"learning_rate": 0.00019216417910447763,
|
| 142 |
+
"loss": 1.7022655487060547,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.041461518528116095,
|
| 147 |
+
"grad_norm": 1.083732008934021,
|
| 148 |
+
"learning_rate": 0.00019174958540630184,
|
| 149 |
+
"loss": 1.798708152770996,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.043534594454521895,
|
| 154 |
+
"grad_norm": 0.9614971280097961,
|
| 155 |
+
"learning_rate": 0.00019133499170812605,
|
| 156 |
+
"loss": 1.755731201171875,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.0456076703809277,
|
| 161 |
+
"grad_norm": 0.8356192708015442,
|
| 162 |
+
"learning_rate": 0.00019092039800995024,
|
| 163 |
+
"loss": 1.7372133255004882,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.04768074630733351,
|
| 168 |
+
"grad_norm": 0.8859673142433167,
|
| 169 |
+
"learning_rate": 0.00019050580431177448,
|
| 170 |
+
"loss": 1.709942626953125,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.04975382223373931,
|
| 175 |
+
"grad_norm": 0.8417310118675232,
|
| 176 |
+
"learning_rate": 0.0001900912106135987,
|
| 177 |
+
"loss": 1.7145137786865234,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.051826898160145116,
|
| 182 |
+
"grad_norm": 1.0017660856246948,
|
| 183 |
+
"learning_rate": 0.00018967661691542289,
|
| 184 |
+
"loss": 1.7842830657958983,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.05389997408655092,
|
| 189 |
+
"grad_norm": 0.8389541506767273,
|
| 190 |
+
"learning_rate": 0.0001892620232172471,
|
| 191 |
+
"loss": 1.696818733215332,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.05597305001295672,
|
| 196 |
+
"grad_norm": 0.9801367521286011,
|
| 197 |
+
"learning_rate": 0.00018884742951907134,
|
| 198 |
+
"loss": 1.6806442260742187,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.05804612593936253,
|
| 203 |
+
"grad_norm": 1.0814357995986938,
|
| 204 |
+
"learning_rate": 0.00018843283582089553,
|
| 205 |
+
"loss": 1.7625520706176758,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.060119201865768336,
|
| 210 |
+
"grad_norm": 1.0982401371002197,
|
| 211 |
+
"learning_rate": 0.00018801824212271974,
|
| 212 |
+
"loss": 1.7068971633911132,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.062192277792174136,
|
| 217 |
+
"grad_norm": 0.8793812394142151,
|
| 218 |
+
"learning_rate": 0.00018760364842454396,
|
| 219 |
+
"loss": 1.6139469146728516,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.06426535371857994,
|
| 224 |
+
"grad_norm": 1.1414549350738525,
|
| 225 |
+
"learning_rate": 0.00018718905472636817,
|
| 226 |
+
"loss": 1.7397516250610352,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.06633842964498575,
|
| 231 |
+
"grad_norm": 0.8776243329048157,
|
| 232 |
+
"learning_rate": 0.00018677446102819239,
|
| 233 |
+
"loss": 1.7217279434204102,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.06841150557139156,
|
| 238 |
+
"grad_norm": 1.0756258964538574,
|
| 239 |
+
"learning_rate": 0.0001863598673300166,
|
| 240 |
+
"loss": 1.757959747314453,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.07048458149779736,
|
| 245 |
+
"grad_norm": 0.9709790349006653,
|
| 246 |
+
"learning_rate": 0.0001859452736318408,
|
| 247 |
+
"loss": 1.7738918304443358,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.07255765742420316,
|
| 252 |
+
"grad_norm": 0.852245569229126,
|
| 253 |
+
"learning_rate": 0.00018553067993366503,
|
| 254 |
+
"loss": 1.718656349182129,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.07463073335060896,
|
| 259 |
+
"grad_norm": 0.9301595091819763,
|
| 260 |
+
"learning_rate": 0.00018511608623548924,
|
| 261 |
+
"loss": 1.6480951309204102,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.07670380927701477,
|
| 266 |
+
"grad_norm": 0.9946972131729126,
|
| 267 |
+
"learning_rate": 0.00018470149253731343,
|
| 268 |
+
"loss": 1.6211790084838866,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.07877688520342058,
|
| 273 |
+
"grad_norm": 0.9088757038116455,
|
| 274 |
+
"learning_rate": 0.00018428689883913764,
|
| 275 |
+
"loss": 1.6915576934814454,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.08084996112982638,
|
| 280 |
+
"grad_norm": 1.0271170139312744,
|
| 281 |
+
"learning_rate": 0.0001838723051409619,
|
| 282 |
+
"loss": 1.7419628143310546,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.08292303705623219,
|
| 287 |
+
"grad_norm": 0.850945770740509,
|
| 288 |
+
"learning_rate": 0.00018345771144278607,
|
| 289 |
+
"loss": 1.7296173095703125,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.08499611298263798,
|
| 294 |
+
"grad_norm": 0.8624365925788879,
|
| 295 |
+
"learning_rate": 0.0001830431177446103,
|
| 296 |
+
"loss": 1.6714574813842773,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.08706918890904379,
|
| 301 |
+
"grad_norm": 0.9081392288208008,
|
| 302 |
+
"learning_rate": 0.0001826285240464345,
|
| 303 |
+
"loss": 1.7895374298095703,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.0891422648354496,
|
| 308 |
+
"grad_norm": 0.8685234189033508,
|
| 309 |
+
"learning_rate": 0.00018221393034825872,
|
| 310 |
+
"loss": 1.6459678649902343,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.0912153407618554,
|
| 315 |
+
"grad_norm": 0.9042524695396423,
|
| 316 |
+
"learning_rate": 0.00018179933665008293,
|
| 317 |
+
"loss": 1.652775764465332,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.09328841668826121,
|
| 322 |
+
"grad_norm": 0.9973405003547668,
|
| 323 |
+
"learning_rate": 0.00018138474295190715,
|
| 324 |
+
"loss": 1.7169090270996095,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.09536149261466702,
|
| 329 |
+
"grad_norm": 0.8893020749092102,
|
| 330 |
+
"learning_rate": 0.00018097014925373136,
|
| 331 |
+
"loss": 1.6703657150268554,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.09743456854107281,
|
| 336 |
+
"grad_norm": 0.8917216658592224,
|
| 337 |
+
"learning_rate": 0.00018055555555555557,
|
| 338 |
+
"loss": 1.7180200576782227,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.09950764446747862,
|
| 343 |
+
"grad_norm": 0.9904600381851196,
|
| 344 |
+
"learning_rate": 0.0001801409618573798,
|
| 345 |
+
"loss": 1.7480133056640625,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.10158072039388442,
|
| 350 |
+
"grad_norm": 0.8615960478782654,
|
| 351 |
+
"learning_rate": 0.00017972636815920398,
|
| 352 |
+
"loss": 1.6338689804077149,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.10365379632029023,
|
| 357 |
+
"grad_norm": 0.8724789619445801,
|
| 358 |
+
"learning_rate": 0.0001793117744610282,
|
| 359 |
+
"loss": 1.7188920974731445,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.10572687224669604,
|
| 364 |
+
"grad_norm": 0.9289916753768921,
|
| 365 |
+
"learning_rate": 0.00017889718076285243,
|
| 366 |
+
"loss": 1.711186408996582,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.10779994817310184,
|
| 371 |
+
"grad_norm": 0.9007911682128906,
|
| 372 |
+
"learning_rate": 0.00017848258706467662,
|
| 373 |
+
"loss": 1.691291046142578,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.10987302409950764,
|
| 378 |
+
"grad_norm": 0.9181972742080688,
|
| 379 |
+
"learning_rate": 0.00017806799336650083,
|
| 380 |
+
"loss": 1.7039215087890625,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.11194610002591344,
|
| 385 |
+
"grad_norm": 0.9199845194816589,
|
| 386 |
+
"learning_rate": 0.00017765339966832505,
|
| 387 |
+
"loss": 1.6865100860595703,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.11401917595231925,
|
| 392 |
+
"grad_norm": 0.986028254032135,
|
| 393 |
+
"learning_rate": 0.00017723880597014926,
|
| 394 |
+
"loss": 1.6208017349243165,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.11609225187872506,
|
| 399 |
+
"grad_norm": 1.0031794309616089,
|
| 400 |
+
"learning_rate": 0.00017682421227197348,
|
| 401 |
+
"loss": 1.7129045486450196,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.11816532780513087,
|
| 406 |
+
"grad_norm": 0.9297766089439392,
|
| 407 |
+
"learning_rate": 0.0001764096185737977,
|
| 408 |
+
"loss": 1.6912664413452148,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.12023840373153667,
|
| 413 |
+
"grad_norm": 0.9929037690162659,
|
| 414 |
+
"learning_rate": 0.0001759950248756219,
|
| 415 |
+
"loss": 1.5491928100585937,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.12231147965794248,
|
| 420 |
+
"grad_norm": 0.9651626944541931,
|
| 421 |
+
"learning_rate": 0.00017558043117744612,
|
| 422 |
+
"loss": 1.611497688293457,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.12438455558434827,
|
| 427 |
+
"grad_norm": 0.9021316766738892,
|
| 428 |
+
"learning_rate": 0.00017516583747927033,
|
| 429 |
+
"loss": 1.67208251953125,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.1264576315107541,
|
| 434 |
+
"grad_norm": 1.012869954109192,
|
| 435 |
+
"learning_rate": 0.00017475124378109452,
|
| 436 |
+
"loss": 1.6646055221557616,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.12853070743715989,
|
| 441 |
+
"grad_norm": 0.9233406186103821,
|
| 442 |
+
"learning_rate": 0.00017433665008291876,
|
| 443 |
+
"loss": 1.7033281326293945,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.13060378336356568,
|
| 448 |
+
"grad_norm": 0.9368692636489868,
|
| 449 |
+
"learning_rate": 0.00017392205638474298,
|
| 450 |
+
"loss": 1.705314826965332,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.1326768592899715,
|
| 455 |
+
"grad_norm": 1.06294846534729,
|
| 456 |
+
"learning_rate": 0.00017350746268656716,
|
| 457 |
+
"loss": 1.637823486328125,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.1347499352163773,
|
| 462 |
+
"grad_norm": 1.02590811252594,
|
| 463 |
+
"learning_rate": 0.00017309286898839138,
|
| 464 |
+
"loss": 1.5813873291015625,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.1368230111427831,
|
| 469 |
+
"grad_norm": 1.0086368322372437,
|
| 470 |
+
"learning_rate": 0.00017267827529021562,
|
| 471 |
+
"loss": 1.670191764831543,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.1388960870691889,
|
| 476 |
+
"grad_norm": 0.9091687798500061,
|
| 477 |
+
"learning_rate": 0.0001722636815920398,
|
| 478 |
+
"loss": 1.6596086502075196,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.14096916299559473,
|
| 483 |
+
"grad_norm": 0.9156310558319092,
|
| 484 |
+
"learning_rate": 0.00017184908789386402,
|
| 485 |
+
"loss": 1.636850929260254,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.14304223892200052,
|
| 490 |
+
"grad_norm": 0.920555055141449,
|
| 491 |
+
"learning_rate": 0.00017143449419568824,
|
| 492 |
+
"loss": 1.6622644424438477,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.1451153148484063,
|
| 497 |
+
"grad_norm": 0.8024299740791321,
|
| 498 |
+
"learning_rate": 0.00017101990049751245,
|
| 499 |
+
"loss": 1.6317838668823241,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.14718839077481213,
|
| 504 |
+
"grad_norm": 0.9355529546737671,
|
| 505 |
+
"learning_rate": 0.00017060530679933667,
|
| 506 |
+
"loss": 1.6054956436157226,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.14926146670121793,
|
| 511 |
+
"grad_norm": 0.9528997540473938,
|
| 512 |
+
"learning_rate": 0.00017019071310116088,
|
| 513 |
+
"loss": 1.5931829452514648,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.15133454262762375,
|
| 518 |
+
"grad_norm": 0.8880454301834106,
|
| 519 |
+
"learning_rate": 0.00016977611940298507,
|
| 520 |
+
"loss": 1.7470476150512695,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.15340761855402954,
|
| 525 |
+
"grad_norm": 0.9789003133773804,
|
| 526 |
+
"learning_rate": 0.0001693615257048093,
|
| 527 |
+
"loss": 1.5642525672912597,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.15548069448043533,
|
| 532 |
+
"grad_norm": 0.9722698330879211,
|
| 533 |
+
"learning_rate": 0.00016894693200663352,
|
| 534 |
+
"loss": 1.5884984016418457,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.15755377040684115,
|
| 539 |
+
"grad_norm": 0.9086152911186218,
|
| 540 |
+
"learning_rate": 0.0001685323383084577,
|
| 541 |
+
"loss": 1.699564552307129,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.15962684633324695,
|
| 546 |
+
"grad_norm": 0.9152286648750305,
|
| 547 |
+
"learning_rate": 0.00016811774461028192,
|
| 548 |
+
"loss": 1.6350950241088866,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.16169992225965277,
|
| 553 |
+
"grad_norm": 0.999038815498352,
|
| 554 |
+
"learning_rate": 0.00016770315091210617,
|
| 555 |
+
"loss": 1.6626720428466797,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.16377299818605856,
|
| 560 |
+
"grad_norm": 0.9354605674743652,
|
| 561 |
+
"learning_rate": 0.00016728855721393035,
|
| 562 |
+
"loss": 1.6083240509033203,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.16584607411246438,
|
| 567 |
+
"grad_norm": 0.9644563794136047,
|
| 568 |
+
"learning_rate": 0.00016687396351575457,
|
| 569 |
+
"loss": 1.584075927734375,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.16791915003887017,
|
| 574 |
+
"grad_norm": 1.0484062433242798,
|
| 575 |
+
"learning_rate": 0.00016645936981757878,
|
| 576 |
+
"loss": 1.5805594444274902,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.16999222596527597,
|
| 581 |
+
"grad_norm": 0.9263212084770203,
|
| 582 |
+
"learning_rate": 0.000166044776119403,
|
| 583 |
+
"loss": 1.5858475685119628,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.1720653018916818,
|
| 588 |
+
"grad_norm": 0.8885413408279419,
|
| 589 |
+
"learning_rate": 0.0001656301824212272,
|
| 590 |
+
"loss": 1.6233335494995118,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.17413837781808758,
|
| 595 |
+
"grad_norm": 1.003126621246338,
|
| 596 |
+
"learning_rate": 0.0001652155887230514,
|
| 597 |
+
"loss": 1.5958114624023438,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.1762114537444934,
|
| 602 |
+
"grad_norm": 0.9760786294937134,
|
| 603 |
+
"learning_rate": 0.00016480099502487564,
|
| 604 |
+
"loss": 1.5831708908081055,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.1782845296708992,
|
| 609 |
+
"grad_norm": 0.9633323550224304,
|
| 610 |
+
"learning_rate": 0.00016438640132669985,
|
| 611 |
+
"loss": 1.6611177444458007,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.180357605597305,
|
| 616 |
+
"grad_norm": 0.9381558895111084,
|
| 617 |
+
"learning_rate": 0.00016397180762852404,
|
| 618 |
+
"loss": 1.6489791870117188,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.1824306815237108,
|
| 623 |
+
"grad_norm": 0.9603164196014404,
|
| 624 |
+
"learning_rate": 0.00016355721393034826,
|
| 625 |
+
"loss": 1.5972728729248047,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.1845037574501166,
|
| 630 |
+
"grad_norm": 1.02583909034729,
|
| 631 |
+
"learning_rate": 0.00016314262023217247,
|
| 632 |
+
"loss": 1.5938024520874023,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.18657683337652242,
|
| 637 |
+
"grad_norm": 1.0646976232528687,
|
| 638 |
+
"learning_rate": 0.00016272802653399668,
|
| 639 |
+
"loss": 1.6365236282348632,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.18864990930292821,
|
| 644 |
+
"grad_norm": 1.0200999975204468,
|
| 645 |
+
"learning_rate": 0.0001623134328358209,
|
| 646 |
+
"loss": 1.6409852981567383,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.19072298522933404,
|
| 651 |
+
"grad_norm": 0.911371648311615,
|
| 652 |
+
"learning_rate": 0.0001618988391376451,
|
| 653 |
+
"loss": 1.647599220275879,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.19279606115573983,
|
| 658 |
+
"grad_norm": 1.0000650882720947,
|
| 659 |
+
"learning_rate": 0.00016148424543946933,
|
| 660 |
+
"loss": 1.6000936508178711,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.19486913708214562,
|
| 665 |
+
"grad_norm": 0.9260374307632446,
|
| 666 |
+
"learning_rate": 0.00016106965174129354,
|
| 667 |
+
"loss": 1.6430105209350585,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.19694221300855144,
|
| 672 |
+
"grad_norm": 0.9303072690963745,
|
| 673 |
+
"learning_rate": 0.00016065505804311776,
|
| 674 |
+
"loss": 1.650974655151367,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.19901528893495724,
|
| 679 |
+
"grad_norm": 0.9936369061470032,
|
| 680 |
+
"learning_rate": 0.00016024046434494194,
|
| 681 |
+
"loss": 1.6197996139526367,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.20108836486136306,
|
| 686 |
+
"grad_norm": 1.029943823814392,
|
| 687 |
+
"learning_rate": 0.00015982587064676618,
|
| 688 |
+
"loss": 1.6034399032592774,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.20316144078776885,
|
| 693 |
+
"grad_norm": 0.9719572067260742,
|
| 694 |
+
"learning_rate": 0.0001594112769485904,
|
| 695 |
+
"loss": 1.6465234756469727,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.20523451671417467,
|
| 700 |
+
"grad_norm": 0.950306236743927,
|
| 701 |
+
"learning_rate": 0.00015899668325041459,
|
| 702 |
+
"loss": 1.5650517463684082,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.20730759264058046,
|
| 707 |
+
"grad_norm": 0.9367968440055847,
|
| 708 |
+
"learning_rate": 0.0001585820895522388,
|
| 709 |
+
"loss": 1.5462970733642578,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.20938066856698626,
|
| 714 |
+
"grad_norm": 0.9189471006393433,
|
| 715 |
+
"learning_rate": 0.00015816749585406304,
|
| 716 |
+
"loss": 1.5616193771362306,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.21145374449339208,
|
| 721 |
+
"grad_norm": 0.9336299896240234,
|
| 722 |
+
"learning_rate": 0.00015775290215588723,
|
| 723 |
+
"loss": 1.5709722518920899,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.21352682041979787,
|
| 728 |
+
"grad_norm": 0.842507004737854,
|
| 729 |
+
"learning_rate": 0.00015733830845771144,
|
| 730 |
+
"loss": 1.5571642875671388,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.2155998963462037,
|
| 735 |
+
"grad_norm": 1.0135430097579956,
|
| 736 |
+
"learning_rate": 0.00015692371475953566,
|
| 737 |
+
"loss": 1.5800284385681151,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.21767297227260948,
|
| 742 |
+
"grad_norm": 1.0689647197723389,
|
| 743 |
+
"learning_rate": 0.00015650912106135987,
|
| 744 |
+
"loss": 1.621286392211914,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.21974604819901528,
|
| 749 |
+
"grad_norm": 0.9640220999717712,
|
| 750 |
+
"learning_rate": 0.0001560945273631841,
|
| 751 |
+
"loss": 1.6154445648193358,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.2218191241254211,
|
| 756 |
+
"grad_norm": 1.0506129264831543,
|
| 757 |
+
"learning_rate": 0.0001556799336650083,
|
| 758 |
+
"loss": 1.6239688873291016,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.2238922000518269,
|
| 763 |
+
"grad_norm": 0.9619534015655518,
|
| 764 |
+
"learning_rate": 0.0001552653399668325,
|
| 765 |
+
"loss": 1.6208015441894532,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.2259652759782327,
|
| 770 |
+
"grad_norm": 0.9947149753570557,
|
| 771 |
+
"learning_rate": 0.00015485074626865673,
|
| 772 |
+
"loss": 1.559681224822998,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.2280383519046385,
|
| 777 |
+
"grad_norm": 0.9842751622200012,
|
| 778 |
+
"learning_rate": 0.00015443615257048094,
|
| 779 |
+
"loss": 1.593973731994629,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.23011142783104432,
|
| 784 |
+
"grad_norm": 1.0848839282989502,
|
| 785 |
+
"learning_rate": 0.00015402155887230513,
|
| 786 |
+
"loss": 1.6429691314697266,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.23218450375745012,
|
| 791 |
+
"grad_norm": 0.9902291297912598,
|
| 792 |
+
"learning_rate": 0.00015360696517412935,
|
| 793 |
+
"loss": 1.560030174255371,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.2342575796838559,
|
| 798 |
+
"grad_norm": 1.0478103160858154,
|
| 799 |
+
"learning_rate": 0.0001531923714759536,
|
| 800 |
+
"loss": 1.5744388580322266,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.23633065561026173,
|
| 805 |
+
"grad_norm": 1.0551514625549316,
|
| 806 |
+
"learning_rate": 0.00015277777777777777,
|
| 807 |
+
"loss": 1.5343515396118164,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.23840373153666752,
|
| 812 |
+
"grad_norm": 0.9508061408996582,
|
| 813 |
+
"learning_rate": 0.000152363184079602,
|
| 814 |
+
"loss": 1.64904842376709,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.24047680746307334,
|
| 819 |
+
"grad_norm": 1.0218685865402222,
|
| 820 |
+
"learning_rate": 0.0001519485903814262,
|
| 821 |
+
"loss": 1.598756980895996,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.24254988338947914,
|
| 826 |
+
"grad_norm": 1.0358250141143799,
|
| 827 |
+
"learning_rate": 0.00015153399668325042,
|
| 828 |
+
"loss": 1.5701421737670898,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.24462295931588496,
|
| 833 |
+
"grad_norm": 0.9931305646896362,
|
| 834 |
+
"learning_rate": 0.00015111940298507463,
|
| 835 |
+
"loss": 1.6070541381835937,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.24669603524229075,
|
| 840 |
+
"grad_norm": 0.9626891016960144,
|
| 841 |
+
"learning_rate": 0.00015070480928689885,
|
| 842 |
+
"loss": 1.4579319953918457,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.24876911116869654,
|
| 847 |
+
"grad_norm": 0.9033750295639038,
|
| 848 |
+
"learning_rate": 0.00015029021558872306,
|
| 849 |
+
"loss": 1.5091530799865722,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.25084218709510236,
|
| 854 |
+
"grad_norm": 0.9851518869400024,
|
| 855 |
+
"learning_rate": 0.00014987562189054728,
|
| 856 |
+
"loss": 1.5484381675720216,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.2529152630215082,
|
| 861 |
+
"grad_norm": 1.124658226966858,
|
| 862 |
+
"learning_rate": 0.0001494610281923715,
|
| 863 |
+
"loss": 1.6561983108520508,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.25498833894791395,
|
| 868 |
+
"grad_norm": 1.1919487714767456,
|
| 869 |
+
"learning_rate": 0.00014904643449419568,
|
| 870 |
+
"loss": 1.5920031547546387,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.25706141487431977,
|
| 875 |
+
"grad_norm": 1.0409331321716309,
|
| 876 |
+
"learning_rate": 0.00014863184079601992,
|
| 877 |
+
"loss": 1.5242692947387695,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.2591344908007256,
|
| 882 |
+
"grad_norm": 0.9168948531150818,
|
| 883 |
+
"learning_rate": 0.00014821724709784413,
|
| 884 |
+
"loss": 1.523965549468994,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.26120756672713136,
|
| 889 |
+
"grad_norm": 0.9807767868041992,
|
| 890 |
+
"learning_rate": 0.00014780265339966832,
|
| 891 |
+
"loss": 1.555476188659668,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.2632806426535372,
|
| 896 |
+
"grad_norm": 0.905844509601593,
|
| 897 |
+
"learning_rate": 0.00014738805970149253,
|
| 898 |
+
"loss": 1.526420497894287,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.265353718579943,
|
| 903 |
+
"grad_norm": 0.9614242315292358,
|
| 904 |
+
"learning_rate": 0.00014697346600331675,
|
| 905 |
+
"loss": 1.5558547973632812,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.2674267945063488,
|
| 910 |
+
"grad_norm": 0.8911798596382141,
|
| 911 |
+
"learning_rate": 0.00014655887230514096,
|
| 912 |
+
"loss": 1.5765740394592285,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.2694998704327546,
|
| 917 |
+
"grad_norm": 0.9637242555618286,
|
| 918 |
+
"learning_rate": 0.00014614427860696518,
|
| 919 |
+
"loss": 1.5548508644104004,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.2715729463591604,
|
| 924 |
+
"grad_norm": 1.0161306858062744,
|
| 925 |
+
"learning_rate": 0.0001457296849087894,
|
| 926 |
+
"loss": 1.5633068084716797,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.2736460222855662,
|
| 931 |
+
"grad_norm": 0.9732279181480408,
|
| 932 |
+
"learning_rate": 0.0001453150912106136,
|
| 933 |
+
"loss": 1.5484658241271974,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.275719098211972,
|
| 938 |
+
"grad_norm": 1.1542972326278687,
|
| 939 |
+
"learning_rate": 0.00014490049751243782,
|
| 940 |
+
"loss": 1.661750030517578,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.2777921741383778,
|
| 945 |
+
"grad_norm": 0.9862635731697083,
|
| 946 |
+
"learning_rate": 0.00014448590381426204,
|
| 947 |
+
"loss": 1.6615022659301757,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.27986525006478363,
|
| 952 |
+
"grad_norm": 0.9343971014022827,
|
| 953 |
+
"learning_rate": 0.00014407131011608622,
|
| 954 |
+
"loss": 1.5562618255615235,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.28193832599118945,
|
| 959 |
+
"grad_norm": 0.9783313870429993,
|
| 960 |
+
"learning_rate": 0.00014365671641791046,
|
| 961 |
+
"loss": 1.6128976821899415,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.2840114019175952,
|
| 966 |
+
"grad_norm": 0.9503439664840698,
|
| 967 |
+
"learning_rate": 0.00014324212271973468,
|
| 968 |
+
"loss": 1.6037235260009766,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.28608447784400104,
|
| 973 |
+
"grad_norm": 1.033592700958252,
|
| 974 |
+
"learning_rate": 0.00014282752902155887,
|
| 975 |
+
"loss": 1.4874424934387207,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.28815755377040686,
|
| 980 |
+
"grad_norm": 1.0737738609313965,
|
| 981 |
+
"learning_rate": 0.00014241293532338308,
|
| 982 |
+
"loss": 1.5970182418823242,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.2902306296968126,
|
| 987 |
+
"grad_norm": 1.0103057622909546,
|
| 988 |
+
"learning_rate": 0.00014199834162520732,
|
| 989 |
+
"loss": 1.5805618286132812,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.29230370562321845,
|
| 994 |
+
"grad_norm": 0.9714734554290771,
|
| 995 |
+
"learning_rate": 0.0001415837479270315,
|
| 996 |
+
"loss": 1.4544689178466796,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.29437678154962427,
|
| 1001 |
+
"grad_norm": 1.0983737707138062,
|
| 1002 |
+
"learning_rate": 0.00014116915422885572,
|
| 1003 |
+
"loss": 1.4936376571655274,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.29644985747603003,
|
| 1008 |
+
"grad_norm": 1.0537210702896118,
|
| 1009 |
+
"learning_rate": 0.00014075456053067994,
|
| 1010 |
+
"loss": 1.531502628326416,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.29852293340243585,
|
| 1015 |
+
"grad_norm": 1.0152987241744995,
|
| 1016 |
+
"learning_rate": 0.00014033996683250415,
|
| 1017 |
+
"loss": 1.5243349075317383,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.3005960093288417,
|
| 1022 |
+
"grad_norm": 0.9748072028160095,
|
| 1023 |
+
"learning_rate": 0.00013992537313432837,
|
| 1024 |
+
"loss": 1.552549457550049,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.3026690852552475,
|
| 1029 |
+
"grad_norm": 0.9957873225212097,
|
| 1030 |
+
"learning_rate": 0.00013951077943615258,
|
| 1031 |
+
"loss": 1.5652660369873046,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.30474216118165326,
|
| 1036 |
+
"grad_norm": 1.0181517601013184,
|
| 1037 |
+
"learning_rate": 0.00013909618573797677,
|
| 1038 |
+
"loss": 1.5933172225952148,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.3068152371080591,
|
| 1043 |
+
"grad_norm": 1.013455867767334,
|
| 1044 |
+
"learning_rate": 0.000138681592039801,
|
| 1045 |
+
"loss": 1.6291587829589844,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.3088883130344649,
|
| 1050 |
+
"grad_norm": 1.0690240859985352,
|
| 1051 |
+
"learning_rate": 0.00013826699834162522,
|
| 1052 |
+
"loss": 1.5185072898864747,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.31096138896087067,
|
| 1057 |
+
"grad_norm": 1.0201985836029053,
|
| 1058 |
+
"learning_rate": 0.0001378524046434494,
|
| 1059 |
+
"loss": 1.6345909118652344,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.3130344648872765,
|
| 1064 |
+
"grad_norm": 1.205460548400879,
|
| 1065 |
+
"learning_rate": 0.00013743781094527363,
|
| 1066 |
+
"loss": 1.4923598289489746,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.3151075408136823,
|
| 1071 |
+
"grad_norm": 1.0943695306777954,
|
| 1072 |
+
"learning_rate": 0.00013702321724709787,
|
| 1073 |
+
"loss": 1.551824951171875,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.31718061674008813,
|
| 1078 |
+
"grad_norm": 0.9574096202850342,
|
| 1079 |
+
"learning_rate": 0.00013660862354892205,
|
| 1080 |
+
"loss": 1.563786506652832,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.3192536926664939,
|
| 1085 |
+
"grad_norm": 1.01716947555542,
|
| 1086 |
+
"learning_rate": 0.00013619402985074627,
|
| 1087 |
+
"loss": 1.5811141014099122,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.3213267685928997,
|
| 1092 |
+
"grad_norm": 1.0344488620758057,
|
| 1093 |
+
"learning_rate": 0.00013577943615257048,
|
| 1094 |
+
"loss": 1.4693257331848144,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.32339984451930553,
|
| 1099 |
+
"grad_norm": 1.1056243181228638,
|
| 1100 |
+
"learning_rate": 0.0001353648424543947,
|
| 1101 |
+
"loss": 1.5346773147583008,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.3254729204457113,
|
| 1106 |
+
"grad_norm": 1.1026792526245117,
|
| 1107 |
+
"learning_rate": 0.0001349502487562189,
|
| 1108 |
+
"loss": 1.4362568855285645,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.3275459963721171,
|
| 1113 |
+
"grad_norm": 1.0443516969680786,
|
| 1114 |
+
"learning_rate": 0.00013453565505804313,
|
| 1115 |
+
"loss": 1.5090986251831056,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.32961907229852294,
|
| 1120 |
+
"grad_norm": 1.006152629852295,
|
| 1121 |
+
"learning_rate": 0.00013412106135986734,
|
| 1122 |
+
"loss": 1.5561832427978515,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.33169214822492876,
|
| 1127 |
+
"grad_norm": 1.0812287330627441,
|
| 1128 |
+
"learning_rate": 0.00013370646766169155,
|
| 1129 |
+
"loss": 1.5622328758239745,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.3337652241513345,
|
| 1134 |
+
"grad_norm": 1.0125651359558105,
|
| 1135 |
+
"learning_rate": 0.00013329187396351577,
|
| 1136 |
+
"loss": 1.5935446739196777,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.33583830007774035,
|
| 1141 |
+
"grad_norm": 1.0166149139404297,
|
| 1142 |
+
"learning_rate": 0.00013287728026533996,
|
| 1143 |
+
"loss": 1.5660451889038085,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.33791137600414617,
|
| 1148 |
+
"grad_norm": 1.0273667573928833,
|
| 1149 |
+
"learning_rate": 0.0001324626865671642,
|
| 1150 |
+
"loss": 1.556844139099121,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.33998445193055193,
|
| 1155 |
+
"grad_norm": 1.0821034908294678,
|
| 1156 |
+
"learning_rate": 0.0001320480928689884,
|
| 1157 |
+
"loss": 1.5019357681274415,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.34205752785695775,
|
| 1162 |
+
"grad_norm": 1.082353949546814,
|
| 1163 |
+
"learning_rate": 0.0001316334991708126,
|
| 1164 |
+
"loss": 1.5400747299194335,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.3441306037833636,
|
| 1169 |
+
"grad_norm": 1.059366226196289,
|
| 1170 |
+
"learning_rate": 0.00013121890547263681,
|
| 1171 |
+
"loss": 1.5414251327514648,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.3462036797097694,
|
| 1176 |
+
"grad_norm": 0.996767520904541,
|
| 1177 |
+
"learning_rate": 0.00013080431177446103,
|
| 1178 |
+
"loss": 1.5605695724487305,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.34827675563617516,
|
| 1183 |
+
"grad_norm": 0.9471081495285034,
|
| 1184 |
+
"learning_rate": 0.00013038971807628524,
|
| 1185 |
+
"loss": 1.550748634338379,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.350349831562581,
|
| 1190 |
+
"grad_norm": 1.0039408206939697,
|
| 1191 |
+
"learning_rate": 0.00012997512437810946,
|
| 1192 |
+
"loss": 1.5467573165893556,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.3524229074889868,
|
| 1197 |
+
"grad_norm": 1.1023355722427368,
|
| 1198 |
+
"learning_rate": 0.00012956053067993367,
|
| 1199 |
+
"loss": 1.6264640808105468,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.35449598341539257,
|
| 1204 |
+
"grad_norm": 0.98204505443573,
|
| 1205 |
+
"learning_rate": 0.00012914593698175789,
|
| 1206 |
+
"loss": 1.5399457931518554,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.3565690593417984,
|
| 1211 |
+
"grad_norm": 1.1038545370101929,
|
| 1212 |
+
"learning_rate": 0.0001287313432835821,
|
| 1213 |
+
"loss": 1.5933405876159668,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.3586421352682042,
|
| 1218 |
+
"grad_norm": 1.0126818418502808,
|
| 1219 |
+
"learning_rate": 0.00012831674958540631,
|
| 1220 |
+
"loss": 1.5504828453063966,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.36071521119461,
|
| 1225 |
+
"grad_norm": 1.2247607707977295,
|
| 1226 |
+
"learning_rate": 0.0001279021558872305,
|
| 1227 |
+
"loss": 1.5725330352783202,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.3627882871210158,
|
| 1232 |
+
"grad_norm": 1.027273416519165,
|
| 1233 |
+
"learning_rate": 0.00012748756218905474,
|
| 1234 |
+
"loss": 1.5412575721740722,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.3648613630474216,
|
| 1239 |
+
"grad_norm": 1.1408429145812988,
|
| 1240 |
+
"learning_rate": 0.00012707296849087896,
|
| 1241 |
+
"loss": 1.5795598030090332,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.36693443897382744,
|
| 1246 |
+
"grad_norm": 0.9655275344848633,
|
| 1247 |
+
"learning_rate": 0.00012665837479270315,
|
| 1248 |
+
"loss": 1.5225658416748047,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.3690075149002332,
|
| 1253 |
+
"grad_norm": 1.0792255401611328,
|
| 1254 |
+
"learning_rate": 0.00012624378109452736,
|
| 1255 |
+
"loss": 1.4800280570983886,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.371080590826639,
|
| 1260 |
+
"grad_norm": 1.1403069496154785,
|
| 1261 |
+
"learning_rate": 0.0001258291873963516,
|
| 1262 |
+
"loss": 1.5279869079589843,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.37315366675304484,
|
| 1267 |
+
"grad_norm": 0.9717866778373718,
|
| 1268 |
+
"learning_rate": 0.0001254145936981758,
|
| 1269 |
+
"loss": 1.5097025871276855,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.3752267426794506,
|
| 1274 |
+
"grad_norm": 1.2142555713653564,
|
| 1275 |
+
"learning_rate": 0.000125,
|
| 1276 |
+
"loss": 1.5517022132873535,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.37729981860585643,
|
| 1281 |
+
"grad_norm": 1.0863559246063232,
|
| 1282 |
+
"learning_rate": 0.00012458540630182422,
|
| 1283 |
+
"loss": 1.6459320068359375,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.37937289453226225,
|
| 1288 |
+
"grad_norm": 0.935858428478241,
|
| 1289 |
+
"learning_rate": 0.00012417081260364843,
|
| 1290 |
+
"loss": 1.4541780471801757,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.38144597045866807,
|
| 1295 |
+
"grad_norm": 1.0745552778244019,
|
| 1296 |
+
"learning_rate": 0.00012375621890547265,
|
| 1297 |
+
"loss": 1.5062150001525878,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.38351904638507384,
|
| 1302 |
+
"grad_norm": 0.98747718334198,
|
| 1303 |
+
"learning_rate": 0.00012334162520729686,
|
| 1304 |
+
"loss": 1.450760841369629,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.38559212231147966,
|
| 1309 |
+
"grad_norm": 1.017136573791504,
|
| 1310 |
+
"learning_rate": 0.00012292703150912105,
|
| 1311 |
+
"loss": 1.5897736549377441,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.3876651982378855,
|
| 1316 |
+
"grad_norm": 1.0018948316574097,
|
| 1317 |
+
"learning_rate": 0.0001225124378109453,
|
| 1318 |
+
"loss": 1.5147670745849608,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.38973827416429124,
|
| 1323 |
+
"grad_norm": 1.0614641904830933,
|
| 1324 |
+
"learning_rate": 0.0001220978441127695,
|
| 1325 |
+
"loss": 1.558132266998291,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.39181135009069706,
|
| 1330 |
+
"grad_norm": 1.192165732383728,
|
| 1331 |
+
"learning_rate": 0.00012168325041459369,
|
| 1332 |
+
"loss": 1.5617985725402832,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.3938844260171029,
|
| 1337 |
+
"grad_norm": 1.1147258281707764,
|
| 1338 |
+
"learning_rate": 0.00012126865671641792,
|
| 1339 |
+
"loss": 1.5168773651123046,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.3959575019435087,
|
| 1344 |
+
"grad_norm": 1.129460096359253,
|
| 1345 |
+
"learning_rate": 0.00012085406301824213,
|
| 1346 |
+
"loss": 1.5103120803833008,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.39803057786991447,
|
| 1351 |
+
"grad_norm": 1.0588513612747192,
|
| 1352 |
+
"learning_rate": 0.00012043946932006633,
|
| 1353 |
+
"loss": 1.5003737449645995,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.4001036537963203,
|
| 1358 |
+
"grad_norm": 0.9957575798034668,
|
| 1359 |
+
"learning_rate": 0.00012002487562189055,
|
| 1360 |
+
"loss": 1.5337603569030762,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.4021767297227261,
|
| 1365 |
+
"grad_norm": 0.996632993221283,
|
| 1366 |
+
"learning_rate": 0.00011961028192371478,
|
| 1367 |
+
"loss": 1.6394582748413087,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.4042498056491319,
|
| 1372 |
+
"grad_norm": 1.086541771888733,
|
| 1373 |
+
"learning_rate": 0.00011919568822553898,
|
| 1374 |
+
"loss": 1.5516023635864258,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.4063228815755377,
|
| 1379 |
+
"grad_norm": 0.9926400184631348,
|
| 1380 |
+
"learning_rate": 0.00011878109452736319,
|
| 1381 |
+
"loss": 1.5786477088928224,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.4083959575019435,
|
| 1386 |
+
"grad_norm": 1.1575102806091309,
|
| 1387 |
+
"learning_rate": 0.0001183665008291874,
|
| 1388 |
+
"loss": 1.5651155471801759,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.41046903342834934,
|
| 1393 |
+
"grad_norm": 0.964144766330719,
|
| 1394 |
+
"learning_rate": 0.0001179519071310116,
|
| 1395 |
+
"loss": 1.5103749275207519,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.4125421093547551,
|
| 1400 |
+
"grad_norm": 1.1728180646896362,
|
| 1401 |
+
"learning_rate": 0.00011753731343283582,
|
| 1402 |
+
"loss": 1.5683252334594726,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.4146151852811609,
|
| 1407 |
+
"grad_norm": 1.0341147184371948,
|
| 1408 |
+
"learning_rate": 0.00011712271973466005,
|
| 1409 |
+
"loss": 1.5328519821166993,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.41668826120756675,
|
| 1414 |
+
"grad_norm": 1.220893383026123,
|
| 1415 |
+
"learning_rate": 0.00011670812603648425,
|
| 1416 |
+
"loss": 1.569212055206299,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.4187613371339725,
|
| 1421 |
+
"grad_norm": 1.287847638130188,
|
| 1422 |
+
"learning_rate": 0.00011629353233830846,
|
| 1423 |
+
"loss": 1.4834338188171388,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.42083441306037833,
|
| 1428 |
+
"grad_norm": 0.9762222766876221,
|
| 1429 |
+
"learning_rate": 0.00011587893864013268,
|
| 1430 |
+
"loss": 1.5161984443664551,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.42290748898678415,
|
| 1435 |
+
"grad_norm": 1.0173159837722778,
|
| 1436 |
+
"learning_rate": 0.00011546434494195688,
|
| 1437 |
+
"loss": 1.531379795074463,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.42498056491319,
|
| 1442 |
+
"grad_norm": 1.1367406845092773,
|
| 1443 |
+
"learning_rate": 0.00011504975124378111,
|
| 1444 |
+
"loss": 1.4666010856628418,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.42705364083959574,
|
| 1449 |
+
"grad_norm": 1.034964919090271,
|
| 1450 |
+
"learning_rate": 0.00011463515754560532,
|
| 1451 |
+
"loss": 1.4785846710205077,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.42912671676600156,
|
| 1456 |
+
"grad_norm": 1.1348105669021606,
|
| 1457 |
+
"learning_rate": 0.00011422056384742952,
|
| 1458 |
+
"loss": 1.5278627395629882,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.4311997926924074,
|
| 1463 |
+
"grad_norm": 1.092238426208496,
|
| 1464 |
+
"learning_rate": 0.00011380597014925374,
|
| 1465 |
+
"loss": 1.54183349609375,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.43327286861881315,
|
| 1470 |
+
"grad_norm": 1.1732505559921265,
|
| 1471 |
+
"learning_rate": 0.00011339137645107795,
|
| 1472 |
+
"loss": 1.5574755668640137,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.43534594454521897,
|
| 1477 |
+
"grad_norm": 1.108764410018921,
|
| 1478 |
+
"learning_rate": 0.00011297678275290215,
|
| 1479 |
+
"loss": 1.5414604187011718,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.4374190204716248,
|
| 1484 |
+
"grad_norm": 0.9649912118911743,
|
| 1485 |
+
"learning_rate": 0.00011256218905472638,
|
| 1486 |
+
"loss": 1.4722467422485352,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.43949209639803055,
|
| 1491 |
+
"grad_norm": 1.0946617126464844,
|
| 1492 |
+
"learning_rate": 0.0001121475953565506,
|
| 1493 |
+
"loss": 1.5284259796142579,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.4415651723244364,
|
| 1498 |
+
"grad_norm": 0.9634913206100464,
|
| 1499 |
+
"learning_rate": 0.0001117330016583748,
|
| 1500 |
+
"loss": 1.517714500427246,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.4436382482508422,
|
| 1505 |
+
"grad_norm": 1.1210685968399048,
|
| 1506 |
+
"learning_rate": 0.00011131840796019901,
|
| 1507 |
+
"loss": 1.463743305206299,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.445711324177248,
|
| 1512 |
+
"grad_norm": 1.065474510192871,
|
| 1513 |
+
"learning_rate": 0.00011090381426202324,
|
| 1514 |
+
"loss": 1.5272763252258301,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.4477844001036538,
|
| 1519 |
+
"grad_norm": 1.0351336002349854,
|
| 1520 |
+
"learning_rate": 0.00011048922056384742,
|
| 1521 |
+
"loss": 1.4388788223266602,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.4498574760300596,
|
| 1526 |
+
"grad_norm": 1.0451213121414185,
|
| 1527 |
+
"learning_rate": 0.00011007462686567165,
|
| 1528 |
+
"loss": 1.495101261138916,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.4519305519564654,
|
| 1533 |
+
"grad_norm": 1.2555310726165771,
|
| 1534 |
+
"learning_rate": 0.00010966003316749587,
|
| 1535 |
+
"loss": 1.4896994590759278,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.4540036278828712,
|
| 1540 |
+
"grad_norm": 1.059262752532959,
|
| 1541 |
+
"learning_rate": 0.00010924543946932007,
|
| 1542 |
+
"loss": 1.4970458030700684,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.456076703809277,
|
| 1547 |
+
"grad_norm": 0.9911238551139832,
|
| 1548 |
+
"learning_rate": 0.00010883084577114428,
|
| 1549 |
+
"loss": 1.5557072639465332,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.4581497797356828,
|
| 1554 |
+
"grad_norm": 1.1385858058929443,
|
| 1555 |
+
"learning_rate": 0.00010841625207296851,
|
| 1556 |
+
"loss": 1.4651107788085938,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.46022285566208865,
|
| 1561 |
+
"grad_norm": 1.1184098720550537,
|
| 1562 |
+
"learning_rate": 0.0001080016583747927,
|
| 1563 |
+
"loss": 1.5804038047790527,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.4622959315884944,
|
| 1568 |
+
"grad_norm": 1.0929696559906006,
|
| 1569 |
+
"learning_rate": 0.00010758706467661693,
|
| 1570 |
+
"loss": 1.5022403717041015,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.46436900751490023,
|
| 1575 |
+
"grad_norm": 0.9907273650169373,
|
| 1576 |
+
"learning_rate": 0.00010717247097844114,
|
| 1577 |
+
"loss": 1.4441984176635743,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.46644208344130605,
|
| 1582 |
+
"grad_norm": 0.9875295758247375,
|
| 1583 |
+
"learning_rate": 0.00010675787728026534,
|
| 1584 |
+
"loss": 1.4747949600219727,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.4685151593677118,
|
| 1589 |
+
"grad_norm": 0.9860086441040039,
|
| 1590 |
+
"learning_rate": 0.00010634328358208955,
|
| 1591 |
+
"loss": 1.506369400024414,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.47058823529411764,
|
| 1596 |
+
"grad_norm": 1.272979497909546,
|
| 1597 |
+
"learning_rate": 0.00010592868988391378,
|
| 1598 |
+
"loss": 1.4900493621826172,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.47266131122052346,
|
| 1603 |
+
"grad_norm": 1.1522997617721558,
|
| 1604 |
+
"learning_rate": 0.00010551409618573797,
|
| 1605 |
+
"loss": 1.4898492813110351,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.4747343871469293,
|
| 1610 |
+
"grad_norm": 1.0061860084533691,
|
| 1611 |
+
"learning_rate": 0.0001050995024875622,
|
| 1612 |
+
"loss": 1.5466057777404785,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.47680746307333505,
|
| 1617 |
+
"grad_norm": 1.1039366722106934,
|
| 1618 |
+
"learning_rate": 0.00010468490878938641,
|
| 1619 |
+
"loss": 1.4958653450012207,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.47888053899974087,
|
| 1624 |
+
"grad_norm": 1.064855933189392,
|
| 1625 |
+
"learning_rate": 0.00010427031509121061,
|
| 1626 |
+
"loss": 1.4066000938415528,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.4809536149261467,
|
| 1631 |
+
"grad_norm": 1.2152620553970337,
|
| 1632 |
+
"learning_rate": 0.00010385572139303483,
|
| 1633 |
+
"loss": 1.532679271697998,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.48302669085255245,
|
| 1638 |
+
"grad_norm": 1.1034210920333862,
|
| 1639 |
+
"learning_rate": 0.00010344112769485906,
|
| 1640 |
+
"loss": 1.4218317985534668,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.4850997667789583,
|
| 1645 |
+
"grad_norm": 1.0778026580810547,
|
| 1646 |
+
"learning_rate": 0.00010302653399668326,
|
| 1647 |
+
"loss": 1.4759449005126952,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.4871728427053641,
|
| 1652 |
+
"grad_norm": 1.0956099033355713,
|
| 1653 |
+
"learning_rate": 0.00010261194029850747,
|
| 1654 |
+
"loss": 1.510129165649414,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.4892459186317699,
|
| 1659 |
+
"grad_norm": 1.026975393295288,
|
| 1660 |
+
"learning_rate": 0.00010219734660033168,
|
| 1661 |
+
"loss": 1.450872802734375,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.4913189945581757,
|
| 1666 |
+
"grad_norm": 1.0078274011611938,
|
| 1667 |
+
"learning_rate": 0.00010178275290215589,
|
| 1668 |
+
"loss": 1.546852207183838,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.4933920704845815,
|
| 1673 |
+
"grad_norm": 0.9396551847457886,
|
| 1674 |
+
"learning_rate": 0.0001013681592039801,
|
| 1675 |
+
"loss": 1.4956705093383789,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.4954651464109873,
|
| 1680 |
+
"grad_norm": 1.0600014925003052,
|
| 1681 |
+
"learning_rate": 0.00010095356550580433,
|
| 1682 |
+
"loss": 1.4916232109069825,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.4975382223373931,
|
| 1687 |
+
"grad_norm": 0.9873512387275696,
|
| 1688 |
+
"learning_rate": 0.00010053897180762853,
|
| 1689 |
+
"loss": 1.383552074432373,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.4996112982637989,
|
| 1694 |
+
"grad_norm": 1.2188613414764404,
|
| 1695 |
+
"learning_rate": 0.00010012437810945274,
|
| 1696 |
+
"loss": 1.529955005645752,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.5016843741902047,
|
| 1701 |
+
"grad_norm": 1.0167559385299683,
|
| 1702 |
+
"learning_rate": 9.970978441127696e-05,
|
| 1703 |
+
"loss": 1.5507872581481934,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.5037574501166106,
|
| 1708 |
+
"grad_norm": 1.1081862449645996,
|
| 1709 |
+
"learning_rate": 9.929519071310116e-05,
|
| 1710 |
+
"loss": 1.4936115264892578,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.5058305260430164,
|
| 1715 |
+
"grad_norm": 1.160117268562317,
|
| 1716 |
+
"learning_rate": 9.888059701492539e-05,
|
| 1717 |
+
"loss": 1.479538917541504,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.5079036019694221,
|
| 1722 |
+
"grad_norm": 1.0124058723449707,
|
| 1723 |
+
"learning_rate": 9.846600331674959e-05,
|
| 1724 |
+
"loss": 1.407692050933838,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.5099766778958279,
|
| 1729 |
+
"grad_norm": 0.9970583319664001,
|
| 1730 |
+
"learning_rate": 9.80514096185738e-05,
|
| 1731 |
+
"loss": 1.5096822738647462,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.5120497538222337,
|
| 1736 |
+
"grad_norm": 1.0601921081542969,
|
| 1737 |
+
"learning_rate": 9.763681592039802e-05,
|
| 1738 |
+
"loss": 1.5124183654785157,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.5141228297486395,
|
| 1743 |
+
"grad_norm": 1.2017216682434082,
|
| 1744 |
+
"learning_rate": 9.722222222222223e-05,
|
| 1745 |
+
"loss": 1.4738014221191407,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.5161959056750454,
|
| 1750 |
+
"grad_norm": 1.1182701587677002,
|
| 1751 |
+
"learning_rate": 9.680762852404643e-05,
|
| 1752 |
+
"loss": 1.4870125770568847,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.5182689816014512,
|
| 1757 |
+
"grad_norm": 0.9587567448616028,
|
| 1758 |
+
"learning_rate": 9.639303482587066e-05,
|
| 1759 |
+
"loss": 1.5147294998168945,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.520342057527857,
|
| 1764 |
+
"grad_norm": 1.177620530128479,
|
| 1765 |
+
"learning_rate": 9.597844112769486e-05,
|
| 1766 |
+
"loss": 1.519681739807129,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.5224151334542627,
|
| 1771 |
+
"grad_norm": 1.1010137796401978,
|
| 1772 |
+
"learning_rate": 9.556384742951907e-05,
|
| 1773 |
+
"loss": 1.4474271774291991,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.5244882093806685,
|
| 1778 |
+
"grad_norm": 0.9620181918144226,
|
| 1779 |
+
"learning_rate": 9.514925373134329e-05,
|
| 1780 |
+
"loss": 1.5070289611816405,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.5265612853070744,
|
| 1785 |
+
"grad_norm": 1.0856534242630005,
|
| 1786 |
+
"learning_rate": 9.47346600331675e-05,
|
| 1787 |
+
"loss": 1.5071434020996093,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.5286343612334802,
|
| 1792 |
+
"grad_norm": 1.1289268732070923,
|
| 1793 |
+
"learning_rate": 9.43200663349917e-05,
|
| 1794 |
+
"loss": 1.6005094528198243,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.530707437159886,
|
| 1799 |
+
"grad_norm": 1.063301682472229,
|
| 1800 |
+
"learning_rate": 9.390547263681593e-05,
|
| 1801 |
+
"loss": 1.490926742553711,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.5327805130862918,
|
| 1806 |
+
"grad_norm": 1.0895897150039673,
|
| 1807 |
+
"learning_rate": 9.349087893864013e-05,
|
| 1808 |
+
"loss": 1.4283631324768067,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.5348535890126976,
|
| 1813 |
+
"grad_norm": 1.0446993112564087,
|
| 1814 |
+
"learning_rate": 9.307628524046435e-05,
|
| 1815 |
+
"loss": 1.5121649742126464,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.5369266649391033,
|
| 1820 |
+
"grad_norm": 1.118340253829956,
|
| 1821 |
+
"learning_rate": 9.266169154228856e-05,
|
| 1822 |
+
"loss": 1.5203582763671875,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.5389997408655092,
|
| 1827 |
+
"grad_norm": 0.9693984389305115,
|
| 1828 |
+
"learning_rate": 9.224709784411278e-05,
|
| 1829 |
+
"loss": 1.493481731414795,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.541072816791915,
|
| 1834 |
+
"grad_norm": 1.027601957321167,
|
| 1835 |
+
"learning_rate": 9.183250414593698e-05,
|
| 1836 |
+
"loss": 1.3991009712219238,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.5431458927183208,
|
| 1841 |
+
"grad_norm": 1.0012259483337402,
|
| 1842 |
+
"learning_rate": 9.14179104477612e-05,
|
| 1843 |
+
"loss": 1.4645806312561036,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.5452189686447266,
|
| 1848 |
+
"grad_norm": 1.021893858909607,
|
| 1849 |
+
"learning_rate": 9.10033167495854e-05,
|
| 1850 |
+
"loss": 1.4260982513427733,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.5472920445711325,
|
| 1855 |
+
"grad_norm": 1.1559139490127563,
|
| 1856 |
+
"learning_rate": 9.058872305140962e-05,
|
| 1857 |
+
"loss": 1.436918354034424,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.5493651204975383,
|
| 1862 |
+
"grad_norm": 1.0691229104995728,
|
| 1863 |
+
"learning_rate": 9.017412935323383e-05,
|
| 1864 |
+
"loss": 1.5417165756225586,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.551438196423944,
|
| 1869 |
+
"grad_norm": 1.0778980255126953,
|
| 1870 |
+
"learning_rate": 8.975953565505805e-05,
|
| 1871 |
+
"loss": 1.4646015167236328,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.5535112723503498,
|
| 1876 |
+
"grad_norm": 1.128537654876709,
|
| 1877 |
+
"learning_rate": 8.934494195688225e-05,
|
| 1878 |
+
"loss": 1.4791038513183594,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.5555843482767556,
|
| 1883 |
+
"grad_norm": 1.1227152347564697,
|
| 1884 |
+
"learning_rate": 8.893034825870648e-05,
|
| 1885 |
+
"loss": 1.477587890625,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.5576574242031614,
|
| 1890 |
+
"grad_norm": 1.1616007089614868,
|
| 1891 |
+
"learning_rate": 8.851575456053068e-05,
|
| 1892 |
+
"loss": 1.5081703186035156,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.5597305001295673,
|
| 1897 |
+
"grad_norm": 1.071717381477356,
|
| 1898 |
+
"learning_rate": 8.810116086235489e-05,
|
| 1899 |
+
"loss": 1.478490161895752,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.5618035760559731,
|
| 1904 |
+
"grad_norm": 0.953491747379303,
|
| 1905 |
+
"learning_rate": 8.76865671641791e-05,
|
| 1906 |
+
"loss": 1.486307144165039,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.5638766519823789,
|
| 1911 |
+
"grad_norm": 1.107778787612915,
|
| 1912 |
+
"learning_rate": 8.727197346600332e-05,
|
| 1913 |
+
"loss": 1.4863730430603028,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.5659497279087846,
|
| 1918 |
+
"grad_norm": 1.1062201261520386,
|
| 1919 |
+
"learning_rate": 8.685737976782754e-05,
|
| 1920 |
+
"loss": 1.4807310104370117,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.5680228038351904,
|
| 1925 |
+
"grad_norm": 1.1240142583847046,
|
| 1926 |
+
"learning_rate": 8.644278606965175e-05,
|
| 1927 |
+
"loss": 1.4995529174804687,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.5700958797615963,
|
| 1932 |
+
"grad_norm": 1.0423475503921509,
|
| 1933 |
+
"learning_rate": 8.602819237147596e-05,
|
| 1934 |
+
"loss": 1.4720562934875487,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.5721689556880021,
|
| 1939 |
+
"grad_norm": 1.1449542045593262,
|
| 1940 |
+
"learning_rate": 8.561359867330017e-05,
|
| 1941 |
+
"loss": 1.5412587165832519,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.5742420316144079,
|
| 1946 |
+
"grad_norm": 1.1100146770477295,
|
| 1947 |
+
"learning_rate": 8.519900497512438e-05,
|
| 1948 |
+
"loss": 1.4932291030883789,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.5763151075408137,
|
| 1953 |
+
"grad_norm": 1.066078543663025,
|
| 1954 |
+
"learning_rate": 8.47844112769486e-05,
|
| 1955 |
+
"loss": 1.4360157012939454,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.5783881834672195,
|
| 1960 |
+
"grad_norm": 1.0685060024261475,
|
| 1961 |
+
"learning_rate": 8.436981757877281e-05,
|
| 1962 |
+
"loss": 1.5007810592651367,
|
| 1963 |
+
"step": 2790
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.5804612593936253,
|
| 1967 |
+
"grad_norm": 1.337509274482727,
|
| 1968 |
+
"learning_rate": 8.395522388059702e-05,
|
| 1969 |
+
"loss": 1.4985486030578614,
|
| 1970 |
+
"step": 2800
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.5825343353200311,
|
| 1974 |
+
"grad_norm": 1.0489015579223633,
|
| 1975 |
+
"learning_rate": 8.354063018242124e-05,
|
| 1976 |
+
"loss": 1.4878012657165527,
|
| 1977 |
+
"step": 2810
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.5846074112464369,
|
| 1981 |
+
"grad_norm": 1.1977568864822388,
|
| 1982 |
+
"learning_rate": 8.312603648424544e-05,
|
| 1983 |
+
"loss": 1.4938278198242188,
|
| 1984 |
+
"step": 2820
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.5866804871728427,
|
| 1988 |
+
"grad_norm": 1.0384935140609741,
|
| 1989 |
+
"learning_rate": 8.271144278606967e-05,
|
| 1990 |
+
"loss": 1.484629249572754,
|
| 1991 |
+
"step": 2830
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.5887535630992485,
|
| 1995 |
+
"grad_norm": 1.0145131349563599,
|
| 1996 |
+
"learning_rate": 8.229684908789387e-05,
|
| 1997 |
+
"loss": 1.4890990257263184,
|
| 1998 |
+
"step": 2840
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.5908266390256544,
|
| 2002 |
+
"grad_norm": 1.0456562042236328,
|
| 2003 |
+
"learning_rate": 8.188225538971808e-05,
|
| 2004 |
+
"loss": 1.4158708572387695,
|
| 2005 |
+
"step": 2850
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.5928997149520601,
|
| 2009 |
+
"grad_norm": 1.0825212001800537,
|
| 2010 |
+
"learning_rate": 8.14676616915423e-05,
|
| 2011 |
+
"loss": 1.456554126739502,
|
| 2012 |
+
"step": 2860
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.5949727908784659,
|
| 2016 |
+
"grad_norm": 1.0650807619094849,
|
| 2017 |
+
"learning_rate": 8.105306799336651e-05,
|
| 2018 |
+
"loss": 1.473994255065918,
|
| 2019 |
+
"step": 2870
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.5970458668048717,
|
| 2023 |
+
"grad_norm": 1.060115098953247,
|
| 2024 |
+
"learning_rate": 8.063847429519071e-05,
|
| 2025 |
+
"loss": 1.4481081008911132,
|
| 2026 |
+
"step": 2880
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.5991189427312775,
|
| 2030 |
+
"grad_norm": 0.9253358840942383,
|
| 2031 |
+
"learning_rate": 8.022388059701494e-05,
|
| 2032 |
+
"loss": 1.4642643928527832,
|
| 2033 |
+
"step": 2890
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.6011920186576833,
|
| 2037 |
+
"grad_norm": 1.0225350856781006,
|
| 2038 |
+
"learning_rate": 7.980928689883914e-05,
|
| 2039 |
+
"loss": 1.3740483283996583,
|
| 2040 |
+
"step": 2900
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.6032650945840892,
|
| 2044 |
+
"grad_norm": 1.0211741924285889,
|
| 2045 |
+
"learning_rate": 7.939469320066335e-05,
|
| 2046 |
+
"loss": 1.4753257751464843,
|
| 2047 |
+
"step": 2910
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.605338170510495,
|
| 2051 |
+
"grad_norm": 1.0062146186828613,
|
| 2052 |
+
"learning_rate": 7.898009950248757e-05,
|
| 2053 |
+
"loss": 1.4432376861572265,
|
| 2054 |
+
"step": 2920
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.6074112464369007,
|
| 2058 |
+
"grad_norm": 1.1036884784698486,
|
| 2059 |
+
"learning_rate": 7.856550580431178e-05,
|
| 2060 |
+
"loss": 1.3941972732543946,
|
| 2061 |
+
"step": 2930
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.6094843223633065,
|
| 2065 |
+
"grad_norm": 1.0829540491104126,
|
| 2066 |
+
"learning_rate": 7.815091210613598e-05,
|
| 2067 |
+
"loss": 1.5212538719177247,
|
| 2068 |
+
"step": 2940
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.6115573982897123,
|
| 2072 |
+
"grad_norm": 1.1836856603622437,
|
| 2073 |
+
"learning_rate": 7.773631840796021e-05,
|
| 2074 |
+
"loss": 1.5671442031860352,
|
| 2075 |
+
"step": 2950
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.6136304742161182,
|
| 2079 |
+
"grad_norm": 0.9901530742645264,
|
| 2080 |
+
"learning_rate": 7.732172470978441e-05,
|
| 2081 |
+
"loss": 1.4176819801330567,
|
| 2082 |
+
"step": 2960
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.615703550142524,
|
| 2086 |
+
"grad_norm": 1.0980446338653564,
|
| 2087 |
+
"learning_rate": 7.690713101160863e-05,
|
| 2088 |
+
"loss": 1.47709379196167,
|
| 2089 |
+
"step": 2970
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.6177766260689298,
|
| 2093 |
+
"grad_norm": 1.0742297172546387,
|
| 2094 |
+
"learning_rate": 7.649253731343284e-05,
|
| 2095 |
+
"loss": 1.3669164657592774,
|
| 2096 |
+
"step": 2980
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.6198497019953356,
|
| 2100 |
+
"grad_norm": 1.0716501474380493,
|
| 2101 |
+
"learning_rate": 7.607794361525706e-05,
|
| 2102 |
+
"loss": 1.5048974990844726,
|
| 2103 |
+
"step": 2990
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.6219227779217413,
|
| 2107 |
+
"grad_norm": 1.2103937864303589,
|
| 2108 |
+
"learning_rate": 7.566334991708126e-05,
|
| 2109 |
+
"loss": 1.4739879608154296,
|
| 2110 |
+
"step": 3000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.6239958538481472,
|
| 2114 |
+
"grad_norm": 1.0737628936767578,
|
| 2115 |
+
"learning_rate": 7.524875621890548e-05,
|
| 2116 |
+
"loss": 1.493875503540039,
|
| 2117 |
+
"step": 3010
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.626068929774553,
|
| 2121 |
+
"grad_norm": 1.0744723081588745,
|
| 2122 |
+
"learning_rate": 7.483416252072968e-05,
|
| 2123 |
+
"loss": 1.50384578704834,
|
| 2124 |
+
"step": 3020
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.6281420057009588,
|
| 2128 |
+
"grad_norm": 1.070535659790039,
|
| 2129 |
+
"learning_rate": 7.44195688225539e-05,
|
| 2130 |
+
"loss": 1.4305116653442382,
|
| 2131 |
+
"step": 3030
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.6302150816273646,
|
| 2135 |
+
"grad_norm": 1.0274264812469482,
|
| 2136 |
+
"learning_rate": 7.400497512437811e-05,
|
| 2137 |
+
"loss": 1.452561092376709,
|
| 2138 |
+
"step": 3040
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.6322881575537704,
|
| 2142 |
+
"grad_norm": 1.1508046388626099,
|
| 2143 |
+
"learning_rate": 7.359038142620233e-05,
|
| 2144 |
+
"loss": 1.4898262023925781,
|
| 2145 |
+
"step": 3050
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.6343612334801763,
|
| 2149 |
+
"grad_norm": 1.0203231573104858,
|
| 2150 |
+
"learning_rate": 7.317578772802653e-05,
|
| 2151 |
+
"loss": 1.490403175354004,
|
| 2152 |
+
"step": 3060
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.636434309406582,
|
| 2156 |
+
"grad_norm": 1.3003417253494263,
|
| 2157 |
+
"learning_rate": 7.276119402985076e-05,
|
| 2158 |
+
"loss": 1.4818619728088378,
|
| 2159 |
+
"step": 3070
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.6385073853329878,
|
| 2163 |
+
"grad_norm": 1.1255285739898682,
|
| 2164 |
+
"learning_rate": 7.234660033167496e-05,
|
| 2165 |
+
"loss": 1.5162216186523438,
|
| 2166 |
+
"step": 3080
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.6405804612593936,
|
| 2170 |
+
"grad_norm": 1.0838392972946167,
|
| 2171 |
+
"learning_rate": 7.193200663349917e-05,
|
| 2172 |
+
"loss": 1.4879429817199707,
|
| 2173 |
+
"step": 3090
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.6426535371857994,
|
| 2177 |
+
"grad_norm": 1.036298394203186,
|
| 2178 |
+
"learning_rate": 7.151741293532339e-05,
|
| 2179 |
+
"loss": 1.5392193794250488,
|
| 2180 |
+
"step": 3100
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.6447266131122052,
|
| 2184 |
+
"grad_norm": 1.0307782888412476,
|
| 2185 |
+
"learning_rate": 7.11028192371476e-05,
|
| 2186 |
+
"loss": 1.4172185897827148,
|
| 2187 |
+
"step": 3110
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.6467996890386111,
|
| 2191 |
+
"grad_norm": 1.0826961994171143,
|
| 2192 |
+
"learning_rate": 7.068822553897181e-05,
|
| 2193 |
+
"loss": 1.5217445373535157,
|
| 2194 |
+
"step": 3120
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.6488727649650169,
|
| 2198 |
+
"grad_norm": 1.1925781965255737,
|
| 2199 |
+
"learning_rate": 7.027363184079603e-05,
|
| 2200 |
+
"loss": 1.4902685165405274,
|
| 2201 |
+
"step": 3130
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.6509458408914226,
|
| 2205 |
+
"grad_norm": 1.1316440105438232,
|
| 2206 |
+
"learning_rate": 6.985903814262023e-05,
|
| 2207 |
+
"loss": 1.4429686546325684,
|
| 2208 |
+
"step": 3140
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.6530189168178284,
|
| 2212 |
+
"grad_norm": 1.0991287231445312,
|
| 2213 |
+
"learning_rate": 6.944444444444444e-05,
|
| 2214 |
+
"loss": 1.5057510375976562,
|
| 2215 |
+
"step": 3150
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.6550919927442342,
|
| 2219 |
+
"grad_norm": 0.997954249382019,
|
| 2220 |
+
"learning_rate": 6.902985074626866e-05,
|
| 2221 |
+
"loss": 1.4608537673950195,
|
| 2222 |
+
"step": 3160
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.6571650686706401,
|
| 2226 |
+
"grad_norm": 1.3616468906402588,
|
| 2227 |
+
"learning_rate": 6.861525704809287e-05,
|
| 2228 |
+
"loss": 1.4557350158691407,
|
| 2229 |
+
"step": 3170
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.6592381445970459,
|
| 2233 |
+
"grad_norm": 1.106767177581787,
|
| 2234 |
+
"learning_rate": 6.820066334991709e-05,
|
| 2235 |
+
"loss": 1.486179733276367,
|
| 2236 |
+
"step": 3180
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.6613112205234517,
|
| 2240 |
+
"grad_norm": 1.0956076383590698,
|
| 2241 |
+
"learning_rate": 6.77860696517413e-05,
|
| 2242 |
+
"loss": 1.4668097496032715,
|
| 2243 |
+
"step": 3190
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.6633842964498575,
|
| 2247 |
+
"grad_norm": 1.1206140518188477,
|
| 2248 |
+
"learning_rate": 6.737147595356552e-05,
|
| 2249 |
+
"loss": 1.4768742561340331,
|
| 2250 |
+
"step": 3200
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.6654573723762632,
|
| 2254 |
+
"grad_norm": 0.9833910465240479,
|
| 2255 |
+
"learning_rate": 6.695688225538972e-05,
|
| 2256 |
+
"loss": 1.5204994201660156,
|
| 2257 |
+
"step": 3210
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.667530448302669,
|
| 2261 |
+
"grad_norm": 1.1817854642868042,
|
| 2262 |
+
"learning_rate": 6.654228855721395e-05,
|
| 2263 |
+
"loss": 1.5230501174926758,
|
| 2264 |
+
"step": 3220
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.6696035242290749,
|
| 2268 |
+
"grad_norm": 1.0882384777069092,
|
| 2269 |
+
"learning_rate": 6.612769485903815e-05,
|
| 2270 |
+
"loss": 1.3979837417602539,
|
| 2271 |
+
"step": 3230
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.6716766001554807,
|
| 2275 |
+
"grad_norm": 1.1264276504516602,
|
| 2276 |
+
"learning_rate": 6.571310116086236e-05,
|
| 2277 |
+
"loss": 1.4921886444091796,
|
| 2278 |
+
"step": 3240
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.6737496760818865,
|
| 2282 |
+
"grad_norm": 1.1087210178375244,
|
| 2283 |
+
"learning_rate": 6.529850746268657e-05,
|
| 2284 |
+
"loss": 1.4735729217529296,
|
| 2285 |
+
"step": 3250
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.6758227520082923,
|
| 2289 |
+
"grad_norm": 1.0597937107086182,
|
| 2290 |
+
"learning_rate": 6.488391376451079e-05,
|
| 2291 |
+
"loss": 1.5197007179260253,
|
| 2292 |
+
"step": 3260
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.6778958279346982,
|
| 2296 |
+
"grad_norm": 1.0482463836669922,
|
| 2297 |
+
"learning_rate": 6.446932006633499e-05,
|
| 2298 |
+
"loss": 1.465884017944336,
|
| 2299 |
+
"step": 3270
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.6799689038611039,
|
| 2303 |
+
"grad_norm": 1.035261869430542,
|
| 2304 |
+
"learning_rate": 6.405472636815922e-05,
|
| 2305 |
+
"loss": 1.4476487159729003,
|
| 2306 |
+
"step": 3280
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.6820419797875097,
|
| 2310 |
+
"grad_norm": 1.1454598903656006,
|
| 2311 |
+
"learning_rate": 6.364013266998342e-05,
|
| 2312 |
+
"loss": 1.453122329711914,
|
| 2313 |
+
"step": 3290
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.6841150557139155,
|
| 2317 |
+
"grad_norm": 1.1053162813186646,
|
| 2318 |
+
"learning_rate": 6.322553897180763e-05,
|
| 2319 |
+
"loss": 1.419975471496582,
|
| 2320 |
+
"step": 3300
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.6861881316403213,
|
| 2324 |
+
"grad_norm": 1.046738624572754,
|
| 2325 |
+
"learning_rate": 6.281094527363185e-05,
|
| 2326 |
+
"loss": 1.4719730377197267,
|
| 2327 |
+
"step": 3310
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.6882612075667272,
|
| 2331 |
+
"grad_norm": 1.2806482315063477,
|
| 2332 |
+
"learning_rate": 6.239635157545606e-05,
|
| 2333 |
+
"loss": 1.4755671501159668,
|
| 2334 |
+
"step": 3320
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.690334283493133,
|
| 2338 |
+
"grad_norm": 0.9969695210456848,
|
| 2339 |
+
"learning_rate": 6.198175787728026e-05,
|
| 2340 |
+
"loss": 1.4757104873657227,
|
| 2341 |
+
"step": 3330
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.6924073594195388,
|
| 2345 |
+
"grad_norm": 1.1298997402191162,
|
| 2346 |
+
"learning_rate": 6.156716417910448e-05,
|
| 2347 |
+
"loss": 1.39326171875,
|
| 2348 |
+
"step": 3340
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.6944804353459445,
|
| 2352 |
+
"grad_norm": 1.1446443796157837,
|
| 2353 |
+
"learning_rate": 6.115257048092869e-05,
|
| 2354 |
+
"loss": 1.518898105621338,
|
| 2355 |
+
"step": 3350
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.6965535112723503,
|
| 2359 |
+
"grad_norm": 1.145512580871582,
|
| 2360 |
+
"learning_rate": 6.0737976782752906e-05,
|
| 2361 |
+
"loss": 1.533563995361328,
|
| 2362 |
+
"step": 3360
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.6986265871987561,
|
| 2366 |
+
"grad_norm": 1.1053916215896606,
|
| 2367 |
+
"learning_rate": 6.032338308457711e-05,
|
| 2368 |
+
"loss": 1.5256379127502442,
|
| 2369 |
+
"step": 3370
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.700699663125162,
|
| 2373 |
+
"grad_norm": 1.1185383796691895,
|
| 2374 |
+
"learning_rate": 5.9908789386401334e-05,
|
| 2375 |
+
"loss": 1.4893531799316406,
|
| 2376 |
+
"step": 3380
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.7027727390515678,
|
| 2380 |
+
"grad_norm": 1.0875242948532104,
|
| 2381 |
+
"learning_rate": 5.949419568822554e-05,
|
| 2382 |
+
"loss": 1.5119455337524415,
|
| 2383 |
+
"step": 3390
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.7048458149779736,
|
| 2387 |
+
"grad_norm": 0.9813434481620789,
|
| 2388 |
+
"learning_rate": 5.907960199004975e-05,
|
| 2389 |
+
"loss": 1.4083710670471192,
|
| 2390 |
+
"step": 3400
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.7069188909043794,
|
| 2394 |
+
"grad_norm": 1.216704249382019,
|
| 2395 |
+
"learning_rate": 5.866500829187397e-05,
|
| 2396 |
+
"loss": 1.3952042579650878,
|
| 2397 |
+
"step": 3410
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.7089919668307851,
|
| 2401 |
+
"grad_norm": 0.9959679841995239,
|
| 2402 |
+
"learning_rate": 5.825041459369818e-05,
|
| 2403 |
+
"loss": 1.4536603927612304,
|
| 2404 |
+
"step": 3420
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.711065042757191,
|
| 2408 |
+
"grad_norm": 1.088835597038269,
|
| 2409 |
+
"learning_rate": 5.7835820895522386e-05,
|
| 2410 |
+
"loss": 1.5083325386047364,
|
| 2411 |
+
"step": 3430
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.7131381186835968,
|
| 2415 |
+
"grad_norm": 1.0195202827453613,
|
| 2416 |
+
"learning_rate": 5.742122719734661e-05,
|
| 2417 |
+
"loss": 1.3630632400512694,
|
| 2418 |
+
"step": 3440
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.7152111946100026,
|
| 2422 |
+
"grad_norm": 1.1602747440338135,
|
| 2423 |
+
"learning_rate": 5.7006633499170815e-05,
|
| 2424 |
+
"loss": 1.4151906967163086,
|
| 2425 |
+
"step": 3450
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.7172842705364084,
|
| 2429 |
+
"grad_norm": 1.0450451374053955,
|
| 2430 |
+
"learning_rate": 5.659203980099502e-05,
|
| 2431 |
+
"loss": 1.4249334335327148,
|
| 2432 |
+
"step": 3460
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.7193573464628142,
|
| 2436 |
+
"grad_norm": 1.100573182106018,
|
| 2437 |
+
"learning_rate": 5.6177446102819243e-05,
|
| 2438 |
+
"loss": 1.4444709777832032,
|
| 2439 |
+
"step": 3470
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.72143042238922,
|
| 2443 |
+
"grad_norm": 1.190826654434204,
|
| 2444 |
+
"learning_rate": 5.576285240464345e-05,
|
| 2445 |
+
"loss": 1.4221847534179688,
|
| 2446 |
+
"step": 3480
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.7235034983156258,
|
| 2450 |
+
"grad_norm": 1.1273324489593506,
|
| 2451 |
+
"learning_rate": 5.534825870646766e-05,
|
| 2452 |
+
"loss": 1.4116867065429688,
|
| 2453 |
+
"step": 3490
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.7255765742420316,
|
| 2457 |
+
"grad_norm": 1.132863163948059,
|
| 2458 |
+
"learning_rate": 5.493366500829188e-05,
|
| 2459 |
+
"loss": 1.5136717796325683,
|
| 2460 |
+
"step": 3500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.7276496501684374,
|
| 2464 |
+
"grad_norm": 1.256491780281067,
|
| 2465 |
+
"learning_rate": 5.451907131011609e-05,
|
| 2466 |
+
"loss": 1.4937585830688476,
|
| 2467 |
+
"step": 3510
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.7297227260948432,
|
| 2471 |
+
"grad_norm": 1.0635231733322144,
|
| 2472 |
+
"learning_rate": 5.4104477611940295e-05,
|
| 2473 |
+
"loss": 1.5216801643371582,
|
| 2474 |
+
"step": 3520
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.731795802021249,
|
| 2478 |
+
"grad_norm": 1.0570056438446045,
|
| 2479 |
+
"learning_rate": 5.3689883913764516e-05,
|
| 2480 |
+
"loss": 1.4815841674804688,
|
| 2481 |
+
"step": 3530
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.7338688779476549,
|
| 2485 |
+
"grad_norm": 1.1593701839447021,
|
| 2486 |
+
"learning_rate": 5.3275290215588724e-05,
|
| 2487 |
+
"loss": 1.4530771255493165,
|
| 2488 |
+
"step": 3540
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.7359419538740606,
|
| 2492 |
+
"grad_norm": 1.1562939882278442,
|
| 2493 |
+
"learning_rate": 5.286069651741293e-05,
|
| 2494 |
+
"loss": 1.5589415550231933,
|
| 2495 |
+
"step": 3550
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.7380150298004664,
|
| 2499 |
+
"grad_norm": 1.1924159526824951,
|
| 2500 |
+
"learning_rate": 5.244610281923715e-05,
|
| 2501 |
+
"loss": 1.3856592178344727,
|
| 2502 |
+
"step": 3560
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.7400881057268722,
|
| 2506 |
+
"grad_norm": 1.2092247009277344,
|
| 2507 |
+
"learning_rate": 5.203150912106136e-05,
|
| 2508 |
+
"loss": 1.402101993560791,
|
| 2509 |
+
"step": 3570
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.742161181653278,
|
| 2513 |
+
"grad_norm": 1.155090093612671,
|
| 2514 |
+
"learning_rate": 5.161691542288557e-05,
|
| 2515 |
+
"loss": 1.4879738807678222,
|
| 2516 |
+
"step": 3580
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.7442342575796839,
|
| 2520 |
+
"grad_norm": 0.9951611161231995,
|
| 2521 |
+
"learning_rate": 5.120232172470979e-05,
|
| 2522 |
+
"loss": 1.463954544067383,
|
| 2523 |
+
"step": 3590
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.7463073335060897,
|
| 2527 |
+
"grad_norm": 1.038360595703125,
|
| 2528 |
+
"learning_rate": 5.0787728026533996e-05,
|
| 2529 |
+
"loss": 1.514687728881836,
|
| 2530 |
+
"step": 3600
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.7483804094324955,
|
| 2534 |
+
"grad_norm": 1.1276081800460815,
|
| 2535 |
+
"learning_rate": 5.0373134328358204e-05,
|
| 2536 |
+
"loss": 1.383653736114502,
|
| 2537 |
+
"step": 3610
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.7504534853589012,
|
| 2541 |
+
"grad_norm": 1.2908998727798462,
|
| 2542 |
+
"learning_rate": 4.995854063018242e-05,
|
| 2543 |
+
"loss": 1.431437873840332,
|
| 2544 |
+
"step": 3620
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.752526561285307,
|
| 2548 |
+
"grad_norm": 1.1836334466934204,
|
| 2549 |
+
"learning_rate": 4.954394693200663e-05,
|
| 2550 |
+
"loss": 1.495081615447998,
|
| 2551 |
+
"step": 3630
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.7545996372117129,
|
| 2555 |
+
"grad_norm": 1.0293713808059692,
|
| 2556 |
+
"learning_rate": 4.912935323383085e-05,
|
| 2557 |
+
"loss": 1.4396793365478515,
|
| 2558 |
+
"step": 3640
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.7566727131381187,
|
| 2562 |
+
"grad_norm": 1.1716481447219849,
|
| 2563 |
+
"learning_rate": 4.8714759535655055e-05,
|
| 2564 |
+
"loss": 1.5675559997558595,
|
| 2565 |
+
"step": 3650
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.7587457890645245,
|
| 2569 |
+
"grad_norm": 1.090667963027954,
|
| 2570 |
+
"learning_rate": 4.830016583747927e-05,
|
| 2571 |
+
"loss": 1.4259960174560546,
|
| 2572 |
+
"step": 3660
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.7608188649909303,
|
| 2576 |
+
"grad_norm": 1.1595834493637085,
|
| 2577 |
+
"learning_rate": 4.7885572139303484e-05,
|
| 2578 |
+
"loss": 1.506321907043457,
|
| 2579 |
+
"step": 3670
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.7628919409173361,
|
| 2583 |
+
"grad_norm": 1.2258275747299194,
|
| 2584 |
+
"learning_rate": 4.74709784411277e-05,
|
| 2585 |
+
"loss": 1.4344300270080566,
|
| 2586 |
+
"step": 3680
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.7649650168437419,
|
| 2590 |
+
"grad_norm": 1.059180498123169,
|
| 2591 |
+
"learning_rate": 4.705638474295191e-05,
|
| 2592 |
+
"loss": 1.4194180488586425,
|
| 2593 |
+
"step": 3690
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.7670380927701477,
|
| 2597 |
+
"grad_norm": 1.0283405780792236,
|
| 2598 |
+
"learning_rate": 4.664179104477612e-05,
|
| 2599 |
+
"loss": 1.466190242767334,
|
| 2600 |
+
"step": 3700
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.7691111686965535,
|
| 2604 |
+
"grad_norm": 1.199347734451294,
|
| 2605 |
+
"learning_rate": 4.6227197346600334e-05,
|
| 2606 |
+
"loss": 1.502589797973633,
|
| 2607 |
+
"step": 3710
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.7711842446229593,
|
| 2611 |
+
"grad_norm": 1.0684884786605835,
|
| 2612 |
+
"learning_rate": 4.581260364842455e-05,
|
| 2613 |
+
"loss": 1.3968034744262696,
|
| 2614 |
+
"step": 3720
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.7732573205493651,
|
| 2618 |
+
"grad_norm": 1.240468978881836,
|
| 2619 |
+
"learning_rate": 4.539800995024876e-05,
|
| 2620 |
+
"loss": 1.4589550971984864,
|
| 2621 |
+
"step": 3730
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.775330396475771,
|
| 2625 |
+
"grad_norm": 1.2167885303497314,
|
| 2626 |
+
"learning_rate": 4.498341625207297e-05,
|
| 2627 |
+
"loss": 1.4414511680603028,
|
| 2628 |
+
"step": 3740
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.7774034724021768,
|
| 2632 |
+
"grad_norm": 1.1880028247833252,
|
| 2633 |
+
"learning_rate": 4.4568822553897185e-05,
|
| 2634 |
+
"loss": 1.4229560852050782,
|
| 2635 |
+
"step": 3750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.7794765483285825,
|
| 2639 |
+
"grad_norm": 1.023346185684204,
|
| 2640 |
+
"learning_rate": 4.41542288557214e-05,
|
| 2641 |
+
"loss": 1.414274311065674,
|
| 2642 |
+
"step": 3760
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.7815496242549883,
|
| 2646 |
+
"grad_norm": 1.0751137733459473,
|
| 2647 |
+
"learning_rate": 4.373963515754561e-05,
|
| 2648 |
+
"loss": 1.4005146980285645,
|
| 2649 |
+
"step": 3770
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.7836227001813941,
|
| 2653 |
+
"grad_norm": 1.1147372722625732,
|
| 2654 |
+
"learning_rate": 4.332504145936982e-05,
|
| 2655 |
+
"loss": 1.4554076194763184,
|
| 2656 |
+
"step": 3780
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.7856957761078,
|
| 2660 |
+
"grad_norm": 1.1774779558181763,
|
| 2661 |
+
"learning_rate": 4.2910447761194036e-05,
|
| 2662 |
+
"loss": 1.4009012222290038,
|
| 2663 |
+
"step": 3790
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.7877688520342058,
|
| 2667 |
+
"grad_norm": 1.0493589639663696,
|
| 2668 |
+
"learning_rate": 4.249585406301824e-05,
|
| 2669 |
+
"loss": 1.4634977340698243,
|
| 2670 |
+
"step": 3800
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.7898419279606116,
|
| 2674 |
+
"grad_norm": 1.1655833721160889,
|
| 2675 |
+
"learning_rate": 4.208126036484246e-05,
|
| 2676 |
+
"loss": 1.4797652244567872,
|
| 2677 |
+
"step": 3810
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.7919150038870174,
|
| 2681 |
+
"grad_norm": 1.1000230312347412,
|
| 2682 |
+
"learning_rate": 4.166666666666667e-05,
|
| 2683 |
+
"loss": 1.4450549125671386,
|
| 2684 |
+
"step": 3820
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.7939880798134231,
|
| 2688 |
+
"grad_norm": 1.0554734468460083,
|
| 2689 |
+
"learning_rate": 4.125207296849088e-05,
|
| 2690 |
+
"loss": 1.4720548629760741,
|
| 2691 |
+
"step": 3830
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.7960611557398289,
|
| 2695 |
+
"grad_norm": 1.1296530961990356,
|
| 2696 |
+
"learning_rate": 4.0837479270315094e-05,
|
| 2697 |
+
"loss": 1.5152462005615235,
|
| 2698 |
+
"step": 3840
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.7981342316662348,
|
| 2702 |
+
"grad_norm": 1.1453872919082642,
|
| 2703 |
+
"learning_rate": 4.042288557213931e-05,
|
| 2704 |
+
"loss": 1.3691265106201171,
|
| 2705 |
+
"step": 3850
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.8002073075926406,
|
| 2709 |
+
"grad_norm": 1.1940151453018188,
|
| 2710 |
+
"learning_rate": 4.0008291873963516e-05,
|
| 2711 |
+
"loss": 1.3959809303283692,
|
| 2712 |
+
"step": 3860
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.8022803835190464,
|
| 2716 |
+
"grad_norm": 1.1130040884017944,
|
| 2717 |
+
"learning_rate": 3.959369817578773e-05,
|
| 2718 |
+
"loss": 1.4111416816711426,
|
| 2719 |
+
"step": 3870
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.8043534594454522,
|
| 2723 |
+
"grad_norm": 1.1695324182510376,
|
| 2724 |
+
"learning_rate": 3.9179104477611945e-05,
|
| 2725 |
+
"loss": 1.507277011871338,
|
| 2726 |
+
"step": 3880
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.806426535371858,
|
| 2730 |
+
"grad_norm": 1.2983999252319336,
|
| 2731 |
+
"learning_rate": 3.876451077943615e-05,
|
| 2732 |
+
"loss": 1.3935456275939941,
|
| 2733 |
+
"step": 3890
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.8084996112982638,
|
| 2737 |
+
"grad_norm": 1.1417698860168457,
|
| 2738 |
+
"learning_rate": 3.834991708126037e-05,
|
| 2739 |
+
"loss": 1.464134407043457,
|
| 2740 |
+
"step": 3900
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.8105726872246696,
|
| 2744 |
+
"grad_norm": 1.0782017707824707,
|
| 2745 |
+
"learning_rate": 3.793532338308458e-05,
|
| 2746 |
+
"loss": 1.4875127792358398,
|
| 2747 |
+
"step": 3910
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.8126457631510754,
|
| 2751 |
+
"grad_norm": 1.2534525394439697,
|
| 2752 |
+
"learning_rate": 3.752072968490879e-05,
|
| 2753 |
+
"loss": 1.5353063583374023,
|
| 2754 |
+
"step": 3920
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.8147188390774812,
|
| 2758 |
+
"grad_norm": 1.2145850658416748,
|
| 2759 |
+
"learning_rate": 3.7106135986733e-05,
|
| 2760 |
+
"loss": 1.4504884719848632,
|
| 2761 |
+
"step": 3930
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.816791915003887,
|
| 2765 |
+
"grad_norm": 1.1368614435195923,
|
| 2766 |
+
"learning_rate": 3.669154228855722e-05,
|
| 2767 |
+
"loss": 1.4631189346313476,
|
| 2768 |
+
"step": 3940
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.8188649909302929,
|
| 2772 |
+
"grad_norm": 1.1054575443267822,
|
| 2773 |
+
"learning_rate": 3.6276948590381425e-05,
|
| 2774 |
+
"loss": 1.44279203414917,
|
| 2775 |
+
"step": 3950
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.8209380668566987,
|
| 2779 |
+
"grad_norm": 1.202141523361206,
|
| 2780 |
+
"learning_rate": 3.586235489220564e-05,
|
| 2781 |
+
"loss": 1.5331624031066895,
|
| 2782 |
+
"step": 3960
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.8230111427831044,
|
| 2786 |
+
"grad_norm": 1.2692559957504272,
|
| 2787 |
+
"learning_rate": 3.5447761194029854e-05,
|
| 2788 |
+
"loss": 1.4537653923034668,
|
| 2789 |
+
"step": 3970
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.8250842187095102,
|
| 2793 |
+
"grad_norm": 1.2438832521438599,
|
| 2794 |
+
"learning_rate": 3.503316749585406e-05,
|
| 2795 |
+
"loss": 1.4415541648864747,
|
| 2796 |
+
"step": 3980
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.827157294635916,
|
| 2800 |
+
"grad_norm": 1.1327502727508545,
|
| 2801 |
+
"learning_rate": 3.4618573797678276e-05,
|
| 2802 |
+
"loss": 1.4588258743286133,
|
| 2803 |
+
"step": 3990
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.8292303705623219,
|
| 2807 |
+
"grad_norm": 1.1558505296707153,
|
| 2808 |
+
"learning_rate": 3.420398009950249e-05,
|
| 2809 |
+
"loss": 1.449343776702881,
|
| 2810 |
+
"step": 4000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.8313034464887277,
|
| 2814 |
+
"grad_norm": 1.146558165550232,
|
| 2815 |
+
"learning_rate": 0.00011689469320066336,
|
| 2816 |
+
"loss": 1.5187210083007812,
|
| 2817 |
+
"step": 4010
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.8333765224151335,
|
| 2821 |
+
"grad_norm": 1.154318928718567,
|
| 2822 |
+
"learning_rate": 0.00011668739635157546,
|
| 2823 |
+
"loss": 1.4608290672302247,
|
| 2824 |
+
"step": 4020
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.8354495983415393,
|
| 2828 |
+
"grad_norm": 1.3546490669250488,
|
| 2829 |
+
"learning_rate": 0.00011648009950248757,
|
| 2830 |
+
"loss": 1.5246877670288086,
|
| 2831 |
+
"step": 4030
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.837522674267945,
|
| 2835 |
+
"grad_norm": 1.1111828088760376,
|
| 2836 |
+
"learning_rate": 0.00011627280265339968,
|
| 2837 |
+
"loss": 1.3747848510742187,
|
| 2838 |
+
"step": 4040
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.8395957501943508,
|
| 2842 |
+
"grad_norm": 1.0534316301345825,
|
| 2843 |
+
"learning_rate": 0.00011606550580431177,
|
| 2844 |
+
"loss": 1.4230124473571777,
|
| 2845 |
+
"step": 4050
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.8416688261207567,
|
| 2849 |
+
"grad_norm": 1.1041001081466675,
|
| 2850 |
+
"learning_rate": 0.00011585820895522388,
|
| 2851 |
+
"loss": 1.5086248397827149,
|
| 2852 |
+
"step": 4060
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.8437419020471625,
|
| 2856 |
+
"grad_norm": 1.1933906078338623,
|
| 2857 |
+
"learning_rate": 0.00011565091210613599,
|
| 2858 |
+
"loss": 1.401639175415039,
|
| 2859 |
+
"step": 4070
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.8458149779735683,
|
| 2863 |
+
"grad_norm": 1.0717347860336304,
|
| 2864 |
+
"learning_rate": 0.0001154436152570481,
|
| 2865 |
+
"loss": 1.4698259353637695,
|
| 2866 |
+
"step": 4080
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.8478880538999741,
|
| 2870 |
+
"grad_norm": 0.955698549747467,
|
| 2871 |
+
"learning_rate": 0.00011523631840796021,
|
| 2872 |
+
"loss": 1.375072193145752,
|
| 2873 |
+
"step": 4090
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.84996112982638,
|
| 2877 |
+
"grad_norm": 1.2389768362045288,
|
| 2878 |
+
"learning_rate": 0.00011502902155887232,
|
| 2879 |
+
"loss": 1.379574966430664,
|
| 2880 |
+
"step": 4100
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 0.8520342057527857,
|
| 2884 |
+
"grad_norm": 1.278762698173523,
|
| 2885 |
+
"learning_rate": 0.0001148217247097844,
|
| 2886 |
+
"loss": 1.4193490982055663,
|
| 2887 |
+
"step": 4110
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 0.8541072816791915,
|
| 2891 |
+
"grad_norm": 1.1002545356750488,
|
| 2892 |
+
"learning_rate": 0.00011461442786069652,
|
| 2893 |
+
"loss": 1.3836387634277343,
|
| 2894 |
+
"step": 4120
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 0.8561803576055973,
|
| 2898 |
+
"grad_norm": 1.1513651609420776,
|
| 2899 |
+
"learning_rate": 0.00011440713101160863,
|
| 2900 |
+
"loss": 1.5280473709106446,
|
| 2901 |
+
"step": 4130
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 0.8582534335320031,
|
| 2905 |
+
"grad_norm": 0.9518608450889587,
|
| 2906 |
+
"learning_rate": 0.00011419983416252074,
|
| 2907 |
+
"loss": 1.4227890968322754,
|
| 2908 |
+
"step": 4140
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 0.8603265094584089,
|
| 2912 |
+
"grad_norm": 1.2304730415344238,
|
| 2913 |
+
"learning_rate": 0.00011399253731343284,
|
| 2914 |
+
"loss": 1.5353459358215331,
|
| 2915 |
+
"step": 4150
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 0.8623995853848148,
|
| 2919 |
+
"grad_norm": 1.1575299501419067,
|
| 2920 |
+
"learning_rate": 0.00011378524046434495,
|
| 2921 |
+
"loss": 1.362869644165039,
|
| 2922 |
+
"step": 4160
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 0.8644726613112205,
|
| 2926 |
+
"grad_norm": 1.1317075490951538,
|
| 2927 |
+
"learning_rate": 0.00011357794361525704,
|
| 2928 |
+
"loss": 1.4479413986206056,
|
| 2929 |
+
"step": 4170
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 0.8665457372376263,
|
| 2933 |
+
"grad_norm": 1.2143278121948242,
|
| 2934 |
+
"learning_rate": 0.00011337064676616915,
|
| 2935 |
+
"loss": 1.4484575271606446,
|
| 2936 |
+
"step": 4180
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 0.8686188131640321,
|
| 2940 |
+
"grad_norm": 1.1178550720214844,
|
| 2941 |
+
"learning_rate": 0.00011316334991708126,
|
| 2942 |
+
"loss": 1.5304969787597655,
|
| 2943 |
+
"step": 4190
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 0.8706918890904379,
|
| 2947 |
+
"grad_norm": 1.2381987571716309,
|
| 2948 |
+
"learning_rate": 0.00011295605306799337,
|
| 2949 |
+
"loss": 1.398491668701172,
|
| 2950 |
+
"step": 4200
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 0.8727649650168438,
|
| 2954 |
+
"grad_norm": 1.288427710533142,
|
| 2955 |
+
"learning_rate": 0.00011274875621890549,
|
| 2956 |
+
"loss": 1.481517219543457,
|
| 2957 |
+
"step": 4210
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 0.8748380409432496,
|
| 2961 |
+
"grad_norm": 1.2424670457839966,
|
| 2962 |
+
"learning_rate": 0.0001125414593698176,
|
| 2963 |
+
"loss": 1.4245829582214355,
|
| 2964 |
+
"step": 4220
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 0.8769111168696554,
|
| 2968 |
+
"grad_norm": 1.0825245380401611,
|
| 2969 |
+
"learning_rate": 0.00011233416252072967,
|
| 2970 |
+
"loss": 1.5052209854125977,
|
| 2971 |
+
"step": 4230
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.8789841927960611,
|
| 2975 |
+
"grad_norm": 1.1469889879226685,
|
| 2976 |
+
"learning_rate": 0.0001121268656716418,
|
| 2977 |
+
"loss": 1.432518768310547,
|
| 2978 |
+
"step": 4240
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 0.8810572687224669,
|
| 2982 |
+
"grad_norm": 1.1925941705703735,
|
| 2983 |
+
"learning_rate": 0.0001119195688225539,
|
| 2984 |
+
"loss": 1.460960865020752,
|
| 2985 |
+
"step": 4250
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 0.8831303446488727,
|
| 2989 |
+
"grad_norm": 1.0974957942962646,
|
| 2990 |
+
"learning_rate": 0.00011171227197346601,
|
| 2991 |
+
"loss": 1.4701688766479493,
|
| 2992 |
+
"step": 4260
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 0.8852034205752786,
|
| 2996 |
+
"grad_norm": 1.19304358959198,
|
| 2997 |
+
"learning_rate": 0.00011150497512437812,
|
| 2998 |
+
"loss": 1.4184856414794922,
|
| 2999 |
+
"step": 4270
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 0.8872764965016844,
|
| 3003 |
+
"grad_norm": 1.2636064291000366,
|
| 3004 |
+
"learning_rate": 0.00011129767827529022,
|
| 3005 |
+
"loss": 1.4618330001831055,
|
| 3006 |
+
"step": 4280
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 0.8893495724280902,
|
| 3010 |
+
"grad_norm": 1.1047471761703491,
|
| 3011 |
+
"learning_rate": 0.00011109038142620232,
|
| 3012 |
+
"loss": 1.4464719772338868,
|
| 3013 |
+
"step": 4290
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 0.891422648354496,
|
| 3017 |
+
"grad_norm": 1.1815509796142578,
|
| 3018 |
+
"learning_rate": 0.00011088308457711442,
|
| 3019 |
+
"loss": 1.4445013999938965,
|
| 3020 |
+
"step": 4300
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 0.8934957242809017,
|
| 3024 |
+
"grad_norm": 1.15771484375,
|
| 3025 |
+
"learning_rate": 0.00011067578772802653,
|
| 3026 |
+
"loss": 1.4567338943481445,
|
| 3027 |
+
"step": 4310
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 0.8955688002073076,
|
| 3031 |
+
"grad_norm": 1.094064474105835,
|
| 3032 |
+
"learning_rate": 0.00011046849087893865,
|
| 3033 |
+
"loss": 1.4705141067504883,
|
| 3034 |
+
"step": 4320
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 0.8976418761337134,
|
| 3038 |
+
"grad_norm": 1.1300767660140991,
|
| 3039 |
+
"learning_rate": 0.00011026119402985076,
|
| 3040 |
+
"loss": 1.3876087188720703,
|
| 3041 |
+
"step": 4330
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 0.8997149520601192,
|
| 3045 |
+
"grad_norm": 1.255149483680725,
|
| 3046 |
+
"learning_rate": 0.00011005389718076287,
|
| 3047 |
+
"loss": 1.3945764541625976,
|
| 3048 |
+
"step": 4340
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 0.901788027986525,
|
| 3052 |
+
"grad_norm": 1.1853265762329102,
|
| 3053 |
+
"learning_rate": 0.00010984660033167495,
|
| 3054 |
+
"loss": 1.4600879669189453,
|
| 3055 |
+
"step": 4350
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 0.9038611039129308,
|
| 3059 |
+
"grad_norm": 1.3775529861450195,
|
| 3060 |
+
"learning_rate": 0.00010963930348258707,
|
| 3061 |
+
"loss": 1.3908918380737305,
|
| 3062 |
+
"step": 4360
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.9059341798393367,
|
| 3066 |
+
"grad_norm": 1.178391695022583,
|
| 3067 |
+
"learning_rate": 0.00010943200663349918,
|
| 3068 |
+
"loss": 1.418002223968506,
|
| 3069 |
+
"step": 4370
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 0.9080072557657424,
|
| 3073 |
+
"grad_norm": 1.3530340194702148,
|
| 3074 |
+
"learning_rate": 0.00010922470978441128,
|
| 3075 |
+
"loss": 1.360008716583252,
|
| 3076 |
+
"step": 4380
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 0.9100803316921482,
|
| 3080 |
+
"grad_norm": 1.3142609596252441,
|
| 3081 |
+
"learning_rate": 0.00010901741293532339,
|
| 3082 |
+
"loss": 1.3430272102355958,
|
| 3083 |
+
"step": 4390
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 0.912153407618554,
|
| 3087 |
+
"grad_norm": 1.1689645051956177,
|
| 3088 |
+
"learning_rate": 0.0001088101160862355,
|
| 3089 |
+
"loss": 1.5633913040161134,
|
| 3090 |
+
"step": 4400
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 0.9142264835449598,
|
| 3094 |
+
"grad_norm": 1.2114495038986206,
|
| 3095 |
+
"learning_rate": 0.00010860281923714759,
|
| 3096 |
+
"loss": 1.4697650909423827,
|
| 3097 |
+
"step": 4410
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 0.9162995594713657,
|
| 3101 |
+
"grad_norm": 1.2312393188476562,
|
| 3102 |
+
"learning_rate": 0.0001083955223880597,
|
| 3103 |
+
"loss": 1.4190072059631347,
|
| 3104 |
+
"step": 4420
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 0.9183726353977715,
|
| 3108 |
+
"grad_norm": 1.3181791305541992,
|
| 3109 |
+
"learning_rate": 0.0001081882255389718,
|
| 3110 |
+
"loss": 1.3760835647583007,
|
| 3111 |
+
"step": 4430
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 0.9204457113241773,
|
| 3115 |
+
"grad_norm": 1.1612746715545654,
|
| 3116 |
+
"learning_rate": 0.00010798092868988393,
|
| 3117 |
+
"loss": 1.4294224739074708,
|
| 3118 |
+
"step": 4440
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 0.922518787250583,
|
| 3122 |
+
"grad_norm": 1.0622650384902954,
|
| 3123 |
+
"learning_rate": 0.00010777363184079603,
|
| 3124 |
+
"loss": 1.3979280471801758,
|
| 3125 |
+
"step": 4450
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 0.9245918631769888,
|
| 3129 |
+
"grad_norm": 1.1344703435897827,
|
| 3130 |
+
"learning_rate": 0.00010756633499170814,
|
| 3131 |
+
"loss": 1.432724380493164,
|
| 3132 |
+
"step": 4460
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 0.9266649391033946,
|
| 3136 |
+
"grad_norm": 1.3609569072723389,
|
| 3137 |
+
"learning_rate": 0.00010735903814262023,
|
| 3138 |
+
"loss": 1.4266067504882813,
|
| 3139 |
+
"step": 4470
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 0.9287380150298005,
|
| 3143 |
+
"grad_norm": 1.2317551374435425,
|
| 3144 |
+
"learning_rate": 0.00010715174129353234,
|
| 3145 |
+
"loss": 1.3972136497497558,
|
| 3146 |
+
"step": 4480
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 0.9308110909562063,
|
| 3150 |
+
"grad_norm": 1.1485719680786133,
|
| 3151 |
+
"learning_rate": 0.00010694444444444445,
|
| 3152 |
+
"loss": 1.4437122344970703,
|
| 3153 |
+
"step": 4490
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 0.9328841668826121,
|
| 3157 |
+
"grad_norm": 1.1265562772750854,
|
| 3158 |
+
"learning_rate": 0.00010673714759535656,
|
| 3159 |
+
"loss": 1.3951814651489258,
|
| 3160 |
+
"step": 4500
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 0.9349572428090179,
|
| 3164 |
+
"grad_norm": 1.2382943630218506,
|
| 3165 |
+
"learning_rate": 0.00010652985074626866,
|
| 3166 |
+
"loss": 1.47876033782959,
|
| 3167 |
+
"step": 4510
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 0.9370303187354236,
|
| 3171 |
+
"grad_norm": 1.1904460191726685,
|
| 3172 |
+
"learning_rate": 0.00010632255389718078,
|
| 3173 |
+
"loss": 1.5116327285766602,
|
| 3174 |
+
"step": 4520
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 0.9391033946618295,
|
| 3178 |
+
"grad_norm": 1.2784380912780762,
|
| 3179 |
+
"learning_rate": 0.00010611525704809286,
|
| 3180 |
+
"loss": 1.4328707695007323,
|
| 3181 |
+
"step": 4530
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 0.9411764705882353,
|
| 3185 |
+
"grad_norm": 1.1920058727264404,
|
| 3186 |
+
"learning_rate": 0.00010590796019900497,
|
| 3187 |
+
"loss": 1.4105209350585937,
|
| 3188 |
+
"step": 4540
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 0.9432495465146411,
|
| 3192 |
+
"grad_norm": 1.3006956577301025,
|
| 3193 |
+
"learning_rate": 0.00010570066334991708,
|
| 3194 |
+
"loss": 1.4261651039123535,
|
| 3195 |
+
"step": 4550
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 0.9453226224410469,
|
| 3199 |
+
"grad_norm": 1.1092578172683716,
|
| 3200 |
+
"learning_rate": 0.0001054933665008292,
|
| 3201 |
+
"loss": 1.3674508094787599,
|
| 3202 |
+
"step": 4560
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 0.9473956983674527,
|
| 3206 |
+
"grad_norm": 1.2003893852233887,
|
| 3207 |
+
"learning_rate": 0.0001052860696517413,
|
| 3208 |
+
"loss": 1.411275577545166,
|
| 3209 |
+
"step": 4570
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 0.9494687742938586,
|
| 3213 |
+
"grad_norm": 1.1365995407104492,
|
| 3214 |
+
"learning_rate": 0.00010507877280265341,
|
| 3215 |
+
"loss": 1.4263607025146485,
|
| 3216 |
+
"step": 4580
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 0.9515418502202643,
|
| 3220 |
+
"grad_norm": 1.1568050384521484,
|
| 3221 |
+
"learning_rate": 0.0001048714759535655,
|
| 3222 |
+
"loss": 1.4921070098876954,
|
| 3223 |
+
"step": 4590
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 0.9536149261466701,
|
| 3227 |
+
"grad_norm": 1.249493956565857,
|
| 3228 |
+
"learning_rate": 0.00010466417910447761,
|
| 3229 |
+
"loss": 1.4664103507995605,
|
| 3230 |
+
"step": 4600
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 0.9556880020730759,
|
| 3234 |
+
"grad_norm": 1.1990628242492676,
|
| 3235 |
+
"learning_rate": 0.00010445688225538972,
|
| 3236 |
+
"loss": 1.4022604942321777,
|
| 3237 |
+
"step": 4610
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 0.9577610779994817,
|
| 3241 |
+
"grad_norm": 1.198508858680725,
|
| 3242 |
+
"learning_rate": 0.00010424958540630183,
|
| 3243 |
+
"loss": 1.3575029373168945,
|
| 3244 |
+
"step": 4620
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 0.9598341539258876,
|
| 3248 |
+
"grad_norm": 1.4220664501190186,
|
| 3249 |
+
"learning_rate": 0.00010404228855721393,
|
| 3250 |
+
"loss": 1.506014347076416,
|
| 3251 |
+
"step": 4630
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 0.9619072298522934,
|
| 3255 |
+
"grad_norm": 1.1849695444107056,
|
| 3256 |
+
"learning_rate": 0.00010383499170812606,
|
| 3257 |
+
"loss": 1.3853163719177246,
|
| 3258 |
+
"step": 4640
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 0.9639803057786992,
|
| 3262 |
+
"grad_norm": 1.183779001235962,
|
| 3263 |
+
"learning_rate": 0.00010362769485903814,
|
| 3264 |
+
"loss": 1.378060531616211,
|
| 3265 |
+
"step": 4650
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 0.9660533817051049,
|
| 3269 |
+
"grad_norm": 1.159185767173767,
|
| 3270 |
+
"learning_rate": 0.00010342039800995024,
|
| 3271 |
+
"loss": 1.5042824745178223,
|
| 3272 |
+
"step": 4660
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 0.9681264576315107,
|
| 3276 |
+
"grad_norm": 1.225111484527588,
|
| 3277 |
+
"learning_rate": 0.00010321310116086236,
|
| 3278 |
+
"loss": 1.4617128372192383,
|
| 3279 |
+
"step": 4670
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 0.9701995335579165,
|
| 3283 |
+
"grad_norm": 1.1813310384750366,
|
| 3284 |
+
"learning_rate": 0.00010300580431177447,
|
| 3285 |
+
"loss": 1.4024372100830078,
|
| 3286 |
+
"step": 4680
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 0.9722726094843224,
|
| 3290 |
+
"grad_norm": 1.261643648147583,
|
| 3291 |
+
"learning_rate": 0.00010279850746268658,
|
| 3292 |
+
"loss": 1.360646915435791,
|
| 3293 |
+
"step": 4690
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 0.9743456854107282,
|
| 3297 |
+
"grad_norm": 1.0765501260757446,
|
| 3298 |
+
"learning_rate": 0.00010259121061359869,
|
| 3299 |
+
"loss": 1.3550106048583985,
|
| 3300 |
+
"step": 4700
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 0.976418761337134,
|
| 3304 |
+
"grad_norm": 1.1051616668701172,
|
| 3305 |
+
"learning_rate": 0.00010238391376451078,
|
| 3306 |
+
"loss": 1.395486831665039,
|
| 3307 |
+
"step": 4710
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 0.9784918372635398,
|
| 3311 |
+
"grad_norm": 1.2162697315216064,
|
| 3312 |
+
"learning_rate": 0.00010217661691542289,
|
| 3313 |
+
"loss": 1.4161664962768554,
|
| 3314 |
+
"step": 4720
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 0.9805649131899455,
|
| 3318 |
+
"grad_norm": 1.2934092283248901,
|
| 3319 |
+
"learning_rate": 0.000101969320066335,
|
| 3320 |
+
"loss": 1.4680258750915527,
|
| 3321 |
+
"step": 4730
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 0.9826379891163514,
|
| 3325 |
+
"grad_norm": 1.1861159801483154,
|
| 3326 |
+
"learning_rate": 0.0001017620232172471,
|
| 3327 |
+
"loss": 1.4943526268005372,
|
| 3328 |
+
"step": 4740
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 0.9847110650427572,
|
| 3332 |
+
"grad_norm": 1.2565635442733765,
|
| 3333 |
+
"learning_rate": 0.00010155472636815921,
|
| 3334 |
+
"loss": 1.4541117668151855,
|
| 3335 |
+
"step": 4750
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 0.986784140969163,
|
| 3339 |
+
"grad_norm": 1.38951575756073,
|
| 3340 |
+
"learning_rate": 0.00010134742951907133,
|
| 3341 |
+
"loss": 1.3703868865966797,
|
| 3342 |
+
"step": 4760
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 0.9888572168955688,
|
| 3346 |
+
"grad_norm": 1.1929153203964233,
|
| 3347 |
+
"learning_rate": 0.00010114013266998341,
|
| 3348 |
+
"loss": 1.4121877670288085,
|
| 3349 |
+
"step": 4770
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 0.9909302928219746,
|
| 3353 |
+
"grad_norm": 1.1389548778533936,
|
| 3354 |
+
"learning_rate": 0.00010093283582089552,
|
| 3355 |
+
"loss": 1.371178436279297,
|
| 3356 |
+
"step": 4780
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 0.9930033687483804,
|
| 3360 |
+
"grad_norm": 0.9990752339363098,
|
| 3361 |
+
"learning_rate": 0.00010072553897180764,
|
| 3362 |
+
"loss": 1.394187831878662,
|
| 3363 |
+
"step": 4790
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 0.9950764446747862,
|
| 3367 |
+
"grad_norm": 1.1418439149856567,
|
| 3368 |
+
"learning_rate": 0.00010051824212271974,
|
| 3369 |
+
"loss": 1.3987725257873536,
|
| 3370 |
+
"step": 4800
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 0.9952837522674268,
|
| 3374 |
+
"grad_norm": 1.3999691009521484,
|
| 3375 |
+
"learning_rate": 0.00010049751243781096,
|
| 3376 |
+
"loss": 1.56894850730896,
|
| 3377 |
+
"step": 4801
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 0.9954910598600674,
|
| 3381 |
+
"grad_norm": 1.1055763959884644,
|
| 3382 |
+
"learning_rate": 9.535655058043119e-07,
|
| 3383 |
+
"loss": 1.3579680919647217,
|
| 3384 |
+
"step": 4802
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 0.995698367452708,
|
| 3388 |
+
"grad_norm": 1.2521191835403442,
|
| 3389 |
+
"learning_rate": 9.121061359867331e-07,
|
| 3390 |
+
"loss": 1.6727182865142822,
|
| 3391 |
+
"step": 4803
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 0.9959056750453485,
|
| 3395 |
+
"grad_norm": 1.1679822206497192,
|
| 3396 |
+
"learning_rate": 8.706467661691543e-07,
|
| 3397 |
+
"loss": 1.5550488233566284,
|
| 3398 |
+
"step": 4804
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 0.9961129826379891,
|
| 3402 |
+
"grad_norm": 1.414447546005249,
|
| 3403 |
+
"learning_rate": 8.291873963515756e-07,
|
| 3404 |
+
"loss": 1.2959469556808472,
|
| 3405 |
+
"step": 4805
|
| 3406 |
+
},
|
| 3407 |
+
{
|
| 3408 |
+
"epoch": 0.9963202902306297,
|
| 3409 |
+
"grad_norm": 1.2053686380386353,
|
| 3410 |
+
"learning_rate": 7.877280265339968e-07,
|
| 3411 |
+
"loss": 1.6059751510620117,
|
| 3412 |
+
"step": 4806
|
| 3413 |
+
},
|
| 3414 |
+
{
|
| 3415 |
+
"epoch": 0.9965275978232703,
|
| 3416 |
+
"grad_norm": 1.3234610557556152,
|
| 3417 |
+
"learning_rate": 7.462686567164179e-07,
|
| 3418 |
+
"loss": 1.3246705532073975,
|
| 3419 |
+
"step": 4807
|
| 3420 |
+
},
|
| 3421 |
+
{
|
| 3422 |
+
"epoch": 0.9967349054159108,
|
| 3423 |
+
"grad_norm": 1.275701880455017,
|
| 3424 |
+
"learning_rate": 7.048092868988392e-07,
|
| 3425 |
+
"loss": 1.456787109375,
|
| 3426 |
+
"step": 4808
|
| 3427 |
+
},
|
| 3428 |
+
{
|
| 3429 |
+
"epoch": 0.9969422130085515,
|
| 3430 |
+
"grad_norm": 1.0960595607757568,
|
| 3431 |
+
"learning_rate": 6.633499170812604e-07,
|
| 3432 |
+
"loss": 1.6712136268615723,
|
| 3433 |
+
"step": 4809
|
| 3434 |
+
},
|
| 3435 |
+
{
|
| 3436 |
+
"epoch": 0.997149520601192,
|
| 3437 |
+
"grad_norm": 1.1167244911193848,
|
| 3438 |
+
"learning_rate": 6.218905472636816e-07,
|
| 3439 |
+
"loss": 1.2081254720687866,
|
| 3440 |
+
"step": 4810
|
| 3441 |
+
},
|
| 3442 |
+
{
|
| 3443 |
+
"epoch": 0.9973568281938326,
|
| 3444 |
+
"grad_norm": 1.1857860088348389,
|
| 3445 |
+
"learning_rate": 5.804311774461028e-07,
|
| 3446 |
+
"loss": 1.4792537689208984,
|
| 3447 |
+
"step": 4811
|
| 3448 |
+
},
|
| 3449 |
+
{
|
| 3450 |
+
"epoch": 0.9975641357864732,
|
| 3451 |
+
"grad_norm": 1.1021283864974976,
|
| 3452 |
+
"learning_rate": 5.38971807628524e-07,
|
| 3453 |
+
"loss": 1.2333704233169556,
|
| 3454 |
+
"step": 4812
|
| 3455 |
+
},
|
| 3456 |
+
{
|
| 3457 |
+
"epoch": 0.9977714433791137,
|
| 3458 |
+
"grad_norm": 1.0850183963775635,
|
| 3459 |
+
"learning_rate": 4.975124378109453e-07,
|
| 3460 |
+
"loss": 1.3954815864562988,
|
| 3461 |
+
"step": 4813
|
| 3462 |
+
},
|
| 3463 |
+
{
|
| 3464 |
+
"epoch": 0.9979787509717544,
|
| 3465 |
+
"grad_norm": 1.2729003429412842,
|
| 3466 |
+
"learning_rate": 4.5605306799336654e-07,
|
| 3467 |
+
"loss": 1.5298696756362915,
|
| 3468 |
+
"step": 4814
|
| 3469 |
+
},
|
| 3470 |
+
{
|
| 3471 |
+
"epoch": 0.9981860585643949,
|
| 3472 |
+
"grad_norm": 1.2735594511032104,
|
| 3473 |
+
"learning_rate": 4.145936981757878e-07,
|
| 3474 |
+
"loss": 1.3652870655059814,
|
| 3475 |
+
"step": 4815
|
| 3476 |
+
},
|
| 3477 |
+
{
|
| 3478 |
+
"epoch": 0.9983933661570356,
|
| 3479 |
+
"grad_norm": 1.3938478231430054,
|
| 3480 |
+
"learning_rate": 3.7313432835820895e-07,
|
| 3481 |
+
"loss": 1.5470430850982666,
|
| 3482 |
+
"step": 4816
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 0.9986006737496761,
|
| 3486 |
+
"grad_norm": 1.2034921646118164,
|
| 3487 |
+
"learning_rate": 3.316749585406302e-07,
|
| 3488 |
+
"loss": 1.539093017578125,
|
| 3489 |
+
"step": 4817
|
| 3490 |
+
},
|
| 3491 |
+
{
|
| 3492 |
+
"epoch": 0.9988079813423166,
|
| 3493 |
+
"grad_norm": 1.165834903717041,
|
| 3494 |
+
"learning_rate": 2.902155887230514e-07,
|
| 3495 |
+
"loss": 1.3995617628097534,
|
| 3496 |
+
"step": 4818
|
| 3497 |
+
},
|
| 3498 |
+
{
|
| 3499 |
+
"epoch": 0.9990152889349573,
|
| 3500 |
+
"grad_norm": 1.1757153272628784,
|
| 3501 |
+
"learning_rate": 2.4875621890547267e-07,
|
| 3502 |
+
"loss": 1.4894084930419922,
|
| 3503 |
+
"step": 4819
|
| 3504 |
+
},
|
| 3505 |
+
{
|
| 3506 |
+
"epoch": 0.9992225965275978,
|
| 3507 |
+
"grad_norm": 1.3626255989074707,
|
| 3508 |
+
"learning_rate": 2.072968490878939e-07,
|
| 3509 |
+
"loss": 1.5547418594360352,
|
| 3510 |
+
"step": 4820
|
| 3511 |
+
},
|
| 3512 |
+
{
|
| 3513 |
+
"epoch": 0.9994299041202384,
|
| 3514 |
+
"grad_norm": 1.1462852954864502,
|
| 3515 |
+
"learning_rate": 1.658374792703151e-07,
|
| 3516 |
+
"loss": 1.5449320077896118,
|
| 3517 |
+
"step": 4821
|
| 3518 |
+
},
|
| 3519 |
+
{
|
| 3520 |
+
"epoch": 0.999637211712879,
|
| 3521 |
+
"grad_norm": 1.122637152671814,
|
| 3522 |
+
"learning_rate": 1.2437810945273633e-07,
|
| 3523 |
+
"loss": 1.3381319046020508,
|
| 3524 |
+
"step": 4822
|
| 3525 |
+
},
|
| 3526 |
+
{
|
| 3527 |
+
"epoch": 0.9998445193055195,
|
| 3528 |
+
"grad_norm": 1.303135871887207,
|
| 3529 |
+
"learning_rate": 8.291873963515755e-08,
|
| 3530 |
+
"loss": 1.4987614154815674,
|
| 3531 |
+
"step": 4823
|
| 3532 |
+
},
|
| 3533 |
+
{
|
| 3534 |
+
"epoch": 1.0,
|
| 3535 |
+
"grad_norm": 1.30817711353302,
|
| 3536 |
+
"learning_rate": 4.1459369817578775e-08,
|
| 3537 |
+
"loss": 1.4066091775894165,
|
| 3538 |
+
"step": 4824
|
| 3539 |
+
}
|
| 3540 |
+
],
|
| 3541 |
+
"logging_steps": 1,
|
| 3542 |
+
"max_steps": 4824,
|
| 3543 |
+
"num_input_tokens_seen": 0,
|
| 3544 |
+
"num_train_epochs": 1,
|
| 3545 |
+
"save_steps": 1,
|
| 3546 |
+
"stateful_callbacks": {
|
| 3547 |
+
"TrainerControl": {
|
| 3548 |
+
"args": {
|
| 3549 |
+
"should_epoch_stop": false,
|
| 3550 |
+
"should_evaluate": false,
|
| 3551 |
+
"should_log": false,
|
| 3552 |
+
"should_save": true,
|
| 3553 |
+
"should_training_stop": true
|
| 3554 |
+
},
|
| 3555 |
+
"attributes": {}
|
| 3556 |
+
}
|
| 3557 |
+
},
|
| 3558 |
+
"total_flos": 9.698521011117097e+17,
|
| 3559 |
+
"train_batch_size": 8,
|
| 3560 |
+
"trial_name": null,
|
| 3561 |
+
"trial_params": null
|
| 3562 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbeeccb81ecffa903bc9a57111b482d318cd96334f1e17944f76415f13be69dd
|
| 3 |
+
size 4728
|