Upload folder using huggingface_hub
Browse files- README.md +202 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +3534 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/csm-1b
|
| 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 0.15.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/csm-1b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 32,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"down_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:935c9d7f6527533be46577a43626d788791243fb59fe44b4fc0f89e0d6d569b9
|
| 3 |
+
size 116190168
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aedb37a4bd3020b8924944630aa09bd26c4c19ec9f24a81bb50dbab11162dcd2
|
| 3 |
+
size 55042373
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2922886dc37f9211a4affea61093cbe4db90c0a37e91e7edac63ec0cf7b13d45
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41759ead8b9ae6a100eb8e6f2f00a602a7bd65aedbf0b0291bd1c72e538569e7
|
| 3 |
+
size 1465
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3534 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.668896321070234,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.013377926421404682,
|
| 14 |
+
"grad_norm": 0.5197079181671143,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 4.2636,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.026755852842809364,
|
| 21 |
+
"grad_norm": 0.5626901984214783,
|
| 22 |
+
"learning_rate": 4e-05,
|
| 23 |
+
"loss": 4.3971,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04013377926421405,
|
| 28 |
+
"grad_norm": 0.5167903304100037,
|
| 29 |
+
"learning_rate": 8e-05,
|
| 30 |
+
"loss": 4.3249,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05351170568561873,
|
| 35 |
+
"grad_norm": 0.4764951169490814,
|
| 36 |
+
"learning_rate": 0.00012,
|
| 37 |
+
"loss": 4.2031,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06688963210702341,
|
| 42 |
+
"grad_norm": 0.45488491654396057,
|
| 43 |
+
"learning_rate": 0.00016,
|
| 44 |
+
"loss": 4.3914,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0802675585284281,
|
| 49 |
+
"grad_norm": 0.568274736404419,
|
| 50 |
+
"learning_rate": 0.0002,
|
| 51 |
+
"loss": 4.2346,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09364548494983277,
|
| 56 |
+
"grad_norm": 0.5974003076553345,
|
| 57 |
+
"learning_rate": 0.0001999555061179088,
|
| 58 |
+
"loss": 4.131,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.10702341137123746,
|
| 63 |
+
"grad_norm": 0.6204471588134766,
|
| 64 |
+
"learning_rate": 0.00019991101223581757,
|
| 65 |
+
"loss": 4.2256,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12040133779264214,
|
| 70 |
+
"grad_norm": 0.7143808603286743,
|
| 71 |
+
"learning_rate": 0.00019986651835372636,
|
| 72 |
+
"loss": 3.8449,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13377926421404682,
|
| 77 |
+
"grad_norm": 0.7799420356750488,
|
| 78 |
+
"learning_rate": 0.00019982202447163517,
|
| 79 |
+
"loss": 4.4301,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.14715719063545152,
|
| 84 |
+
"grad_norm": 0.8880407214164734,
|
| 85 |
+
"learning_rate": 0.00019977753058954395,
|
| 86 |
+
"loss": 4.2266,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1605351170568562,
|
| 91 |
+
"grad_norm": 0.7776209712028503,
|
| 92 |
+
"learning_rate": 0.00019973303670745273,
|
| 93 |
+
"loss": 4.3208,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.17391304347826086,
|
| 98 |
+
"grad_norm": 0.9125858545303345,
|
| 99 |
+
"learning_rate": 0.0001996885428253615,
|
| 100 |
+
"loss": 4.4363,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.18729096989966554,
|
| 105 |
+
"grad_norm": 0.9000256657600403,
|
| 106 |
+
"learning_rate": 0.00019964404894327032,
|
| 107 |
+
"loss": 4.2917,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.20066889632107024,
|
| 112 |
+
"grad_norm": 0.9995108246803284,
|
| 113 |
+
"learning_rate": 0.00019959955506117908,
|
| 114 |
+
"loss": 4.1784,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.2140468227424749,
|
| 119 |
+
"grad_norm": 0.9209024310112,
|
| 120 |
+
"learning_rate": 0.0001995550611790879,
|
| 121 |
+
"loss": 4.7852,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.22742474916387959,
|
| 126 |
+
"grad_norm": 0.9421981573104858,
|
| 127 |
+
"learning_rate": 0.00019951056729699667,
|
| 128 |
+
"loss": 4.8501,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2408026755852843,
|
| 133 |
+
"grad_norm": 0.9213201403617859,
|
| 134 |
+
"learning_rate": 0.00019946607341490545,
|
| 135 |
+
"loss": 4.7923,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.25418060200668896,
|
| 140 |
+
"grad_norm": 0.9378194212913513,
|
| 141 |
+
"learning_rate": 0.00019942157953281423,
|
| 142 |
+
"loss": 4.9593,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.26755852842809363,
|
| 147 |
+
"grad_norm": 1.0096492767333984,
|
| 148 |
+
"learning_rate": 0.00019937708565072304,
|
| 149 |
+
"loss": 4.7099,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2809364548494983,
|
| 154 |
+
"grad_norm": 0.8903587460517883,
|
| 155 |
+
"learning_rate": 0.00019933259176863183,
|
| 156 |
+
"loss": 4.3746,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.29431438127090304,
|
| 161 |
+
"grad_norm": 0.7808490991592407,
|
| 162 |
+
"learning_rate": 0.0001992880978865406,
|
| 163 |
+
"loss": 4.5873,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3076923076923077,
|
| 168 |
+
"grad_norm": 0.8145670294761658,
|
| 169 |
+
"learning_rate": 0.0001992436040044494,
|
| 170 |
+
"loss": 4.7924,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.3210702341137124,
|
| 175 |
+
"grad_norm": 0.7945849299430847,
|
| 176 |
+
"learning_rate": 0.0001991991101223582,
|
| 177 |
+
"loss": 4.8881,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.33444816053511706,
|
| 182 |
+
"grad_norm": 0.7871395349502563,
|
| 183 |
+
"learning_rate": 0.00019915461624026696,
|
| 184 |
+
"loss": 4.6922,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.34782608695652173,
|
| 189 |
+
"grad_norm": 0.9111238718032837,
|
| 190 |
+
"learning_rate": 0.00019911012235817577,
|
| 191 |
+
"loss": 4.9982,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.3612040133779264,
|
| 196 |
+
"grad_norm": 0.7121369242668152,
|
| 197 |
+
"learning_rate": 0.00019906562847608455,
|
| 198 |
+
"loss": 4.4756,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3745819397993311,
|
| 203 |
+
"grad_norm": 0.7118422389030457,
|
| 204 |
+
"learning_rate": 0.00019902113459399333,
|
| 205 |
+
"loss": 5.1389,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3879598662207358,
|
| 210 |
+
"grad_norm": 0.7100292444229126,
|
| 211 |
+
"learning_rate": 0.0001989766407119021,
|
| 212 |
+
"loss": 4.7691,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.4013377926421405,
|
| 217 |
+
"grad_norm": 0.708591639995575,
|
| 218 |
+
"learning_rate": 0.00019893214682981092,
|
| 219 |
+
"loss": 4.8721,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.41471571906354515,
|
| 224 |
+
"grad_norm": 0.6711616516113281,
|
| 225 |
+
"learning_rate": 0.0001988876529477197,
|
| 226 |
+
"loss": 4.9152,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.4280936454849498,
|
| 231 |
+
"grad_norm": 0.7158232927322388,
|
| 232 |
+
"learning_rate": 0.0001988431590656285,
|
| 233 |
+
"loss": 4.828,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.4414715719063545,
|
| 238 |
+
"grad_norm": 0.6246087551116943,
|
| 239 |
+
"learning_rate": 0.00019879866518353727,
|
| 240 |
+
"loss": 4.8452,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.45484949832775917,
|
| 245 |
+
"grad_norm": 0.6088873744010925,
|
| 246 |
+
"learning_rate": 0.00019875417130144608,
|
| 247 |
+
"loss": 4.9702,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4682274247491639,
|
| 252 |
+
"grad_norm": 0.5798126459121704,
|
| 253 |
+
"learning_rate": 0.00019870967741935483,
|
| 254 |
+
"loss": 4.9838,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.4816053511705686,
|
| 259 |
+
"grad_norm": 0.6268919706344604,
|
| 260 |
+
"learning_rate": 0.00019866518353726364,
|
| 261 |
+
"loss": 4.7636,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.49498327759197325,
|
| 266 |
+
"grad_norm": 0.5649904012680054,
|
| 267 |
+
"learning_rate": 0.00019862068965517243,
|
| 268 |
+
"loss": 4.506,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.5083612040133779,
|
| 273 |
+
"grad_norm": 0.5947792530059814,
|
| 274 |
+
"learning_rate": 0.0001985761957730812,
|
| 275 |
+
"loss": 4.8057,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.5217391304347826,
|
| 280 |
+
"grad_norm": 0.6204257011413574,
|
| 281 |
+
"learning_rate": 0.00019853170189099,
|
| 282 |
+
"loss": 5.0511,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5351170568561873,
|
| 287 |
+
"grad_norm": 0.5972265601158142,
|
| 288 |
+
"learning_rate": 0.0001984872080088988,
|
| 289 |
+
"loss": 4.924,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5484949832775919,
|
| 294 |
+
"grad_norm": 0.6117077469825745,
|
| 295 |
+
"learning_rate": 0.00019844271412680758,
|
| 296 |
+
"loss": 4.8729,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5618729096989966,
|
| 301 |
+
"grad_norm": 0.5085508823394775,
|
| 302 |
+
"learning_rate": 0.00019839822024471637,
|
| 303 |
+
"loss": 4.3616,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5752508361204013,
|
| 308 |
+
"grad_norm": 0.550647497177124,
|
| 309 |
+
"learning_rate": 0.00019835372636262515,
|
| 310 |
+
"loss": 5.2512,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5886287625418061,
|
| 315 |
+
"grad_norm": 0.48329588770866394,
|
| 316 |
+
"learning_rate": 0.00019830923248053396,
|
| 317 |
+
"loss": 4.9501,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.6020066889632107,
|
| 322 |
+
"grad_norm": 0.6313246488571167,
|
| 323 |
+
"learning_rate": 0.0001982647385984427,
|
| 324 |
+
"loss": 4.5767,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.6153846153846154,
|
| 329 |
+
"grad_norm": 0.5111928582191467,
|
| 330 |
+
"learning_rate": 0.00019822024471635152,
|
| 331 |
+
"loss": 4.5586,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.6287625418060201,
|
| 336 |
+
"grad_norm": 0.5264492630958557,
|
| 337 |
+
"learning_rate": 0.0001981757508342603,
|
| 338 |
+
"loss": 4.7033,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.6421404682274248,
|
| 343 |
+
"grad_norm": 0.5058289170265198,
|
| 344 |
+
"learning_rate": 0.0001981312569521691,
|
| 345 |
+
"loss": 4.8396,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6555183946488294,
|
| 350 |
+
"grad_norm": 0.5688439607620239,
|
| 351 |
+
"learning_rate": 0.00019808676307007787,
|
| 352 |
+
"loss": 5.1887,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6688963210702341,
|
| 357 |
+
"grad_norm": 0.5488842129707336,
|
| 358 |
+
"learning_rate": 0.00019804226918798665,
|
| 359 |
+
"loss": 4.6075,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6822742474916388,
|
| 364 |
+
"grad_norm": 0.5358632206916809,
|
| 365 |
+
"learning_rate": 0.00019799777530589546,
|
| 366 |
+
"loss": 5.0205,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6956521739130435,
|
| 371 |
+
"grad_norm": 0.47869494557380676,
|
| 372 |
+
"learning_rate": 0.00019795328142380422,
|
| 373 |
+
"loss": 4.8495,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.7090301003344481,
|
| 378 |
+
"grad_norm": 0.49378660321235657,
|
| 379 |
+
"learning_rate": 0.00019790878754171303,
|
| 380 |
+
"loss": 4.6563,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.7224080267558528,
|
| 385 |
+
"grad_norm": 0.5167868733406067,
|
| 386 |
+
"learning_rate": 0.0001978642936596218,
|
| 387 |
+
"loss": 5.2558,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.7357859531772575,
|
| 392 |
+
"grad_norm": 0.5230040550231934,
|
| 393 |
+
"learning_rate": 0.0001978197997775306,
|
| 394 |
+
"loss": 4.7769,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.7491638795986622,
|
| 399 |
+
"grad_norm": 0.4822310507297516,
|
| 400 |
+
"learning_rate": 0.00019777530589543937,
|
| 401 |
+
"loss": 4.9282,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7625418060200669,
|
| 406 |
+
"grad_norm": 0.500045895576477,
|
| 407 |
+
"learning_rate": 0.00019773081201334818,
|
| 408 |
+
"loss": 5.0399,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.7759197324414716,
|
| 413 |
+
"grad_norm": 0.4740642309188843,
|
| 414 |
+
"learning_rate": 0.00019768631813125696,
|
| 415 |
+
"loss": 4.8041,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7892976588628763,
|
| 420 |
+
"grad_norm": 0.45918184518814087,
|
| 421 |
+
"learning_rate": 0.00019764182424916575,
|
| 422 |
+
"loss": 4.6304,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.802675585284281,
|
| 427 |
+
"grad_norm": 0.53122878074646,
|
| 428 |
+
"learning_rate": 0.00019759733036707453,
|
| 429 |
+
"loss": 4.8377,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.8160535117056856,
|
| 434 |
+
"grad_norm": 0.4925791919231415,
|
| 435 |
+
"learning_rate": 0.00019755283648498334,
|
| 436 |
+
"loss": 5.0919,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.8294314381270903,
|
| 441 |
+
"grad_norm": 0.4777262806892395,
|
| 442 |
+
"learning_rate": 0.0001975083426028921,
|
| 443 |
+
"loss": 4.8379,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.842809364548495,
|
| 448 |
+
"grad_norm": 0.49119675159454346,
|
| 449 |
+
"learning_rate": 0.0001974638487208009,
|
| 450 |
+
"loss": 5.0819,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.8561872909698997,
|
| 455 |
+
"grad_norm": 0.4732685089111328,
|
| 456 |
+
"learning_rate": 0.00019741935483870969,
|
| 457 |
+
"loss": 4.8948,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8695652173913043,
|
| 462 |
+
"grad_norm": 0.46269145607948303,
|
| 463 |
+
"learning_rate": 0.00019737486095661847,
|
| 464 |
+
"loss": 4.824,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.882943143812709,
|
| 469 |
+
"grad_norm": 0.49532708525657654,
|
| 470 |
+
"learning_rate": 0.00019733036707452725,
|
| 471 |
+
"loss": 4.8986,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.8963210702341137,
|
| 476 |
+
"grad_norm": 0.5253002643585205,
|
| 477 |
+
"learning_rate": 0.00019728587319243606,
|
| 478 |
+
"loss": 4.9073,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.9096989966555183,
|
| 483 |
+
"grad_norm": 0.5069419145584106,
|
| 484 |
+
"learning_rate": 0.00019724137931034484,
|
| 485 |
+
"loss": 4.8962,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.9230769230769231,
|
| 490 |
+
"grad_norm": 0.5038817524909973,
|
| 491 |
+
"learning_rate": 0.00019719688542825363,
|
| 492 |
+
"loss": 4.8711,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.9364548494983278,
|
| 497 |
+
"grad_norm": 0.4987100064754486,
|
| 498 |
+
"learning_rate": 0.0001971523915461624,
|
| 499 |
+
"loss": 4.8816,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.9498327759197325,
|
| 504 |
+
"grad_norm": 0.47370976209640503,
|
| 505 |
+
"learning_rate": 0.00019710789766407122,
|
| 506 |
+
"loss": 4.9675,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.9632107023411371,
|
| 511 |
+
"grad_norm": 0.5081727504730225,
|
| 512 |
+
"learning_rate": 0.00019706340378197997,
|
| 513 |
+
"loss": 4.2768,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9765886287625418,
|
| 518 |
+
"grad_norm": 0.45571258664131165,
|
| 519 |
+
"learning_rate": 0.00019701890989988878,
|
| 520 |
+
"loss": 4.6182,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.9899665551839465,
|
| 525 |
+
"grad_norm": 0.5216127634048462,
|
| 526 |
+
"learning_rate": 0.00019697441601779756,
|
| 527 |
+
"loss": 4.7126,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.0,
|
| 532 |
+
"grad_norm": 0.5393329858779907,
|
| 533 |
+
"learning_rate": 0.00019692992213570635,
|
| 534 |
+
"loss": 4.4919,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.0133779264214047,
|
| 539 |
+
"grad_norm": 0.4506986737251282,
|
| 540 |
+
"learning_rate": 0.00019688542825361513,
|
| 541 |
+
"loss": 4.5089,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.0267558528428093,
|
| 546 |
+
"grad_norm": 0.4328899085521698,
|
| 547 |
+
"learning_rate": 0.00019684093437152394,
|
| 548 |
+
"loss": 4.7518,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.040133779264214,
|
| 553 |
+
"grad_norm": 0.4397362470626831,
|
| 554 |
+
"learning_rate": 0.00019679644048943272,
|
| 555 |
+
"loss": 4.5069,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.0535117056856187,
|
| 560 |
+
"grad_norm": 0.4604664146900177,
|
| 561 |
+
"learning_rate": 0.0001967519466073415,
|
| 562 |
+
"loss": 4.7054,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.0668896321070234,
|
| 567 |
+
"grad_norm": 0.4398234784603119,
|
| 568 |
+
"learning_rate": 0.00019670745272525029,
|
| 569 |
+
"loss": 4.2743,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.080267558528428,
|
| 574 |
+
"grad_norm": 0.4570735692977905,
|
| 575 |
+
"learning_rate": 0.0001966629588431591,
|
| 576 |
+
"loss": 4.8012,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0936454849498327,
|
| 581 |
+
"grad_norm": 0.4814144968986511,
|
| 582 |
+
"learning_rate": 0.00019661846496106785,
|
| 583 |
+
"loss": 4.6449,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.1070234113712374,
|
| 588 |
+
"grad_norm": 0.4526231288909912,
|
| 589 |
+
"learning_rate": 0.00019657397107897666,
|
| 590 |
+
"loss": 4.5546,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.120401337792642,
|
| 595 |
+
"grad_norm": 0.4847906827926636,
|
| 596 |
+
"learning_rate": 0.00019652947719688544,
|
| 597 |
+
"loss": 4.4421,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.1337792642140467,
|
| 602 |
+
"grad_norm": 0.5136271715164185,
|
| 603 |
+
"learning_rate": 0.00019648498331479422,
|
| 604 |
+
"loss": 4.7136,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.1471571906354514,
|
| 609 |
+
"grad_norm": 0.49209895730018616,
|
| 610 |
+
"learning_rate": 0.000196440489432703,
|
| 611 |
+
"loss": 4.3145,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.160535117056856,
|
| 616 |
+
"grad_norm": 0.4972032904624939,
|
| 617 |
+
"learning_rate": 0.00019639599555061182,
|
| 618 |
+
"loss": 4.0408,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.1739130434782608,
|
| 623 |
+
"grad_norm": 0.5077862739562988,
|
| 624 |
+
"learning_rate": 0.0001963515016685206,
|
| 625 |
+
"loss": 4.4074,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.1872909698996654,
|
| 630 |
+
"grad_norm": 0.5293861031532288,
|
| 631 |
+
"learning_rate": 0.00019630700778642935,
|
| 632 |
+
"loss": 4.5385,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.2006688963210703,
|
| 637 |
+
"grad_norm": 0.5062645673751831,
|
| 638 |
+
"learning_rate": 0.00019626251390433816,
|
| 639 |
+
"loss": 4.5141,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.214046822742475,
|
| 644 |
+
"grad_norm": 0.49655866622924805,
|
| 645 |
+
"learning_rate": 0.00019621802002224695,
|
| 646 |
+
"loss": 4.4765,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.2274247491638797,
|
| 651 |
+
"grad_norm": 0.6059755086898804,
|
| 652 |
+
"learning_rate": 0.00019617352614015573,
|
| 653 |
+
"loss": 4.568,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.2408026755852843,
|
| 658 |
+
"grad_norm": 0.5442761778831482,
|
| 659 |
+
"learning_rate": 0.0001961290322580645,
|
| 660 |
+
"loss": 4.7724,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.254180602006689,
|
| 665 |
+
"grad_norm": 0.5426056385040283,
|
| 666 |
+
"learning_rate": 0.00019608453837597332,
|
| 667 |
+
"loss": 4.5308,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.2675585284280937,
|
| 672 |
+
"grad_norm": 0.525372326374054,
|
| 673 |
+
"learning_rate": 0.0001960400444938821,
|
| 674 |
+
"loss": 4.394,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.2809364548494984,
|
| 679 |
+
"grad_norm": 0.5407588481903076,
|
| 680 |
+
"learning_rate": 0.00019599555061179089,
|
| 681 |
+
"loss": 4.7347,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.294314381270903,
|
| 686 |
+
"grad_norm": 0.5726659893989563,
|
| 687 |
+
"learning_rate": 0.00019595105672969967,
|
| 688 |
+
"loss": 4.9446,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.3076923076923077,
|
| 693 |
+
"grad_norm": 0.6211283206939697,
|
| 694 |
+
"learning_rate": 0.00019590656284760848,
|
| 695 |
+
"loss": 4.697,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.3210702341137124,
|
| 700 |
+
"grad_norm": 0.5627567172050476,
|
| 701 |
+
"learning_rate": 0.00019586206896551723,
|
| 702 |
+
"loss": 4.4892,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.334448160535117,
|
| 707 |
+
"grad_norm": 0.6174790859222412,
|
| 708 |
+
"learning_rate": 0.00019581757508342604,
|
| 709 |
+
"loss": 4.5686,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.3478260869565217,
|
| 714 |
+
"grad_norm": 0.5586990118026733,
|
| 715 |
+
"learning_rate": 0.00019577308120133482,
|
| 716 |
+
"loss": 4.3916,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.3612040133779264,
|
| 721 |
+
"grad_norm": 0.5655365586280823,
|
| 722 |
+
"learning_rate": 0.0001957285873192436,
|
| 723 |
+
"loss": 4.1789,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.374581939799331,
|
| 728 |
+
"grad_norm": 0.5834594964981079,
|
| 729 |
+
"learning_rate": 0.0001956840934371524,
|
| 730 |
+
"loss": 4.3316,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.3879598662207357,
|
| 735 |
+
"grad_norm": 0.6065447926521301,
|
| 736 |
+
"learning_rate": 0.0001956395995550612,
|
| 737 |
+
"loss": 4.5167,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.4013377926421404,
|
| 742 |
+
"grad_norm": 0.5250216722488403,
|
| 743 |
+
"learning_rate": 0.00019559510567296998,
|
| 744 |
+
"loss": 4.1718,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.414715719063545,
|
| 749 |
+
"grad_norm": 0.5861116051673889,
|
| 750 |
+
"learning_rate": 0.00019555061179087876,
|
| 751 |
+
"loss": 4.3077,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.4280936454849498,
|
| 756 |
+
"grad_norm": 0.6138104796409607,
|
| 757 |
+
"learning_rate": 0.00019550611790878755,
|
| 758 |
+
"loss": 4.4748,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.4414715719063544,
|
| 763 |
+
"grad_norm": 0.6742071509361267,
|
| 764 |
+
"learning_rate": 0.00019546162402669636,
|
| 765 |
+
"loss": 4.8769,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.4548494983277591,
|
| 770 |
+
"grad_norm": 0.6634951233863831,
|
| 771 |
+
"learning_rate": 0.0001954171301446051,
|
| 772 |
+
"loss": 4.6423,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.468227424749164,
|
| 777 |
+
"grad_norm": 0.626646876335144,
|
| 778 |
+
"learning_rate": 0.00019537263626251392,
|
| 779 |
+
"loss": 4.4654,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.4816053511705687,
|
| 784 |
+
"grad_norm": 0.6306963562965393,
|
| 785 |
+
"learning_rate": 0.0001953281423804227,
|
| 786 |
+
"loss": 4.7021,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.4949832775919734,
|
| 791 |
+
"grad_norm": 0.620370626449585,
|
| 792 |
+
"learning_rate": 0.00019528364849833149,
|
| 793 |
+
"loss": 4.587,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.508361204013378,
|
| 798 |
+
"grad_norm": 0.6410287618637085,
|
| 799 |
+
"learning_rate": 0.00019523915461624027,
|
| 800 |
+
"loss": 4.8089,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.5217391304347827,
|
| 805 |
+
"grad_norm": 0.676434338092804,
|
| 806 |
+
"learning_rate": 0.00019519466073414908,
|
| 807 |
+
"loss": 4.668,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.5351170568561874,
|
| 812 |
+
"grad_norm": 0.5756319761276245,
|
| 813 |
+
"learning_rate": 0.00019515016685205786,
|
| 814 |
+
"loss": 4.3223,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.548494983277592,
|
| 819 |
+
"grad_norm": 0.5850693583488464,
|
| 820 |
+
"learning_rate": 0.00019510567296996664,
|
| 821 |
+
"loss": 4.2343,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.5618729096989967,
|
| 826 |
+
"grad_norm": 0.6172360777854919,
|
| 827 |
+
"learning_rate": 0.00019506117908787542,
|
| 828 |
+
"loss": 4.6102,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.5752508361204014,
|
| 833 |
+
"grad_norm": 0.5887568593025208,
|
| 834 |
+
"learning_rate": 0.00019501668520578423,
|
| 835 |
+
"loss": 4.8097,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.588628762541806,
|
| 840 |
+
"grad_norm": 0.5763369798660278,
|
| 841 |
+
"learning_rate": 0.000194972191323693,
|
| 842 |
+
"loss": 4.2001,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.6020066889632107,
|
| 847 |
+
"grad_norm": 0.6158986687660217,
|
| 848 |
+
"learning_rate": 0.0001949276974416018,
|
| 849 |
+
"loss": 4.7075,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.6153846153846154,
|
| 854 |
+
"grad_norm": 0.5540957450866699,
|
| 855 |
+
"learning_rate": 0.00019488320355951058,
|
| 856 |
+
"loss": 4.452,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.62876254180602,
|
| 861 |
+
"grad_norm": 0.6193795204162598,
|
| 862 |
+
"learning_rate": 0.00019483870967741936,
|
| 863 |
+
"loss": 4.4583,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.6421404682274248,
|
| 868 |
+
"grad_norm": 0.6699966788291931,
|
| 869 |
+
"learning_rate": 0.00019479421579532815,
|
| 870 |
+
"loss": 4.3728,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.6555183946488294,
|
| 875 |
+
"grad_norm": 0.5904677510261536,
|
| 876 |
+
"learning_rate": 0.00019474972191323696,
|
| 877 |
+
"loss": 4.5452,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.6688963210702341,
|
| 882 |
+
"grad_norm": 0.6137760281562805,
|
| 883 |
+
"learning_rate": 0.00019470522803114574,
|
| 884 |
+
"loss": 4.2853,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.6822742474916388,
|
| 889 |
+
"grad_norm": 0.6396192908287048,
|
| 890 |
+
"learning_rate": 0.00019466073414905452,
|
| 891 |
+
"loss": 4.4258,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.6956521739130435,
|
| 896 |
+
"grad_norm": 0.6190487742424011,
|
| 897 |
+
"learning_rate": 0.0001946162402669633,
|
| 898 |
+
"loss": 4.9866,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.7090301003344481,
|
| 903 |
+
"grad_norm": 0.6971675157546997,
|
| 904 |
+
"learning_rate": 0.0001945717463848721,
|
| 905 |
+
"loss": 4.2126,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.7224080267558528,
|
| 910 |
+
"grad_norm": 0.6245931386947632,
|
| 911 |
+
"learning_rate": 0.00019452725250278087,
|
| 912 |
+
"loss": 4.8477,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.7357859531772575,
|
| 917 |
+
"grad_norm": 0.5675052404403687,
|
| 918 |
+
"learning_rate": 0.00019448275862068965,
|
| 919 |
+
"loss": 4.4097,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.7491638795986622,
|
| 924 |
+
"grad_norm": 0.6594040393829346,
|
| 925 |
+
"learning_rate": 0.00019443826473859846,
|
| 926 |
+
"loss": 4.3747,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.7625418060200668,
|
| 931 |
+
"grad_norm": 0.6377655267715454,
|
| 932 |
+
"learning_rate": 0.00019439377085650724,
|
| 933 |
+
"loss": 4.2733,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.7759197324414715,
|
| 938 |
+
"grad_norm": 0.6167862415313721,
|
| 939 |
+
"learning_rate": 0.00019434927697441602,
|
| 940 |
+
"loss": 4.5694,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.7892976588628762,
|
| 945 |
+
"grad_norm": 0.577671468257904,
|
| 946 |
+
"learning_rate": 0.0001943047830923248,
|
| 947 |
+
"loss": 4.5006,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.8026755852842808,
|
| 952 |
+
"grad_norm": 0.6361016035079956,
|
| 953 |
+
"learning_rate": 0.00019426028921023362,
|
| 954 |
+
"loss": 4.9907,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.8160535117056855,
|
| 959 |
+
"grad_norm": 0.6445321440696716,
|
| 960 |
+
"learning_rate": 0.00019421579532814237,
|
| 961 |
+
"loss": 4.779,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.8294314381270902,
|
| 966 |
+
"grad_norm": 0.5955402851104736,
|
| 967 |
+
"learning_rate": 0.00019417130144605118,
|
| 968 |
+
"loss": 4.6026,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.8428093645484949,
|
| 973 |
+
"grad_norm": 0.6807080507278442,
|
| 974 |
+
"learning_rate": 0.00019412680756395996,
|
| 975 |
+
"loss": 4.7124,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.8561872909698995,
|
| 980 |
+
"grad_norm": 0.5799288153648376,
|
| 981 |
+
"learning_rate": 0.00019408231368186875,
|
| 982 |
+
"loss": 4.0701,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.8695652173913042,
|
| 987 |
+
"grad_norm": 0.6187757253646851,
|
| 988 |
+
"learning_rate": 0.00019403781979977753,
|
| 989 |
+
"loss": 4.705,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.8829431438127089,
|
| 994 |
+
"grad_norm": 0.6614826917648315,
|
| 995 |
+
"learning_rate": 0.00019399332591768634,
|
| 996 |
+
"loss": 4.8146,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.8963210702341136,
|
| 1001 |
+
"grad_norm": 0.6204859614372253,
|
| 1002 |
+
"learning_rate": 0.00019394883203559512,
|
| 1003 |
+
"loss": 4.3041,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.9096989966555182,
|
| 1008 |
+
"grad_norm": 0.6527450680732727,
|
| 1009 |
+
"learning_rate": 0.0001939043381535039,
|
| 1010 |
+
"loss": 4.4493,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.9230769230769231,
|
| 1015 |
+
"grad_norm": 0.6470615267753601,
|
| 1016 |
+
"learning_rate": 0.00019385984427141268,
|
| 1017 |
+
"loss": 4.7771,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.9364548494983278,
|
| 1022 |
+
"grad_norm": 0.5642555952072144,
|
| 1023 |
+
"learning_rate": 0.0001938153503893215,
|
| 1024 |
+
"loss": 4.3344,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.9498327759197325,
|
| 1029 |
+
"grad_norm": 0.6206467151641846,
|
| 1030 |
+
"learning_rate": 0.00019377085650723025,
|
| 1031 |
+
"loss": 4.2191,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.9632107023411371,
|
| 1036 |
+
"grad_norm": 0.6079016923904419,
|
| 1037 |
+
"learning_rate": 0.00019372636262513906,
|
| 1038 |
+
"loss": 4.7397,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.9765886287625418,
|
| 1043 |
+
"grad_norm": 0.6197662353515625,
|
| 1044 |
+
"learning_rate": 0.00019368186874304784,
|
| 1045 |
+
"loss": 4.5342,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.9899665551839465,
|
| 1050 |
+
"grad_norm": 0.6556297540664673,
|
| 1051 |
+
"learning_rate": 0.00019363737486095662,
|
| 1052 |
+
"loss": 4.6709,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.0,
|
| 1057 |
+
"grad_norm": 0.7837930917739868,
|
| 1058 |
+
"learning_rate": 0.0001935928809788654,
|
| 1059 |
+
"loss": 4.6215,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.0133779264214047,
|
| 1064 |
+
"grad_norm": 0.5267267227172852,
|
| 1065 |
+
"learning_rate": 0.00019354838709677422,
|
| 1066 |
+
"loss": 4.2695,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.0267558528428093,
|
| 1071 |
+
"grad_norm": 0.5862157344818115,
|
| 1072 |
+
"learning_rate": 0.000193503893214683,
|
| 1073 |
+
"loss": 4.3702,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.040133779264214,
|
| 1078 |
+
"grad_norm": 0.538254976272583,
|
| 1079 |
+
"learning_rate": 0.00019345939933259178,
|
| 1080 |
+
"loss": 4.3953,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.0535117056856187,
|
| 1085 |
+
"grad_norm": 0.5977053642272949,
|
| 1086 |
+
"learning_rate": 0.00019341490545050056,
|
| 1087 |
+
"loss": 4.2156,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.0668896321070234,
|
| 1092 |
+
"grad_norm": 0.606006383895874,
|
| 1093 |
+
"learning_rate": 0.00019337041156840937,
|
| 1094 |
+
"loss": 4.2802,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.080267558528428,
|
| 1099 |
+
"grad_norm": 0.6071277856826782,
|
| 1100 |
+
"learning_rate": 0.00019332591768631813,
|
| 1101 |
+
"loss": 4.5545,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.0936454849498327,
|
| 1106 |
+
"grad_norm": 0.6281546354293823,
|
| 1107 |
+
"learning_rate": 0.00019328142380422694,
|
| 1108 |
+
"loss": 4.6105,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.1070234113712374,
|
| 1113 |
+
"grad_norm": 0.5703116655349731,
|
| 1114 |
+
"learning_rate": 0.00019323692992213572,
|
| 1115 |
+
"loss": 4.2751,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.120401337792642,
|
| 1120 |
+
"grad_norm": 0.6587452292442322,
|
| 1121 |
+
"learning_rate": 0.0001931924360400445,
|
| 1122 |
+
"loss": 4.6342,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.1337792642140467,
|
| 1127 |
+
"grad_norm": 0.6141905784606934,
|
| 1128 |
+
"learning_rate": 0.00019314794215795328,
|
| 1129 |
+
"loss": 4.4345,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.1471571906354514,
|
| 1134 |
+
"grad_norm": 0.6741939187049866,
|
| 1135 |
+
"learning_rate": 0.0001931034482758621,
|
| 1136 |
+
"loss": 4.0257,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.160535117056856,
|
| 1141 |
+
"grad_norm": 0.6468759179115295,
|
| 1142 |
+
"learning_rate": 0.00019305895439377088,
|
| 1143 |
+
"loss": 4.2313,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.1739130434782608,
|
| 1148 |
+
"grad_norm": 0.6703383326530457,
|
| 1149 |
+
"learning_rate": 0.00019301446051167966,
|
| 1150 |
+
"loss": 4.2164,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.1872909698996654,
|
| 1155 |
+
"grad_norm": 0.710967481136322,
|
| 1156 |
+
"learning_rate": 0.00019296996662958844,
|
| 1157 |
+
"loss": 4.3398,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.20066889632107,
|
| 1162 |
+
"grad_norm": 0.6862124800682068,
|
| 1163 |
+
"learning_rate": 0.00019292547274749725,
|
| 1164 |
+
"loss": 4.3379,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.2140468227424748,
|
| 1169 |
+
"grad_norm": 0.6288430690765381,
|
| 1170 |
+
"learning_rate": 0.000192880978865406,
|
| 1171 |
+
"loss": 4.3487,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.2274247491638794,
|
| 1176 |
+
"grad_norm": 0.6358796954154968,
|
| 1177 |
+
"learning_rate": 0.00019283648498331481,
|
| 1178 |
+
"loss": 4.1656,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.240802675585284,
|
| 1183 |
+
"grad_norm": 0.6818917393684387,
|
| 1184 |
+
"learning_rate": 0.0001927919911012236,
|
| 1185 |
+
"loss": 4.5363,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.254180602006689,
|
| 1190 |
+
"grad_norm": 0.6996105313301086,
|
| 1191 |
+
"learning_rate": 0.00019274749721913238,
|
| 1192 |
+
"loss": 4.3208,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.2675585284280935,
|
| 1197 |
+
"grad_norm": 0.6730326414108276,
|
| 1198 |
+
"learning_rate": 0.00019270300333704116,
|
| 1199 |
+
"loss": 4.1401,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.280936454849498,
|
| 1204 |
+
"grad_norm": 0.7022603750228882,
|
| 1205 |
+
"learning_rate": 0.00019265850945494994,
|
| 1206 |
+
"loss": 4.5761,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.294314381270903,
|
| 1211 |
+
"grad_norm": 0.6525995135307312,
|
| 1212 |
+
"learning_rate": 0.00019261401557285875,
|
| 1213 |
+
"loss": 4.4017,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.3076923076923075,
|
| 1218 |
+
"grad_norm": 0.7066033482551575,
|
| 1219 |
+
"learning_rate": 0.0001925695216907675,
|
| 1220 |
+
"loss": 4.0037,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.321070234113712,
|
| 1225 |
+
"grad_norm": 0.6708059310913086,
|
| 1226 |
+
"learning_rate": 0.00019252502780867632,
|
| 1227 |
+
"loss": 4.1947,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.334448160535117,
|
| 1232 |
+
"grad_norm": 0.8711172342300415,
|
| 1233 |
+
"learning_rate": 0.0001924805339265851,
|
| 1234 |
+
"loss": 3.9958,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.3478260869565215,
|
| 1239 |
+
"grad_norm": 0.7258634567260742,
|
| 1240 |
+
"learning_rate": 0.00019243604004449388,
|
| 1241 |
+
"loss": 4.4682,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.361204013377926,
|
| 1246 |
+
"grad_norm": 0.7693021893501282,
|
| 1247 |
+
"learning_rate": 0.00019239154616240267,
|
| 1248 |
+
"loss": 4.54,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.374581939799331,
|
| 1253 |
+
"grad_norm": 0.7271276116371155,
|
| 1254 |
+
"learning_rate": 0.00019234705228031148,
|
| 1255 |
+
"loss": 4.2942,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.387959866220736,
|
| 1260 |
+
"grad_norm": 0.6836609244346619,
|
| 1261 |
+
"learning_rate": 0.00019230255839822026,
|
| 1262 |
+
"loss": 4.3099,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.4013377926421406,
|
| 1267 |
+
"grad_norm": 0.731164813041687,
|
| 1268 |
+
"learning_rate": 0.00019225806451612904,
|
| 1269 |
+
"loss": 4.4077,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.4147157190635453,
|
| 1274 |
+
"grad_norm": 0.7575274109840393,
|
| 1275 |
+
"learning_rate": 0.00019221357063403782,
|
| 1276 |
+
"loss": 4.6572,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.42809364548495,
|
| 1281 |
+
"grad_norm": 0.8461325168609619,
|
| 1282 |
+
"learning_rate": 0.00019216907675194663,
|
| 1283 |
+
"loss": 4.4922,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.4414715719063547,
|
| 1288 |
+
"grad_norm": 0.7225251197814941,
|
| 1289 |
+
"learning_rate": 0.0001921245828698554,
|
| 1290 |
+
"loss": 4.0372,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.4548494983277593,
|
| 1295 |
+
"grad_norm": 3.563720703125,
|
| 1296 |
+
"learning_rate": 0.0001920800889877642,
|
| 1297 |
+
"loss": 4.5412,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.468227424749164,
|
| 1302 |
+
"grad_norm": 0.8452121019363403,
|
| 1303 |
+
"learning_rate": 0.00019203559510567298,
|
| 1304 |
+
"loss": 4.4961,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.4816053511705687,
|
| 1309 |
+
"grad_norm": 0.8734024167060852,
|
| 1310 |
+
"learning_rate": 0.00019199110122358176,
|
| 1311 |
+
"loss": 4.0884,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.4949832775919734,
|
| 1316 |
+
"grad_norm": 1.1765823364257812,
|
| 1317 |
+
"learning_rate": 0.00019194660734149054,
|
| 1318 |
+
"loss": 4.2228,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.508361204013378,
|
| 1323 |
+
"grad_norm": 0.750206708908081,
|
| 1324 |
+
"learning_rate": 0.00019190211345939935,
|
| 1325 |
+
"loss": 4.4305,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.5217391304347827,
|
| 1330 |
+
"grad_norm": 0.7574430704116821,
|
| 1331 |
+
"learning_rate": 0.00019185761957730814,
|
| 1332 |
+
"loss": 4.1511,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.5351170568561874,
|
| 1337 |
+
"grad_norm": 0.7105517387390137,
|
| 1338 |
+
"learning_rate": 0.00019181312569521692,
|
| 1339 |
+
"loss": 4.4793,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.548494983277592,
|
| 1344 |
+
"grad_norm": 0.7495557069778442,
|
| 1345 |
+
"learning_rate": 0.0001917686318131257,
|
| 1346 |
+
"loss": 4.1335,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.5618729096989967,
|
| 1351 |
+
"grad_norm": 0.8001168966293335,
|
| 1352 |
+
"learning_rate": 0.0001917241379310345,
|
| 1353 |
+
"loss": 4.7898,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.5752508361204014,
|
| 1358 |
+
"grad_norm": 0.7402104735374451,
|
| 1359 |
+
"learning_rate": 0.00019167964404894327,
|
| 1360 |
+
"loss": 4.4482,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.588628762541806,
|
| 1365 |
+
"grad_norm": 0.748267650604248,
|
| 1366 |
+
"learning_rate": 0.00019163515016685207,
|
| 1367 |
+
"loss": 4.3167,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.6020066889632107,
|
| 1372 |
+
"grad_norm": 0.8291250467300415,
|
| 1373 |
+
"learning_rate": 0.00019159065628476086,
|
| 1374 |
+
"loss": 4.058,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.6153846153846154,
|
| 1379 |
+
"grad_norm": 0.6945542693138123,
|
| 1380 |
+
"learning_rate": 0.00019154616240266964,
|
| 1381 |
+
"loss": 3.9751,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.62876254180602,
|
| 1386 |
+
"grad_norm": 0.7307319045066833,
|
| 1387 |
+
"learning_rate": 0.00019150166852057842,
|
| 1388 |
+
"loss": 4.2736,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.6421404682274248,
|
| 1393 |
+
"grad_norm": 0.7489168047904968,
|
| 1394 |
+
"learning_rate": 0.00019145717463848723,
|
| 1395 |
+
"loss": 4.3075,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.6555183946488294,
|
| 1400 |
+
"grad_norm": 0.9727582931518555,
|
| 1401 |
+
"learning_rate": 0.00019141268075639601,
|
| 1402 |
+
"loss": 4.6474,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.668896321070234,
|
| 1407 |
+
"grad_norm": 0.6776256561279297,
|
| 1408 |
+
"learning_rate": 0.0001913681868743048,
|
| 1409 |
+
"loss": 4.4217,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.682274247491639,
|
| 1414 |
+
"grad_norm": 0.7305111885070801,
|
| 1415 |
+
"learning_rate": 0.00019132369299221358,
|
| 1416 |
+
"loss": 4.2804,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.6956521739130435,
|
| 1421 |
+
"grad_norm": 0.7196978330612183,
|
| 1422 |
+
"learning_rate": 0.0001912791991101224,
|
| 1423 |
+
"loss": 4.3941,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.709030100334448,
|
| 1428 |
+
"grad_norm": 0.7988458871841431,
|
| 1429 |
+
"learning_rate": 0.00019123470522803114,
|
| 1430 |
+
"loss": 4.437,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.722408026755853,
|
| 1435 |
+
"grad_norm": 0.7004797458648682,
|
| 1436 |
+
"learning_rate": 0.00019119021134593995,
|
| 1437 |
+
"loss": 4.4986,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.7357859531772575,
|
| 1442 |
+
"grad_norm": 0.677796483039856,
|
| 1443 |
+
"learning_rate": 0.00019114571746384874,
|
| 1444 |
+
"loss": 4.0851,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.749163879598662,
|
| 1449 |
+
"grad_norm": 0.7527475357055664,
|
| 1450 |
+
"learning_rate": 0.00019110122358175752,
|
| 1451 |
+
"loss": 4.4469,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.762541806020067,
|
| 1456 |
+
"grad_norm": 1.1659115552902222,
|
| 1457 |
+
"learning_rate": 0.0001910567296996663,
|
| 1458 |
+
"loss": 4.3284,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.7759197324414715,
|
| 1463 |
+
"grad_norm": 0.7238364815711975,
|
| 1464 |
+
"learning_rate": 0.0001910122358175751,
|
| 1465 |
+
"loss": 4.2605,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.789297658862876,
|
| 1470 |
+
"grad_norm": 0.7537760734558105,
|
| 1471 |
+
"learning_rate": 0.0001909677419354839,
|
| 1472 |
+
"loss": 4.3775,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.802675585284281,
|
| 1477 |
+
"grad_norm": 0.6874127388000488,
|
| 1478 |
+
"learning_rate": 0.00019092324805339267,
|
| 1479 |
+
"loss": 4.3404,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.8160535117056855,
|
| 1484 |
+
"grad_norm": 0.7045959830284119,
|
| 1485 |
+
"learning_rate": 0.00019087875417130146,
|
| 1486 |
+
"loss": 4.1568,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.82943143812709,
|
| 1491 |
+
"grad_norm": 0.7249194383621216,
|
| 1492 |
+
"learning_rate": 0.00019083426028921027,
|
| 1493 |
+
"loss": 4.1969,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.842809364548495,
|
| 1498 |
+
"grad_norm": 0.8331268429756165,
|
| 1499 |
+
"learning_rate": 0.00019078976640711902,
|
| 1500 |
+
"loss": 4.3169,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.8561872909698995,
|
| 1505 |
+
"grad_norm": 0.7171936631202698,
|
| 1506 |
+
"learning_rate": 0.0001907452725250278,
|
| 1507 |
+
"loss": 4.5123,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.869565217391304,
|
| 1512 |
+
"grad_norm": 0.759919285774231,
|
| 1513 |
+
"learning_rate": 0.0001907007786429366,
|
| 1514 |
+
"loss": 4.5412,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.882943143812709,
|
| 1519 |
+
"grad_norm": 0.7451274991035461,
|
| 1520 |
+
"learning_rate": 0.0001906562847608454,
|
| 1521 |
+
"loss": 4.5253,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.8963210702341136,
|
| 1526 |
+
"grad_norm": 0.6564481258392334,
|
| 1527 |
+
"learning_rate": 0.00019061179087875418,
|
| 1528 |
+
"loss": 4.1092,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.9096989966555182,
|
| 1533 |
+
"grad_norm": 0.7339865565299988,
|
| 1534 |
+
"learning_rate": 0.00019056729699666296,
|
| 1535 |
+
"loss": 4.5092,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.9230769230769234,
|
| 1540 |
+
"grad_norm": 0.7113937735557556,
|
| 1541 |
+
"learning_rate": 0.00019052280311457177,
|
| 1542 |
+
"loss": 4.3355,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.936454849498328,
|
| 1547 |
+
"grad_norm": 0.7306456565856934,
|
| 1548 |
+
"learning_rate": 0.00019047830923248053,
|
| 1549 |
+
"loss": 4.5745,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.9498327759197327,
|
| 1554 |
+
"grad_norm": 0.7971818447113037,
|
| 1555 |
+
"learning_rate": 0.00019043381535038933,
|
| 1556 |
+
"loss": 4.2903,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.9632107023411374,
|
| 1561 |
+
"grad_norm": 0.7757331728935242,
|
| 1562 |
+
"learning_rate": 0.00019038932146829812,
|
| 1563 |
+
"loss": 4.2832,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.976588628762542,
|
| 1568 |
+
"grad_norm": 0.7326288223266602,
|
| 1569 |
+
"learning_rate": 0.0001903448275862069,
|
| 1570 |
+
"loss": 4.2444,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.9899665551839467,
|
| 1575 |
+
"grad_norm": 0.7363834381103516,
|
| 1576 |
+
"learning_rate": 0.00019030033370411568,
|
| 1577 |
+
"loss": 4.6744,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 3.0,
|
| 1582 |
+
"grad_norm": 0.8835271596908569,
|
| 1583 |
+
"learning_rate": 0.0001902558398220245,
|
| 1584 |
+
"loss": 4.432,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 3.0133779264214047,
|
| 1589 |
+
"grad_norm": 0.6591921448707581,
|
| 1590 |
+
"learning_rate": 0.00019021134593993327,
|
| 1591 |
+
"loss": 4.1353,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 3.0267558528428093,
|
| 1596 |
+
"grad_norm": 0.6895263195037842,
|
| 1597 |
+
"learning_rate": 0.00019016685205784206,
|
| 1598 |
+
"loss": 4.1253,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 3.040133779264214,
|
| 1603 |
+
"grad_norm": 0.6476898789405823,
|
| 1604 |
+
"learning_rate": 0.00019012235817575084,
|
| 1605 |
+
"loss": 4.0354,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 3.0535117056856187,
|
| 1610 |
+
"grad_norm": 0.6398957967758179,
|
| 1611 |
+
"learning_rate": 0.00019007786429365965,
|
| 1612 |
+
"loss": 4.024,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 3.0668896321070234,
|
| 1617 |
+
"grad_norm": 0.7483389973640442,
|
| 1618 |
+
"learning_rate": 0.0001900333704115684,
|
| 1619 |
+
"loss": 4.1405,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 3.080267558528428,
|
| 1624 |
+
"grad_norm": 0.7003724575042725,
|
| 1625 |
+
"learning_rate": 0.0001899888765294772,
|
| 1626 |
+
"loss": 4.3593,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 3.0936454849498327,
|
| 1631 |
+
"grad_norm": 0.7426732182502747,
|
| 1632 |
+
"learning_rate": 0.000189944382647386,
|
| 1633 |
+
"loss": 4.485,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 3.1070234113712374,
|
| 1638 |
+
"grad_norm": 0.6957541108131409,
|
| 1639 |
+
"learning_rate": 0.00018989988876529478,
|
| 1640 |
+
"loss": 4.1017,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 3.120401337792642,
|
| 1645 |
+
"grad_norm": 0.8613067865371704,
|
| 1646 |
+
"learning_rate": 0.00018985539488320356,
|
| 1647 |
+
"loss": 4.3038,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 3.1337792642140467,
|
| 1652 |
+
"grad_norm": 0.8375754952430725,
|
| 1653 |
+
"learning_rate": 0.00018981090100111237,
|
| 1654 |
+
"loss": 4.4356,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 3.1471571906354514,
|
| 1659 |
+
"grad_norm": 0.7878522872924805,
|
| 1660 |
+
"learning_rate": 0.00018976640711902115,
|
| 1661 |
+
"loss": 3.9916,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 3.160535117056856,
|
| 1666 |
+
"grad_norm": 0.7463901042938232,
|
| 1667 |
+
"learning_rate": 0.00018972191323692993,
|
| 1668 |
+
"loss": 3.6761,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 3.1739130434782608,
|
| 1673 |
+
"grad_norm": 0.7360939979553223,
|
| 1674 |
+
"learning_rate": 0.00018967741935483872,
|
| 1675 |
+
"loss": 3.9573,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 3.1872909698996654,
|
| 1680 |
+
"grad_norm": 0.891861081123352,
|
| 1681 |
+
"learning_rate": 0.00018963292547274753,
|
| 1682 |
+
"loss": 4.1853,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 3.20066889632107,
|
| 1687 |
+
"grad_norm": 0.8589549660682678,
|
| 1688 |
+
"learning_rate": 0.00018958843159065628,
|
| 1689 |
+
"loss": 4.0679,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 3.2140468227424748,
|
| 1694 |
+
"grad_norm": 0.9534163475036621,
|
| 1695 |
+
"learning_rate": 0.0001895439377085651,
|
| 1696 |
+
"loss": 3.732,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 3.2274247491638794,
|
| 1701 |
+
"grad_norm": 0.8968185186386108,
|
| 1702 |
+
"learning_rate": 0.00018949944382647387,
|
| 1703 |
+
"loss": 4.2217,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 3.240802675585284,
|
| 1708 |
+
"grad_norm": 0.81589275598526,
|
| 1709 |
+
"learning_rate": 0.00018945494994438266,
|
| 1710 |
+
"loss": 4.428,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 3.254180602006689,
|
| 1715 |
+
"grad_norm": 0.929050862789154,
|
| 1716 |
+
"learning_rate": 0.00018941045606229144,
|
| 1717 |
+
"loss": 4.3468,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 3.2675585284280935,
|
| 1722 |
+
"grad_norm": 0.8535035252571106,
|
| 1723 |
+
"learning_rate": 0.00018936596218020025,
|
| 1724 |
+
"loss": 3.8489,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 3.280936454849498,
|
| 1729 |
+
"grad_norm": 0.9484681487083435,
|
| 1730 |
+
"learning_rate": 0.00018932146829810903,
|
| 1731 |
+
"loss": 4.0132,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 3.294314381270903,
|
| 1736 |
+
"grad_norm": 0.8190047144889832,
|
| 1737 |
+
"learning_rate": 0.0001892769744160178,
|
| 1738 |
+
"loss": 4.3574,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 3.3076923076923075,
|
| 1743 |
+
"grad_norm": 0.8764749765396118,
|
| 1744 |
+
"learning_rate": 0.0001892324805339266,
|
| 1745 |
+
"loss": 4.3103,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 3.321070234113712,
|
| 1750 |
+
"grad_norm": 0.8929185271263123,
|
| 1751 |
+
"learning_rate": 0.0001891879866518354,
|
| 1752 |
+
"loss": 4.3606,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 3.334448160535117,
|
| 1757 |
+
"grad_norm": 0.9096692204475403,
|
| 1758 |
+
"learning_rate": 0.00018914349276974416,
|
| 1759 |
+
"loss": 4.0047,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 3.3478260869565215,
|
| 1764 |
+
"grad_norm": 0.885143518447876,
|
| 1765 |
+
"learning_rate": 0.00018909899888765297,
|
| 1766 |
+
"loss": 4.182,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 3.361204013377926,
|
| 1771 |
+
"grad_norm": 0.7724215984344482,
|
| 1772 |
+
"learning_rate": 0.00018905450500556175,
|
| 1773 |
+
"loss": 3.9529,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 3.374581939799331,
|
| 1778 |
+
"grad_norm": 0.8351865410804749,
|
| 1779 |
+
"learning_rate": 0.00018901001112347053,
|
| 1780 |
+
"loss": 3.9533,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 3.387959866220736,
|
| 1785 |
+
"grad_norm": 0.8684999942779541,
|
| 1786 |
+
"learning_rate": 0.00018896551724137932,
|
| 1787 |
+
"loss": 3.8594,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 3.4013377926421406,
|
| 1792 |
+
"grad_norm": 0.8903334736824036,
|
| 1793 |
+
"learning_rate": 0.0001889210233592881,
|
| 1794 |
+
"loss": 3.9248,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 3.4147157190635453,
|
| 1799 |
+
"grad_norm": 0.826690137386322,
|
| 1800 |
+
"learning_rate": 0.0001888765294771969,
|
| 1801 |
+
"loss": 4.0389,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 3.42809364548495,
|
| 1806 |
+
"grad_norm": 0.8306142687797546,
|
| 1807 |
+
"learning_rate": 0.00018883203559510566,
|
| 1808 |
+
"loss": 3.8168,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 3.4414715719063547,
|
| 1813 |
+
"grad_norm": 0.9032199382781982,
|
| 1814 |
+
"learning_rate": 0.00018878754171301447,
|
| 1815 |
+
"loss": 4.178,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 3.4548494983277593,
|
| 1820 |
+
"grad_norm": 0.9081966280937195,
|
| 1821 |
+
"learning_rate": 0.00018874304783092326,
|
| 1822 |
+
"loss": 4.2583,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 3.468227424749164,
|
| 1827 |
+
"grad_norm": 0.8424077033996582,
|
| 1828 |
+
"learning_rate": 0.00018869855394883204,
|
| 1829 |
+
"loss": 4.3285,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 3.4816053511705687,
|
| 1834 |
+
"grad_norm": 0.8302170038223267,
|
| 1835 |
+
"learning_rate": 0.00018865406006674082,
|
| 1836 |
+
"loss": 4.1346,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 3.4949832775919734,
|
| 1841 |
+
"grad_norm": 0.8747193217277527,
|
| 1842 |
+
"learning_rate": 0.00018860956618464963,
|
| 1843 |
+
"loss": 4.0747,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 3.508361204013378,
|
| 1848 |
+
"grad_norm": 0.8613927364349365,
|
| 1849 |
+
"learning_rate": 0.0001885650723025584,
|
| 1850 |
+
"loss": 4.2346,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 3.5217391304347827,
|
| 1855 |
+
"grad_norm": 0.8321558833122253,
|
| 1856 |
+
"learning_rate": 0.0001885205784204672,
|
| 1857 |
+
"loss": 3.9781,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 3.5351170568561874,
|
| 1862 |
+
"grad_norm": 0.8961741328239441,
|
| 1863 |
+
"learning_rate": 0.00018847608453837598,
|
| 1864 |
+
"loss": 4.311,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.548494983277592,
|
| 1869 |
+
"grad_norm": 0.7703898549079895,
|
| 1870 |
+
"learning_rate": 0.00018843159065628479,
|
| 1871 |
+
"loss": 4.1163,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 3.5618729096989967,
|
| 1876 |
+
"grad_norm": 0.880051851272583,
|
| 1877 |
+
"learning_rate": 0.00018838709677419354,
|
| 1878 |
+
"loss": 3.8032,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 3.5752508361204014,
|
| 1883 |
+
"grad_norm": 0.8287038207054138,
|
| 1884 |
+
"learning_rate": 0.00018834260289210235,
|
| 1885 |
+
"loss": 4.1627,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 3.588628762541806,
|
| 1890 |
+
"grad_norm": 0.9726569652557373,
|
| 1891 |
+
"learning_rate": 0.00018829810901001113,
|
| 1892 |
+
"loss": 4.4055,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 3.6020066889632107,
|
| 1897 |
+
"grad_norm": 0.8071132898330688,
|
| 1898 |
+
"learning_rate": 0.00018825361512791992,
|
| 1899 |
+
"loss": 4.1709,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 3.6153846153846154,
|
| 1904 |
+
"grad_norm": 0.8310988545417786,
|
| 1905 |
+
"learning_rate": 0.0001882091212458287,
|
| 1906 |
+
"loss": 4.2359,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 3.62876254180602,
|
| 1911 |
+
"grad_norm": 0.8713561296463013,
|
| 1912 |
+
"learning_rate": 0.0001881646273637375,
|
| 1913 |
+
"loss": 4.1247,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 3.6421404682274248,
|
| 1918 |
+
"grad_norm": 0.8964342474937439,
|
| 1919 |
+
"learning_rate": 0.0001881201334816463,
|
| 1920 |
+
"loss": 4.0794,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 3.6555183946488294,
|
| 1925 |
+
"grad_norm": 0.9901681542396545,
|
| 1926 |
+
"learning_rate": 0.00018807563959955507,
|
| 1927 |
+
"loss": 4.0217,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 3.668896321070234,
|
| 1932 |
+
"grad_norm": 0.9279042482376099,
|
| 1933 |
+
"learning_rate": 0.00018803114571746385,
|
| 1934 |
+
"loss": 4.3244,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 3.682274247491639,
|
| 1939 |
+
"grad_norm": 0.8105964660644531,
|
| 1940 |
+
"learning_rate": 0.00018798665183537266,
|
| 1941 |
+
"loss": 3.9041,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 3.6956521739130435,
|
| 1946 |
+
"grad_norm": 0.8511622548103333,
|
| 1947 |
+
"learning_rate": 0.00018794215795328142,
|
| 1948 |
+
"loss": 3.8969,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 3.709030100334448,
|
| 1953 |
+
"grad_norm": 0.9072037935256958,
|
| 1954 |
+
"learning_rate": 0.00018789766407119023,
|
| 1955 |
+
"loss": 4.2185,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 3.722408026755853,
|
| 1960 |
+
"grad_norm": 0.9792962670326233,
|
| 1961 |
+
"learning_rate": 0.000187853170189099,
|
| 1962 |
+
"loss": 4.1915,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 3.7357859531772575,
|
| 1967 |
+
"grad_norm": 0.8579828143119812,
|
| 1968 |
+
"learning_rate": 0.0001878086763070078,
|
| 1969 |
+
"loss": 3.8903,
|
| 1970 |
+
"step": 280
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 3.749163879598662,
|
| 1974 |
+
"grad_norm": 0.9866719841957092,
|
| 1975 |
+
"learning_rate": 0.00018776418242491658,
|
| 1976 |
+
"loss": 4.2022,
|
| 1977 |
+
"step": 281
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 3.762541806020067,
|
| 1981 |
+
"grad_norm": 0.9251964688301086,
|
| 1982 |
+
"learning_rate": 0.00018771968854282539,
|
| 1983 |
+
"loss": 3.9536,
|
| 1984 |
+
"step": 282
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 3.7759197324414715,
|
| 1988 |
+
"grad_norm": 1.0300836563110352,
|
| 1989 |
+
"learning_rate": 0.00018767519466073417,
|
| 1990 |
+
"loss": 4.2908,
|
| 1991 |
+
"step": 283
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 3.789297658862876,
|
| 1995 |
+
"grad_norm": 1.0194575786590576,
|
| 1996 |
+
"learning_rate": 0.00018763070077864295,
|
| 1997 |
+
"loss": 4.1851,
|
| 1998 |
+
"step": 284
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 3.802675585284281,
|
| 2002 |
+
"grad_norm": 0.8165330290794373,
|
| 2003 |
+
"learning_rate": 0.00018758620689655173,
|
| 2004 |
+
"loss": 4.138,
|
| 2005 |
+
"step": 285
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 3.8160535117056855,
|
| 2009 |
+
"grad_norm": 1.0104280710220337,
|
| 2010 |
+
"learning_rate": 0.00018754171301446054,
|
| 2011 |
+
"loss": 3.9481,
|
| 2012 |
+
"step": 286
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 3.82943143812709,
|
| 2016 |
+
"grad_norm": 0.9972538352012634,
|
| 2017 |
+
"learning_rate": 0.0001874972191323693,
|
| 2018 |
+
"loss": 4.3932,
|
| 2019 |
+
"step": 287
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 3.842809364548495,
|
| 2023 |
+
"grad_norm": 0.96323162317276,
|
| 2024 |
+
"learning_rate": 0.0001874527252502781,
|
| 2025 |
+
"loss": 4.1133,
|
| 2026 |
+
"step": 288
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 3.8561872909698995,
|
| 2030 |
+
"grad_norm": 0.8500615954399109,
|
| 2031 |
+
"learning_rate": 0.0001874082313681869,
|
| 2032 |
+
"loss": 4.2205,
|
| 2033 |
+
"step": 289
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 3.869565217391304,
|
| 2037 |
+
"grad_norm": 0.8451250195503235,
|
| 2038 |
+
"learning_rate": 0.00018736373748609567,
|
| 2039 |
+
"loss": 4.1371,
|
| 2040 |
+
"step": 290
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 3.882943143812709,
|
| 2044 |
+
"grad_norm": 0.9399815201759338,
|
| 2045 |
+
"learning_rate": 0.00018731924360400445,
|
| 2046 |
+
"loss": 4.5237,
|
| 2047 |
+
"step": 291
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 3.8963210702341136,
|
| 2051 |
+
"grad_norm": 0.8061622977256775,
|
| 2052 |
+
"learning_rate": 0.00018727474972191326,
|
| 2053 |
+
"loss": 4.1033,
|
| 2054 |
+
"step": 292
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 3.9096989966555182,
|
| 2058 |
+
"grad_norm": 0.7987121343612671,
|
| 2059 |
+
"learning_rate": 0.00018723025583982205,
|
| 2060 |
+
"loss": 3.9311,
|
| 2061 |
+
"step": 293
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 3.9230769230769234,
|
| 2065 |
+
"grad_norm": 0.9041138291358948,
|
| 2066 |
+
"learning_rate": 0.00018718576195773083,
|
| 2067 |
+
"loss": 4.0252,
|
| 2068 |
+
"step": 294
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 3.936454849498328,
|
| 2072 |
+
"grad_norm": 1.0002484321594238,
|
| 2073 |
+
"learning_rate": 0.0001871412680756396,
|
| 2074 |
+
"loss": 4.4605,
|
| 2075 |
+
"step": 295
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 3.9498327759197327,
|
| 2079 |
+
"grad_norm": 0.9991098046302795,
|
| 2080 |
+
"learning_rate": 0.0001870967741935484,
|
| 2081 |
+
"loss": 4.1528,
|
| 2082 |
+
"step": 296
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 3.9632107023411374,
|
| 2086 |
+
"grad_norm": 1.2179397344589233,
|
| 2087 |
+
"learning_rate": 0.00018705228031145718,
|
| 2088 |
+
"loss": 4.5224,
|
| 2089 |
+
"step": 297
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 3.976588628762542,
|
| 2093 |
+
"grad_norm": 0.8279774785041809,
|
| 2094 |
+
"learning_rate": 0.00018700778642936596,
|
| 2095 |
+
"loss": 3.9464,
|
| 2096 |
+
"step": 298
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 3.9899665551839467,
|
| 2100 |
+
"grad_norm": 0.8012803792953491,
|
| 2101 |
+
"learning_rate": 0.00018696329254727477,
|
| 2102 |
+
"loss": 4.0139,
|
| 2103 |
+
"step": 299
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 4.0,
|
| 2107 |
+
"grad_norm": 0.9700272083282471,
|
| 2108 |
+
"learning_rate": 0.00018691879866518355,
|
| 2109 |
+
"loss": 3.8306,
|
| 2110 |
+
"step": 300
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 4.013377926421405,
|
| 2114 |
+
"grad_norm": 0.7136749625205994,
|
| 2115 |
+
"learning_rate": 0.00018687430478309233,
|
| 2116 |
+
"loss": 3.9253,
|
| 2117 |
+
"step": 301
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 4.026755852842809,
|
| 2121 |
+
"grad_norm": 0.7885096669197083,
|
| 2122 |
+
"learning_rate": 0.00018682981090100111,
|
| 2123 |
+
"loss": 3.927,
|
| 2124 |
+
"step": 302
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 4.040133779264214,
|
| 2128 |
+
"grad_norm": 0.7801666855812073,
|
| 2129 |
+
"learning_rate": 0.00018678531701890992,
|
| 2130 |
+
"loss": 3.6482,
|
| 2131 |
+
"step": 303
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 4.053511705685619,
|
| 2135 |
+
"grad_norm": 0.7857955098152161,
|
| 2136 |
+
"learning_rate": 0.00018674082313681868,
|
| 2137 |
+
"loss": 4.0665,
|
| 2138 |
+
"step": 304
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 4.066889632107023,
|
| 2142 |
+
"grad_norm": 0.707421064376831,
|
| 2143 |
+
"learning_rate": 0.0001866963292547275,
|
| 2144 |
+
"loss": 3.9142,
|
| 2145 |
+
"step": 305
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 4.080267558528428,
|
| 2149 |
+
"grad_norm": 0.7936912775039673,
|
| 2150 |
+
"learning_rate": 0.00018665183537263627,
|
| 2151 |
+
"loss": 4.1227,
|
| 2152 |
+
"step": 306
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 4.093645484949833,
|
| 2156 |
+
"grad_norm": 0.8899754881858826,
|
| 2157 |
+
"learning_rate": 0.00018660734149054505,
|
| 2158 |
+
"loss": 3.7661,
|
| 2159 |
+
"step": 307
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 4.107023411371237,
|
| 2163 |
+
"grad_norm": 0.7760347723960876,
|
| 2164 |
+
"learning_rate": 0.00018656284760845384,
|
| 2165 |
+
"loss": 3.8921,
|
| 2166 |
+
"step": 308
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 4.120401337792642,
|
| 2170 |
+
"grad_norm": 0.8672968745231628,
|
| 2171 |
+
"learning_rate": 0.00018651835372636265,
|
| 2172 |
+
"loss": 3.6037,
|
| 2173 |
+
"step": 309
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 4.133779264214047,
|
| 2177 |
+
"grad_norm": 0.8046863675117493,
|
| 2178 |
+
"learning_rate": 0.0001864738598442714,
|
| 2179 |
+
"loss": 3.9117,
|
| 2180 |
+
"step": 310
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 4.147157190635451,
|
| 2184 |
+
"grad_norm": 0.9172897934913635,
|
| 2185 |
+
"learning_rate": 0.0001864293659621802,
|
| 2186 |
+
"loss": 3.7229,
|
| 2187 |
+
"step": 311
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 4.160535117056856,
|
| 2191 |
+
"grad_norm": 0.9616653919219971,
|
| 2192 |
+
"learning_rate": 0.000186384872080089,
|
| 2193 |
+
"loss": 3.8851,
|
| 2194 |
+
"step": 312
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 4.173913043478261,
|
| 2198 |
+
"grad_norm": 0.9659278988838196,
|
| 2199 |
+
"learning_rate": 0.0001863403781979978,
|
| 2200 |
+
"loss": 4.005,
|
| 2201 |
+
"step": 313
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 4.187290969899665,
|
| 2205 |
+
"grad_norm": 0.9171205163002014,
|
| 2206 |
+
"learning_rate": 0.00018629588431590656,
|
| 2207 |
+
"loss": 3.8634,
|
| 2208 |
+
"step": 314
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 4.20066889632107,
|
| 2212 |
+
"grad_norm": 0.9968683123588562,
|
| 2213 |
+
"learning_rate": 0.00018625139043381537,
|
| 2214 |
+
"loss": 3.7321,
|
| 2215 |
+
"step": 315
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 4.214046822742475,
|
| 2219 |
+
"grad_norm": 0.8762083053588867,
|
| 2220 |
+
"learning_rate": 0.00018620689655172415,
|
| 2221 |
+
"loss": 3.931,
|
| 2222 |
+
"step": 316
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 4.2274247491638794,
|
| 2226 |
+
"grad_norm": 0.9815887212753296,
|
| 2227 |
+
"learning_rate": 0.00018616240266963293,
|
| 2228 |
+
"loss": 3.9975,
|
| 2229 |
+
"step": 317
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 4.240802675585284,
|
| 2233 |
+
"grad_norm": 1.0065505504608154,
|
| 2234 |
+
"learning_rate": 0.00018611790878754171,
|
| 2235 |
+
"loss": 3.8364,
|
| 2236 |
+
"step": 318
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 4.254180602006689,
|
| 2240 |
+
"grad_norm": 0.9785431623458862,
|
| 2241 |
+
"learning_rate": 0.00018607341490545052,
|
| 2242 |
+
"loss": 3.8822,
|
| 2243 |
+
"step": 319
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 4.2675585284280935,
|
| 2247 |
+
"grad_norm": 1.077799677848816,
|
| 2248 |
+
"learning_rate": 0.00018602892102335928,
|
| 2249 |
+
"loss": 3.8299,
|
| 2250 |
+
"step": 320
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 4.280936454849498,
|
| 2254 |
+
"grad_norm": 0.8109619617462158,
|
| 2255 |
+
"learning_rate": 0.0001859844271412681,
|
| 2256 |
+
"loss": 3.8096,
|
| 2257 |
+
"step": 321
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 4.294314381270903,
|
| 2261 |
+
"grad_norm": 0.967856764793396,
|
| 2262 |
+
"learning_rate": 0.00018593993325917687,
|
| 2263 |
+
"loss": 3.8639,
|
| 2264 |
+
"step": 322
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 4.3076923076923075,
|
| 2268 |
+
"grad_norm": 0.8657905459403992,
|
| 2269 |
+
"learning_rate": 0.00018589543937708568,
|
| 2270 |
+
"loss": 3.7556,
|
| 2271 |
+
"step": 323
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 4.321070234113712,
|
| 2275 |
+
"grad_norm": 0.9641517400741577,
|
| 2276 |
+
"learning_rate": 0.00018585094549499444,
|
| 2277 |
+
"loss": 3.9702,
|
| 2278 |
+
"step": 324
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 4.334448160535117,
|
| 2282 |
+
"grad_norm": 0.9664435982704163,
|
| 2283 |
+
"learning_rate": 0.00018580645161290325,
|
| 2284 |
+
"loss": 3.8754,
|
| 2285 |
+
"step": 325
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 4.3478260869565215,
|
| 2289 |
+
"grad_norm": 0.8322617411613464,
|
| 2290 |
+
"learning_rate": 0.00018576195773081203,
|
| 2291 |
+
"loss": 3.83,
|
| 2292 |
+
"step": 326
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 4.361204013377926,
|
| 2296 |
+
"grad_norm": 1.0363450050354004,
|
| 2297 |
+
"learning_rate": 0.0001857174638487208,
|
| 2298 |
+
"loss": 3.9825,
|
| 2299 |
+
"step": 327
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 4.374581939799331,
|
| 2303 |
+
"grad_norm": 1.0125840902328491,
|
| 2304 |
+
"learning_rate": 0.0001856729699666296,
|
| 2305 |
+
"loss": 3.6525,
|
| 2306 |
+
"step": 328
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 4.3879598662207355,
|
| 2310 |
+
"grad_norm": 0.9922601580619812,
|
| 2311 |
+
"learning_rate": 0.0001856284760845384,
|
| 2312 |
+
"loss": 4.2373,
|
| 2313 |
+
"step": 329
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 4.40133779264214,
|
| 2317 |
+
"grad_norm": 0.9070426225662231,
|
| 2318 |
+
"learning_rate": 0.00018558398220244716,
|
| 2319 |
+
"loss": 3.9623,
|
| 2320 |
+
"step": 330
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 4.414715719063545,
|
| 2324 |
+
"grad_norm": 0.9369637370109558,
|
| 2325 |
+
"learning_rate": 0.00018553948832035597,
|
| 2326 |
+
"loss": 3.9297,
|
| 2327 |
+
"step": 331
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 4.4280936454849495,
|
| 2331 |
+
"grad_norm": 1.108876347541809,
|
| 2332 |
+
"learning_rate": 0.00018549499443826475,
|
| 2333 |
+
"loss": 3.7325,
|
| 2334 |
+
"step": 332
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 4.441471571906354,
|
| 2338 |
+
"grad_norm": 0.9405660629272461,
|
| 2339 |
+
"learning_rate": 0.00018545050055617356,
|
| 2340 |
+
"loss": 3.8615,
|
| 2341 |
+
"step": 333
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 4.454849498327759,
|
| 2345 |
+
"grad_norm": 0.9730128645896912,
|
| 2346 |
+
"learning_rate": 0.00018540600667408231,
|
| 2347 |
+
"loss": 4.1794,
|
| 2348 |
+
"step": 334
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 4.468227424749164,
|
| 2352 |
+
"grad_norm": 0.9341335892677307,
|
| 2353 |
+
"learning_rate": 0.00018536151279199112,
|
| 2354 |
+
"loss": 3.9422,
|
| 2355 |
+
"step": 335
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 4.481605351170568,
|
| 2359 |
+
"grad_norm": 0.9262625575065613,
|
| 2360 |
+
"learning_rate": 0.0001853170189098999,
|
| 2361 |
+
"loss": 3.9819,
|
| 2362 |
+
"step": 336
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 4.494983277591973,
|
| 2366 |
+
"grad_norm": 1.0419141054153442,
|
| 2367 |
+
"learning_rate": 0.00018527252502780866,
|
| 2368 |
+
"loss": 3.7481,
|
| 2369 |
+
"step": 337
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 4.508361204013378,
|
| 2373 |
+
"grad_norm": 0.8986826539039612,
|
| 2374 |
+
"learning_rate": 0.00018522803114571747,
|
| 2375 |
+
"loss": 4.1195,
|
| 2376 |
+
"step": 338
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 4.521739130434782,
|
| 2380 |
+
"grad_norm": 0.9502431154251099,
|
| 2381 |
+
"learning_rate": 0.00018518353726362625,
|
| 2382 |
+
"loss": 3.8521,
|
| 2383 |
+
"step": 339
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 4.535117056856187,
|
| 2387 |
+
"grad_norm": 0.8936267495155334,
|
| 2388 |
+
"learning_rate": 0.00018513904338153504,
|
| 2389 |
+
"loss": 3.647,
|
| 2390 |
+
"step": 340
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 4.548494983277592,
|
| 2394 |
+
"grad_norm": 0.8870158195495605,
|
| 2395 |
+
"learning_rate": 0.00018509454949944382,
|
| 2396 |
+
"loss": 3.7624,
|
| 2397 |
+
"step": 341
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 4.561872909698996,
|
| 2401 |
+
"grad_norm": 0.9030978679656982,
|
| 2402 |
+
"learning_rate": 0.00018505005561735263,
|
| 2403 |
+
"loss": 3.8018,
|
| 2404 |
+
"step": 342
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 4.575250836120401,
|
| 2408 |
+
"grad_norm": 0.8690946698188782,
|
| 2409 |
+
"learning_rate": 0.0001850055617352614,
|
| 2410 |
+
"loss": 3.6183,
|
| 2411 |
+
"step": 343
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 4.588628762541806,
|
| 2415 |
+
"grad_norm": 0.9812071323394775,
|
| 2416 |
+
"learning_rate": 0.0001849610678531702,
|
| 2417 |
+
"loss": 4.1231,
|
| 2418 |
+
"step": 344
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 4.602006688963211,
|
| 2422 |
+
"grad_norm": 0.9404383301734924,
|
| 2423 |
+
"learning_rate": 0.00018491657397107897,
|
| 2424 |
+
"loss": 3.9645,
|
| 2425 |
+
"step": 345
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 4.615384615384615,
|
| 2429 |
+
"grad_norm": 1.0422123670578003,
|
| 2430 |
+
"learning_rate": 0.00018487208008898778,
|
| 2431 |
+
"loss": 3.9031,
|
| 2432 |
+
"step": 346
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 4.6287625418060205,
|
| 2436 |
+
"grad_norm": 0.9838129281997681,
|
| 2437 |
+
"learning_rate": 0.00018482758620689654,
|
| 2438 |
+
"loss": 3.9985,
|
| 2439 |
+
"step": 347
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 4.642140468227424,
|
| 2443 |
+
"grad_norm": 0.9232532978057861,
|
| 2444 |
+
"learning_rate": 0.00018478309232480535,
|
| 2445 |
+
"loss": 4.0343,
|
| 2446 |
+
"step": 348
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 4.65551839464883,
|
| 2450 |
+
"grad_norm": 0.9242956042289734,
|
| 2451 |
+
"learning_rate": 0.00018473859844271413,
|
| 2452 |
+
"loss": 4.0669,
|
| 2453 |
+
"step": 349
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 4.668896321070234,
|
| 2457 |
+
"grad_norm": 0.919269859790802,
|
| 2458 |
+
"learning_rate": 0.0001846941045606229,
|
| 2459 |
+
"loss": 4.0549,
|
| 2460 |
+
"step": 350
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 4.682274247491639,
|
| 2464 |
+
"grad_norm": 0.93565833568573,
|
| 2465 |
+
"learning_rate": 0.0001846496106785317,
|
| 2466 |
+
"loss": 4.1306,
|
| 2467 |
+
"step": 351
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 4.695652173913043,
|
| 2471 |
+
"grad_norm": 0.9001899361610413,
|
| 2472 |
+
"learning_rate": 0.0001846051167964405,
|
| 2473 |
+
"loss": 3.8916,
|
| 2474 |
+
"step": 352
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 4.709030100334449,
|
| 2478 |
+
"grad_norm": 0.8896821737289429,
|
| 2479 |
+
"learning_rate": 0.0001845606229143493,
|
| 2480 |
+
"loss": 3.8377,
|
| 2481 |
+
"step": 353
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 4.722408026755852,
|
| 2485 |
+
"grad_norm": 1.0137807130813599,
|
| 2486 |
+
"learning_rate": 0.00018451612903225807,
|
| 2487 |
+
"loss": 3.9923,
|
| 2488 |
+
"step": 354
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 4.735785953177258,
|
| 2492 |
+
"grad_norm": 1.075823426246643,
|
| 2493 |
+
"learning_rate": 0.00018447163515016685,
|
| 2494 |
+
"loss": 4.0706,
|
| 2495 |
+
"step": 355
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 4.749163879598662,
|
| 2499 |
+
"grad_norm": 1.0076895952224731,
|
| 2500 |
+
"learning_rate": 0.00018442714126807566,
|
| 2501 |
+
"loss": 4.0759,
|
| 2502 |
+
"step": 356
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 4.762541806020067,
|
| 2506 |
+
"grad_norm": 0.9387428164482117,
|
| 2507 |
+
"learning_rate": 0.00018438264738598442,
|
| 2508 |
+
"loss": 3.6959,
|
| 2509 |
+
"step": 357
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 4.775919732441472,
|
| 2513 |
+
"grad_norm": 0.8920648097991943,
|
| 2514 |
+
"learning_rate": 0.00018433815350389323,
|
| 2515 |
+
"loss": 3.9213,
|
| 2516 |
+
"step": 358
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 4.789297658862877,
|
| 2520 |
+
"grad_norm": 1.0252491235733032,
|
| 2521 |
+
"learning_rate": 0.000184293659621802,
|
| 2522 |
+
"loss": 3.9118,
|
| 2523 |
+
"step": 359
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 4.802675585284281,
|
| 2527 |
+
"grad_norm": 1.0382707118988037,
|
| 2528 |
+
"learning_rate": 0.0001842491657397108,
|
| 2529 |
+
"loss": 4.0172,
|
| 2530 |
+
"step": 360
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 4.816053511705686,
|
| 2534 |
+
"grad_norm": 1.07838773727417,
|
| 2535 |
+
"learning_rate": 0.00018420467185761957,
|
| 2536 |
+
"loss": 3.8531,
|
| 2537 |
+
"step": 361
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 4.829431438127091,
|
| 2541 |
+
"grad_norm": 0.9974546432495117,
|
| 2542 |
+
"learning_rate": 0.00018416017797552838,
|
| 2543 |
+
"loss": 4.0387,
|
| 2544 |
+
"step": 362
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 4.842809364548495,
|
| 2548 |
+
"grad_norm": 1.024491548538208,
|
| 2549 |
+
"learning_rate": 0.00018411568409343717,
|
| 2550 |
+
"loss": 3.9504,
|
| 2551 |
+
"step": 363
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 4.8561872909699,
|
| 2555 |
+
"grad_norm": 0.9236369132995605,
|
| 2556 |
+
"learning_rate": 0.00018407119021134595,
|
| 2557 |
+
"loss": 3.7119,
|
| 2558 |
+
"step": 364
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 4.869565217391305,
|
| 2562 |
+
"grad_norm": 0.935644268989563,
|
| 2563 |
+
"learning_rate": 0.00018402669632925473,
|
| 2564 |
+
"loss": 4.0077,
|
| 2565 |
+
"step": 365
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 4.882943143812709,
|
| 2569 |
+
"grad_norm": 0.9328681230545044,
|
| 2570 |
+
"learning_rate": 0.00018398220244716354,
|
| 2571 |
+
"loss": 3.9133,
|
| 2572 |
+
"step": 366
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 4.896321070234114,
|
| 2576 |
+
"grad_norm": 0.9596607089042664,
|
| 2577 |
+
"learning_rate": 0.0001839377085650723,
|
| 2578 |
+
"loss": 3.8003,
|
| 2579 |
+
"step": 367
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 4.909698996655519,
|
| 2583 |
+
"grad_norm": 0.9878052473068237,
|
| 2584 |
+
"learning_rate": 0.0001838932146829811,
|
| 2585 |
+
"loss": 3.8805,
|
| 2586 |
+
"step": 368
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 4.923076923076923,
|
| 2590 |
+
"grad_norm": 1.00381600856781,
|
| 2591 |
+
"learning_rate": 0.0001838487208008899,
|
| 2592 |
+
"loss": 4.0264,
|
| 2593 |
+
"step": 369
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 4.936454849498328,
|
| 2597 |
+
"grad_norm": 1.024754524230957,
|
| 2598 |
+
"learning_rate": 0.00018380422691879867,
|
| 2599 |
+
"loss": 3.7291,
|
| 2600 |
+
"step": 370
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 4.949832775919733,
|
| 2604 |
+
"grad_norm": 0.9670823812484741,
|
| 2605 |
+
"learning_rate": 0.00018375973303670745,
|
| 2606 |
+
"loss": 3.9418,
|
| 2607 |
+
"step": 371
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 4.963210702341137,
|
| 2611 |
+
"grad_norm": 0.9736581444740295,
|
| 2612 |
+
"learning_rate": 0.00018371523915461626,
|
| 2613 |
+
"loss": 3.8813,
|
| 2614 |
+
"step": 372
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 4.976588628762542,
|
| 2618 |
+
"grad_norm": 0.9752672910690308,
|
| 2619 |
+
"learning_rate": 0.00018367074527252504,
|
| 2620 |
+
"loss": 3.6717,
|
| 2621 |
+
"step": 373
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 4.989966555183947,
|
| 2625 |
+
"grad_norm": 1.1268304586410522,
|
| 2626 |
+
"learning_rate": 0.00018362625139043383,
|
| 2627 |
+
"loss": 3.9782,
|
| 2628 |
+
"step": 374
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 5.0,
|
| 2632 |
+
"grad_norm": 1.7933701276779175,
|
| 2633 |
+
"learning_rate": 0.0001835817575083426,
|
| 2634 |
+
"loss": 3.001,
|
| 2635 |
+
"step": 375
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 5.013377926421405,
|
| 2639 |
+
"grad_norm": 0.8035010099411011,
|
| 2640 |
+
"learning_rate": 0.00018353726362625142,
|
| 2641 |
+
"loss": 3.7943,
|
| 2642 |
+
"step": 376
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 5.026755852842809,
|
| 2646 |
+
"grad_norm": 0.8016420006752014,
|
| 2647 |
+
"learning_rate": 0.00018349276974416017,
|
| 2648 |
+
"loss": 3.7454,
|
| 2649 |
+
"step": 377
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 5.040133779264214,
|
| 2653 |
+
"grad_norm": 0.6844643354415894,
|
| 2654 |
+
"learning_rate": 0.00018344827586206896,
|
| 2655 |
+
"loss": 3.699,
|
| 2656 |
+
"step": 378
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 5.053511705685619,
|
| 2660 |
+
"grad_norm": 0.8649943470954895,
|
| 2661 |
+
"learning_rate": 0.00018340378197997777,
|
| 2662 |
+
"loss": 3.7197,
|
| 2663 |
+
"step": 379
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 5.066889632107023,
|
| 2667 |
+
"grad_norm": 0.9685015678405762,
|
| 2668 |
+
"learning_rate": 0.00018335928809788655,
|
| 2669 |
+
"loss": 3.6952,
|
| 2670 |
+
"step": 380
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 5.080267558528428,
|
| 2674 |
+
"grad_norm": 0.8728330135345459,
|
| 2675 |
+
"learning_rate": 0.00018331479421579533,
|
| 2676 |
+
"loss": 3.7164,
|
| 2677 |
+
"step": 381
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 5.093645484949833,
|
| 2681 |
+
"grad_norm": 0.962504506111145,
|
| 2682 |
+
"learning_rate": 0.0001832703003337041,
|
| 2683 |
+
"loss": 3.6123,
|
| 2684 |
+
"step": 382
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 5.107023411371237,
|
| 2688 |
+
"grad_norm": 0.9194462895393372,
|
| 2689 |
+
"learning_rate": 0.00018322580645161292,
|
| 2690 |
+
"loss": 3.275,
|
| 2691 |
+
"step": 383
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 5.120401337792642,
|
| 2695 |
+
"grad_norm": 0.9851329326629639,
|
| 2696 |
+
"learning_rate": 0.00018318131256952168,
|
| 2697 |
+
"loss": 3.6222,
|
| 2698 |
+
"step": 384
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 5.133779264214047,
|
| 2702 |
+
"grad_norm": 1.0702580213546753,
|
| 2703 |
+
"learning_rate": 0.0001831368186874305,
|
| 2704 |
+
"loss": 3.8728,
|
| 2705 |
+
"step": 385
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 5.147157190635451,
|
| 2709 |
+
"grad_norm": 1.3237228393554688,
|
| 2710 |
+
"learning_rate": 0.00018309232480533927,
|
| 2711 |
+
"loss": 3.8948,
|
| 2712 |
+
"step": 386
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 5.160535117056856,
|
| 2716 |
+
"grad_norm": 1.0076218843460083,
|
| 2717 |
+
"learning_rate": 0.00018304783092324805,
|
| 2718 |
+
"loss": 3.8894,
|
| 2719 |
+
"step": 387
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 5.173913043478261,
|
| 2723 |
+
"grad_norm": 1.084722876548767,
|
| 2724 |
+
"learning_rate": 0.00018300333704115683,
|
| 2725 |
+
"loss": 3.7398,
|
| 2726 |
+
"step": 388
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 5.187290969899665,
|
| 2730 |
+
"grad_norm": 0.9112711548805237,
|
| 2731 |
+
"learning_rate": 0.00018295884315906564,
|
| 2732 |
+
"loss": 3.5901,
|
| 2733 |
+
"step": 389
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 5.20066889632107,
|
| 2737 |
+
"grad_norm": 0.9451406002044678,
|
| 2738 |
+
"learning_rate": 0.00018291434927697443,
|
| 2739 |
+
"loss": 3.6313,
|
| 2740 |
+
"step": 390
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 5.214046822742475,
|
| 2744 |
+
"grad_norm": 0.8901047706604004,
|
| 2745 |
+
"learning_rate": 0.0001828698553948832,
|
| 2746 |
+
"loss": 3.3191,
|
| 2747 |
+
"step": 391
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 5.2274247491638794,
|
| 2751 |
+
"grad_norm": 0.9838565587997437,
|
| 2752 |
+
"learning_rate": 0.000182825361512792,
|
| 2753 |
+
"loss": 3.882,
|
| 2754 |
+
"step": 392
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 5.240802675585284,
|
| 2758 |
+
"grad_norm": 0.9839156866073608,
|
| 2759 |
+
"learning_rate": 0.0001827808676307008,
|
| 2760 |
+
"loss": 3.6068,
|
| 2761 |
+
"step": 393
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 5.254180602006689,
|
| 2765 |
+
"grad_norm": 0.9328583478927612,
|
| 2766 |
+
"learning_rate": 0.00018273637374860956,
|
| 2767 |
+
"loss": 3.6856,
|
| 2768 |
+
"step": 394
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 5.2675585284280935,
|
| 2772 |
+
"grad_norm": 0.8705796003341675,
|
| 2773 |
+
"learning_rate": 0.00018269187986651837,
|
| 2774 |
+
"loss": 3.7282,
|
| 2775 |
+
"step": 395
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 5.280936454849498,
|
| 2779 |
+
"grad_norm": 0.9675374031066895,
|
| 2780 |
+
"learning_rate": 0.00018264738598442715,
|
| 2781 |
+
"loss": 3.6588,
|
| 2782 |
+
"step": 396
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 5.294314381270903,
|
| 2786 |
+
"grad_norm": 1.145280361175537,
|
| 2787 |
+
"learning_rate": 0.00018260289210233593,
|
| 2788 |
+
"loss": 3.8843,
|
| 2789 |
+
"step": 397
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 5.3076923076923075,
|
| 2793 |
+
"grad_norm": 0.9769694805145264,
|
| 2794 |
+
"learning_rate": 0.0001825583982202447,
|
| 2795 |
+
"loss": 3.7207,
|
| 2796 |
+
"step": 398
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 5.321070234113712,
|
| 2800 |
+
"grad_norm": 0.9277816414833069,
|
| 2801 |
+
"learning_rate": 0.00018251390433815352,
|
| 2802 |
+
"loss": 3.712,
|
| 2803 |
+
"step": 399
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 5.334448160535117,
|
| 2807 |
+
"grad_norm": 1.1015180349349976,
|
| 2808 |
+
"learning_rate": 0.0001824694104560623,
|
| 2809 |
+
"loss": 3.7941,
|
| 2810 |
+
"step": 400
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 5.3478260869565215,
|
| 2814 |
+
"grad_norm": 1.2234200239181519,
|
| 2815 |
+
"learning_rate": 0.0001824249165739711,
|
| 2816 |
+
"loss": 3.6559,
|
| 2817 |
+
"step": 401
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 5.361204013377926,
|
| 2821 |
+
"grad_norm": 0.9358471035957336,
|
| 2822 |
+
"learning_rate": 0.00018238042269187987,
|
| 2823 |
+
"loss": 3.7665,
|
| 2824 |
+
"step": 402
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 5.374581939799331,
|
| 2828 |
+
"grad_norm": 0.8287034630775452,
|
| 2829 |
+
"learning_rate": 0.00018233592880978868,
|
| 2830 |
+
"loss": 3.8265,
|
| 2831 |
+
"step": 403
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 5.3879598662207355,
|
| 2835 |
+
"grad_norm": 1.0219204425811768,
|
| 2836 |
+
"learning_rate": 0.00018229143492769743,
|
| 2837 |
+
"loss": 3.6829,
|
| 2838 |
+
"step": 404
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 5.40133779264214,
|
| 2842 |
+
"grad_norm": 1.0601041316986084,
|
| 2843 |
+
"learning_rate": 0.00018224694104560624,
|
| 2844 |
+
"loss": 3.5879,
|
| 2845 |
+
"step": 405
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 5.414715719063545,
|
| 2849 |
+
"grad_norm": 1.2221566438674927,
|
| 2850 |
+
"learning_rate": 0.00018220244716351503,
|
| 2851 |
+
"loss": 3.6023,
|
| 2852 |
+
"step": 406
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 5.4280936454849495,
|
| 2856 |
+
"grad_norm": 0.9589087963104248,
|
| 2857 |
+
"learning_rate": 0.0001821579532814238,
|
| 2858 |
+
"loss": 3.9109,
|
| 2859 |
+
"step": 407
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 5.441471571906354,
|
| 2863 |
+
"grad_norm": 1.088295340538025,
|
| 2864 |
+
"learning_rate": 0.0001821134593993326,
|
| 2865 |
+
"loss": 3.5695,
|
| 2866 |
+
"step": 408
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 5.454849498327759,
|
| 2870 |
+
"grad_norm": 1.1284915208816528,
|
| 2871 |
+
"learning_rate": 0.0001820689655172414,
|
| 2872 |
+
"loss": 3.6004,
|
| 2873 |
+
"step": 409
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 5.468227424749164,
|
| 2877 |
+
"grad_norm": 1.0108689069747925,
|
| 2878 |
+
"learning_rate": 0.00018202447163515018,
|
| 2879 |
+
"loss": 3.7797,
|
| 2880 |
+
"step": 410
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 5.481605351170568,
|
| 2884 |
+
"grad_norm": 0.8550918102264404,
|
| 2885 |
+
"learning_rate": 0.00018197997775305896,
|
| 2886 |
+
"loss": 3.5758,
|
| 2887 |
+
"step": 411
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 5.494983277591973,
|
| 2891 |
+
"grad_norm": 0.8765145540237427,
|
| 2892 |
+
"learning_rate": 0.00018193548387096775,
|
| 2893 |
+
"loss": 3.7625,
|
| 2894 |
+
"step": 412
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 5.508361204013378,
|
| 2898 |
+
"grad_norm": 1.0253541469573975,
|
| 2899 |
+
"learning_rate": 0.00018189098998887656,
|
| 2900 |
+
"loss": 3.6033,
|
| 2901 |
+
"step": 413
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 5.521739130434782,
|
| 2905 |
+
"grad_norm": 1.0475622415542603,
|
| 2906 |
+
"learning_rate": 0.0001818464961067853,
|
| 2907 |
+
"loss": 3.813,
|
| 2908 |
+
"step": 414
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 5.535117056856187,
|
| 2912 |
+
"grad_norm": 1.053133249282837,
|
| 2913 |
+
"learning_rate": 0.00018180200222469412,
|
| 2914 |
+
"loss": 3.4779,
|
| 2915 |
+
"step": 415
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 5.548494983277592,
|
| 2919 |
+
"grad_norm": 1.0151216983795166,
|
| 2920 |
+
"learning_rate": 0.0001817575083426029,
|
| 2921 |
+
"loss": 3.9038,
|
| 2922 |
+
"step": 416
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 5.561872909698996,
|
| 2926 |
+
"grad_norm": 1.4666434526443481,
|
| 2927 |
+
"learning_rate": 0.00018171301446051169,
|
| 2928 |
+
"loss": 3.4735,
|
| 2929 |
+
"step": 417
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 5.575250836120401,
|
| 2933 |
+
"grad_norm": 1.1043344736099243,
|
| 2934 |
+
"learning_rate": 0.00018166852057842047,
|
| 2935 |
+
"loss": 3.7449,
|
| 2936 |
+
"step": 418
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 5.588628762541806,
|
| 2940 |
+
"grad_norm": 0.900745153427124,
|
| 2941 |
+
"learning_rate": 0.00018162402669632925,
|
| 2942 |
+
"loss": 3.7401,
|
| 2943 |
+
"step": 419
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 5.602006688963211,
|
| 2947 |
+
"grad_norm": 0.9771101474761963,
|
| 2948 |
+
"learning_rate": 0.00018157953281423806,
|
| 2949 |
+
"loss": 3.8328,
|
| 2950 |
+
"step": 420
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 5.615384615384615,
|
| 2954 |
+
"grad_norm": 0.9099516272544861,
|
| 2955 |
+
"learning_rate": 0.00018153503893214682,
|
| 2956 |
+
"loss": 3.6245,
|
| 2957 |
+
"step": 421
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 5.6287625418060205,
|
| 2961 |
+
"grad_norm": 0.9844585657119751,
|
| 2962 |
+
"learning_rate": 0.00018149054505005563,
|
| 2963 |
+
"loss": 3.5776,
|
| 2964 |
+
"step": 422
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 5.642140468227424,
|
| 2968 |
+
"grad_norm": 1.0481154918670654,
|
| 2969 |
+
"learning_rate": 0.0001814460511679644,
|
| 2970 |
+
"loss": 3.6304,
|
| 2971 |
+
"step": 423
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 5.65551839464883,
|
| 2975 |
+
"grad_norm": 0.9971081614494324,
|
| 2976 |
+
"learning_rate": 0.0001814015572858732,
|
| 2977 |
+
"loss": 3.7863,
|
| 2978 |
+
"step": 424
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 5.668896321070234,
|
| 2982 |
+
"grad_norm": 0.9247872829437256,
|
| 2983 |
+
"learning_rate": 0.00018135706340378197,
|
| 2984 |
+
"loss": 3.7319,
|
| 2985 |
+
"step": 425
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 5.682274247491639,
|
| 2989 |
+
"grad_norm": 0.9895725846290588,
|
| 2990 |
+
"learning_rate": 0.00018131256952169078,
|
| 2991 |
+
"loss": 3.78,
|
| 2992 |
+
"step": 426
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 5.695652173913043,
|
| 2996 |
+
"grad_norm": 1.0847641229629517,
|
| 2997 |
+
"learning_rate": 0.00018126807563959956,
|
| 2998 |
+
"loss": 3.8662,
|
| 2999 |
+
"step": 427
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 5.709030100334449,
|
| 3003 |
+
"grad_norm": 0.986259937286377,
|
| 3004 |
+
"learning_rate": 0.00018122358175750835,
|
| 3005 |
+
"loss": 3.5621,
|
| 3006 |
+
"step": 428
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 5.722408026755852,
|
| 3010 |
+
"grad_norm": 0.9166681170463562,
|
| 3011 |
+
"learning_rate": 0.00018117908787541713,
|
| 3012 |
+
"loss": 3.6153,
|
| 3013 |
+
"step": 429
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 5.735785953177258,
|
| 3017 |
+
"grad_norm": 1.1331177949905396,
|
| 3018 |
+
"learning_rate": 0.00018113459399332594,
|
| 3019 |
+
"loss": 3.5976,
|
| 3020 |
+
"step": 430
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 5.749163879598662,
|
| 3024 |
+
"grad_norm": 0.8743540644645691,
|
| 3025 |
+
"learning_rate": 0.0001810901001112347,
|
| 3026 |
+
"loss": 3.2511,
|
| 3027 |
+
"step": 431
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 5.762541806020067,
|
| 3031 |
+
"grad_norm": 1.0700207948684692,
|
| 3032 |
+
"learning_rate": 0.0001810456062291435,
|
| 3033 |
+
"loss": 3.7634,
|
| 3034 |
+
"step": 432
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 5.775919732441472,
|
| 3038 |
+
"grad_norm": 0.9412694573402405,
|
| 3039 |
+
"learning_rate": 0.00018100111234705229,
|
| 3040 |
+
"loss": 3.6264,
|
| 3041 |
+
"step": 433
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 5.789297658862877,
|
| 3045 |
+
"grad_norm": 1.0398496389389038,
|
| 3046 |
+
"learning_rate": 0.00018095661846496107,
|
| 3047 |
+
"loss": 3.744,
|
| 3048 |
+
"step": 434
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 5.802675585284281,
|
| 3052 |
+
"grad_norm": 0.9605004787445068,
|
| 3053 |
+
"learning_rate": 0.00018091212458286985,
|
| 3054 |
+
"loss": 3.5532,
|
| 3055 |
+
"step": 435
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 5.816053511705686,
|
| 3059 |
+
"grad_norm": 1.0449095964431763,
|
| 3060 |
+
"learning_rate": 0.00018086763070077866,
|
| 3061 |
+
"loss": 4.0611,
|
| 3062 |
+
"step": 436
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 5.829431438127091,
|
| 3066 |
+
"grad_norm": 0.9342606663703918,
|
| 3067 |
+
"learning_rate": 0.00018082313681868744,
|
| 3068 |
+
"loss": 3.9957,
|
| 3069 |
+
"step": 437
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 5.842809364548495,
|
| 3073 |
+
"grad_norm": 0.9687880873680115,
|
| 3074 |
+
"learning_rate": 0.00018077864293659622,
|
| 3075 |
+
"loss": 3.9299,
|
| 3076 |
+
"step": 438
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 5.8561872909699,
|
| 3080 |
+
"grad_norm": 1.1390576362609863,
|
| 3081 |
+
"learning_rate": 0.000180734149054505,
|
| 3082 |
+
"loss": 3.6552,
|
| 3083 |
+
"step": 439
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 5.869565217391305,
|
| 3087 |
+
"grad_norm": 0.9280988574028015,
|
| 3088 |
+
"learning_rate": 0.00018068965517241382,
|
| 3089 |
+
"loss": 3.7828,
|
| 3090 |
+
"step": 440
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 5.882943143812709,
|
| 3094 |
+
"grad_norm": 1.2928193807601929,
|
| 3095 |
+
"learning_rate": 0.00018064516129032257,
|
| 3096 |
+
"loss": 3.6292,
|
| 3097 |
+
"step": 441
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 5.896321070234114,
|
| 3101 |
+
"grad_norm": 1.0959875583648682,
|
| 3102 |
+
"learning_rate": 0.00018060066740823138,
|
| 3103 |
+
"loss": 3.4293,
|
| 3104 |
+
"step": 442
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 5.909698996655519,
|
| 3108 |
+
"grad_norm": 1.0713289976119995,
|
| 3109 |
+
"learning_rate": 0.00018055617352614016,
|
| 3110 |
+
"loss": 3.7767,
|
| 3111 |
+
"step": 443
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 5.923076923076923,
|
| 3115 |
+
"grad_norm": 0.9309440851211548,
|
| 3116 |
+
"learning_rate": 0.00018051167964404895,
|
| 3117 |
+
"loss": 3.5473,
|
| 3118 |
+
"step": 444
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 5.936454849498328,
|
| 3122 |
+
"grad_norm": 1.0999056100845337,
|
| 3123 |
+
"learning_rate": 0.00018046718576195773,
|
| 3124 |
+
"loss": 3.9694,
|
| 3125 |
+
"step": 445
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 5.949832775919733,
|
| 3129 |
+
"grad_norm": 1.1073781251907349,
|
| 3130 |
+
"learning_rate": 0.00018042269187986654,
|
| 3131 |
+
"loss": 3.6882,
|
| 3132 |
+
"step": 446
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 5.963210702341137,
|
| 3136 |
+
"grad_norm": 1.0430257320404053,
|
| 3137 |
+
"learning_rate": 0.00018037819799777532,
|
| 3138 |
+
"loss": 3.4009,
|
| 3139 |
+
"step": 447
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 5.976588628762542,
|
| 3143 |
+
"grad_norm": 1.1132690906524658,
|
| 3144 |
+
"learning_rate": 0.0001803337041156841,
|
| 3145 |
+
"loss": 3.8832,
|
| 3146 |
+
"step": 448
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 5.989966555183947,
|
| 3150 |
+
"grad_norm": 1.0147771835327148,
|
| 3151 |
+
"learning_rate": 0.00018028921023359289,
|
| 3152 |
+
"loss": 3.7117,
|
| 3153 |
+
"step": 449
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 6.0,
|
| 3157 |
+
"grad_norm": 1.458959698677063,
|
| 3158 |
+
"learning_rate": 0.0001802447163515017,
|
| 3159 |
+
"loss": 3.5745,
|
| 3160 |
+
"step": 450
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 6.013377926421405,
|
| 3164 |
+
"grad_norm": 0.8363592028617859,
|
| 3165 |
+
"learning_rate": 0.00018020022246941045,
|
| 3166 |
+
"loss": 3.5835,
|
| 3167 |
+
"step": 451
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 6.026755852842809,
|
| 3171 |
+
"grad_norm": 0.8071937561035156,
|
| 3172 |
+
"learning_rate": 0.00018015572858731926,
|
| 3173 |
+
"loss": 3.5923,
|
| 3174 |
+
"step": 452
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 6.040133779264214,
|
| 3178 |
+
"grad_norm": 0.7746313214302063,
|
| 3179 |
+
"learning_rate": 0.00018011123470522804,
|
| 3180 |
+
"loss": 3.5688,
|
| 3181 |
+
"step": 453
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 6.053511705685619,
|
| 3185 |
+
"grad_norm": 0.689179539680481,
|
| 3186 |
+
"learning_rate": 0.00018006674082313682,
|
| 3187 |
+
"loss": 3.412,
|
| 3188 |
+
"step": 454
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 6.066889632107023,
|
| 3192 |
+
"grad_norm": 0.8438050746917725,
|
| 3193 |
+
"learning_rate": 0.0001800222469410456,
|
| 3194 |
+
"loss": 3.403,
|
| 3195 |
+
"step": 455
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 6.080267558528428,
|
| 3199 |
+
"grad_norm": 0.7670062780380249,
|
| 3200 |
+
"learning_rate": 0.00017997775305895442,
|
| 3201 |
+
"loss": 3.5029,
|
| 3202 |
+
"step": 456
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 6.093645484949833,
|
| 3206 |
+
"grad_norm": 0.8185870051383972,
|
| 3207 |
+
"learning_rate": 0.0001799332591768632,
|
| 3208 |
+
"loss": 3.4584,
|
| 3209 |
+
"step": 457
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 6.107023411371237,
|
| 3213 |
+
"grad_norm": 0.9618543386459351,
|
| 3214 |
+
"learning_rate": 0.00017988876529477198,
|
| 3215 |
+
"loss": 3.6538,
|
| 3216 |
+
"step": 458
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 6.120401337792642,
|
| 3220 |
+
"grad_norm": 0.959724485874176,
|
| 3221 |
+
"learning_rate": 0.00017984427141268076,
|
| 3222 |
+
"loss": 3.5284,
|
| 3223 |
+
"step": 459
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 6.133779264214047,
|
| 3227 |
+
"grad_norm": 0.8044765591621399,
|
| 3228 |
+
"learning_rate": 0.00017979977753058955,
|
| 3229 |
+
"loss": 3.2198,
|
| 3230 |
+
"step": 460
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 6.147157190635451,
|
| 3234 |
+
"grad_norm": 0.8287092447280884,
|
| 3235 |
+
"learning_rate": 0.00017975528364849833,
|
| 3236 |
+
"loss": 3.4977,
|
| 3237 |
+
"step": 461
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 6.160535117056856,
|
| 3241 |
+
"grad_norm": 0.8855329155921936,
|
| 3242 |
+
"learning_rate": 0.0001797107897664071,
|
| 3243 |
+
"loss": 3.5008,
|
| 3244 |
+
"step": 462
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 6.173913043478261,
|
| 3248 |
+
"grad_norm": 0.8839483857154846,
|
| 3249 |
+
"learning_rate": 0.00017966629588431592,
|
| 3250 |
+
"loss": 3.6135,
|
| 3251 |
+
"step": 463
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 6.187290969899665,
|
| 3255 |
+
"grad_norm": 0.963446319103241,
|
| 3256 |
+
"learning_rate": 0.0001796218020022247,
|
| 3257 |
+
"loss": 3.6156,
|
| 3258 |
+
"step": 464
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 6.20066889632107,
|
| 3262 |
+
"grad_norm": 0.896743655204773,
|
| 3263 |
+
"learning_rate": 0.00017957730812013348,
|
| 3264 |
+
"loss": 3.6623,
|
| 3265 |
+
"step": 465
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 6.214046822742475,
|
| 3269 |
+
"grad_norm": 0.9268617033958435,
|
| 3270 |
+
"learning_rate": 0.00017953281423804227,
|
| 3271 |
+
"loss": 3.4343,
|
| 3272 |
+
"step": 466
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 6.2274247491638794,
|
| 3276 |
+
"grad_norm": 0.8335449695587158,
|
| 3277 |
+
"learning_rate": 0.00017948832035595108,
|
| 3278 |
+
"loss": 3.5716,
|
| 3279 |
+
"step": 467
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 6.240802675585284,
|
| 3283 |
+
"grad_norm": 0.7771849036216736,
|
| 3284 |
+
"learning_rate": 0.00017944382647385983,
|
| 3285 |
+
"loss": 3.5191,
|
| 3286 |
+
"step": 468
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 6.254180602006689,
|
| 3290 |
+
"grad_norm": 0.9157488346099854,
|
| 3291 |
+
"learning_rate": 0.00017939933259176864,
|
| 3292 |
+
"loss": 3.5583,
|
| 3293 |
+
"step": 469
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 6.2675585284280935,
|
| 3297 |
+
"grad_norm": 0.9348477721214294,
|
| 3298 |
+
"learning_rate": 0.00017935483870967742,
|
| 3299 |
+
"loss": 3.3137,
|
| 3300 |
+
"step": 470
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 6.280936454849498,
|
| 3304 |
+
"grad_norm": 0.8791135549545288,
|
| 3305 |
+
"learning_rate": 0.0001793103448275862,
|
| 3306 |
+
"loss": 3.5111,
|
| 3307 |
+
"step": 471
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 6.294314381270903,
|
| 3311 |
+
"grad_norm": 0.9963672757148743,
|
| 3312 |
+
"learning_rate": 0.000179265850945495,
|
| 3313 |
+
"loss": 3.7518,
|
| 3314 |
+
"step": 472
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 6.3076923076923075,
|
| 3318 |
+
"grad_norm": 0.9291539192199707,
|
| 3319 |
+
"learning_rate": 0.0001792213570634038,
|
| 3320 |
+
"loss": 3.4524,
|
| 3321 |
+
"step": 473
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 6.321070234113712,
|
| 3325 |
+
"grad_norm": 0.9349279403686523,
|
| 3326 |
+
"learning_rate": 0.00017917686318131258,
|
| 3327 |
+
"loss": 3.4753,
|
| 3328 |
+
"step": 474
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 6.334448160535117,
|
| 3332 |
+
"grad_norm": 0.8984476327896118,
|
| 3333 |
+
"learning_rate": 0.00017913236929922136,
|
| 3334 |
+
"loss": 3.7325,
|
| 3335 |
+
"step": 475
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 6.3478260869565215,
|
| 3339 |
+
"grad_norm": 0.8452139496803284,
|
| 3340 |
+
"learning_rate": 0.00017908787541713015,
|
| 3341 |
+
"loss": 3.8021,
|
| 3342 |
+
"step": 476
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 6.361204013377926,
|
| 3346 |
+
"grad_norm": 0.9418376088142395,
|
| 3347 |
+
"learning_rate": 0.00017904338153503895,
|
| 3348 |
+
"loss": 3.7426,
|
| 3349 |
+
"step": 477
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 6.374581939799331,
|
| 3353 |
+
"grad_norm": 1.0661097764968872,
|
| 3354 |
+
"learning_rate": 0.0001789988876529477,
|
| 3355 |
+
"loss": 3.7556,
|
| 3356 |
+
"step": 478
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 6.3879598662207355,
|
| 3360 |
+
"grad_norm": 0.9645984768867493,
|
| 3361 |
+
"learning_rate": 0.00017895439377085652,
|
| 3362 |
+
"loss": 3.3353,
|
| 3363 |
+
"step": 479
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 6.40133779264214,
|
| 3367 |
+
"grad_norm": 0.9243470430374146,
|
| 3368 |
+
"learning_rate": 0.0001789098998887653,
|
| 3369 |
+
"loss": 3.5729,
|
| 3370 |
+
"step": 480
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 6.414715719063545,
|
| 3374 |
+
"grad_norm": 0.885061502456665,
|
| 3375 |
+
"learning_rate": 0.00017886540600667408,
|
| 3376 |
+
"loss": 3.5699,
|
| 3377 |
+
"step": 481
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 6.4280936454849495,
|
| 3381 |
+
"grad_norm": 0.9025402069091797,
|
| 3382 |
+
"learning_rate": 0.00017882091212458287,
|
| 3383 |
+
"loss": 3.4532,
|
| 3384 |
+
"step": 482
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 6.441471571906354,
|
| 3388 |
+
"grad_norm": 0.9760842323303223,
|
| 3389 |
+
"learning_rate": 0.00017877641824249168,
|
| 3390 |
+
"loss": 3.7222,
|
| 3391 |
+
"step": 483
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 6.454849498327759,
|
| 3395 |
+
"grad_norm": 1.2709609270095825,
|
| 3396 |
+
"learning_rate": 0.00017873192436040046,
|
| 3397 |
+
"loss": 3.756,
|
| 3398 |
+
"step": 484
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 6.468227424749164,
|
| 3402 |
+
"grad_norm": 0.904513955116272,
|
| 3403 |
+
"learning_rate": 0.00017868743047830924,
|
| 3404 |
+
"loss": 3.657,
|
| 3405 |
+
"step": 485
|
| 3406 |
+
},
|
| 3407 |
+
{
|
| 3408 |
+
"epoch": 6.481605351170568,
|
| 3409 |
+
"grad_norm": 1.158915400505066,
|
| 3410 |
+
"learning_rate": 0.00017864293659621802,
|
| 3411 |
+
"loss": 3.5897,
|
| 3412 |
+
"step": 486
|
| 3413 |
+
},
|
| 3414 |
+
{
|
| 3415 |
+
"epoch": 6.494983277591973,
|
| 3416 |
+
"grad_norm": 0.9457879066467285,
|
| 3417 |
+
"learning_rate": 0.00017859844271412683,
|
| 3418 |
+
"loss": 3.4394,
|
| 3419 |
+
"step": 487
|
| 3420 |
+
},
|
| 3421 |
+
{
|
| 3422 |
+
"epoch": 6.508361204013378,
|
| 3423 |
+
"grad_norm": 1.04762601852417,
|
| 3424 |
+
"learning_rate": 0.0001785539488320356,
|
| 3425 |
+
"loss": 3.39,
|
| 3426 |
+
"step": 488
|
| 3427 |
+
},
|
| 3428 |
+
{
|
| 3429 |
+
"epoch": 6.521739130434782,
|
| 3430 |
+
"grad_norm": 0.9370948076248169,
|
| 3431 |
+
"learning_rate": 0.0001785094549499444,
|
| 3432 |
+
"loss": 3.4816,
|
| 3433 |
+
"step": 489
|
| 3434 |
+
},
|
| 3435 |
+
{
|
| 3436 |
+
"epoch": 6.535117056856187,
|
| 3437 |
+
"grad_norm": 1.1307988166809082,
|
| 3438 |
+
"learning_rate": 0.00017846496106785318,
|
| 3439 |
+
"loss": 3.5079,
|
| 3440 |
+
"step": 490
|
| 3441 |
+
},
|
| 3442 |
+
{
|
| 3443 |
+
"epoch": 6.548494983277592,
|
| 3444 |
+
"grad_norm": 1.0025054216384888,
|
| 3445 |
+
"learning_rate": 0.00017842046718576196,
|
| 3446 |
+
"loss": 3.3447,
|
| 3447 |
+
"step": 491
|
| 3448 |
+
},
|
| 3449 |
+
{
|
| 3450 |
+
"epoch": 6.561872909698996,
|
| 3451 |
+
"grad_norm": 0.9893412590026855,
|
| 3452 |
+
"learning_rate": 0.00017837597330367074,
|
| 3453 |
+
"loss": 3.4698,
|
| 3454 |
+
"step": 492
|
| 3455 |
+
},
|
| 3456 |
+
{
|
| 3457 |
+
"epoch": 6.575250836120401,
|
| 3458 |
+
"grad_norm": 1.0476347208023071,
|
| 3459 |
+
"learning_rate": 0.00017833147942157955,
|
| 3460 |
+
"loss": 3.4955,
|
| 3461 |
+
"step": 493
|
| 3462 |
+
},
|
| 3463 |
+
{
|
| 3464 |
+
"epoch": 6.588628762541806,
|
| 3465 |
+
"grad_norm": 1.0508891344070435,
|
| 3466 |
+
"learning_rate": 0.00017828698553948834,
|
| 3467 |
+
"loss": 3.6568,
|
| 3468 |
+
"step": 494
|
| 3469 |
+
},
|
| 3470 |
+
{
|
| 3471 |
+
"epoch": 6.602006688963211,
|
| 3472 |
+
"grad_norm": 1.0397465229034424,
|
| 3473 |
+
"learning_rate": 0.00017824249165739712,
|
| 3474 |
+
"loss": 3.5087,
|
| 3475 |
+
"step": 495
|
| 3476 |
+
},
|
| 3477 |
+
{
|
| 3478 |
+
"epoch": 6.615384615384615,
|
| 3479 |
+
"grad_norm": 0.9884181022644043,
|
| 3480 |
+
"learning_rate": 0.0001781979977753059,
|
| 3481 |
+
"loss": 3.6778,
|
| 3482 |
+
"step": 496
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 6.6287625418060205,
|
| 3486 |
+
"grad_norm": 1.1187562942504883,
|
| 3487 |
+
"learning_rate": 0.0001781535038932147,
|
| 3488 |
+
"loss": 3.4345,
|
| 3489 |
+
"step": 497
|
| 3490 |
+
},
|
| 3491 |
+
{
|
| 3492 |
+
"epoch": 6.642140468227424,
|
| 3493 |
+
"grad_norm": 1.1133880615234375,
|
| 3494 |
+
"learning_rate": 0.00017810901001112347,
|
| 3495 |
+
"loss": 3.4959,
|
| 3496 |
+
"step": 498
|
| 3497 |
+
},
|
| 3498 |
+
{
|
| 3499 |
+
"epoch": 6.65551839464883,
|
| 3500 |
+
"grad_norm": 0.9368589520454407,
|
| 3501 |
+
"learning_rate": 0.00017806451612903228,
|
| 3502 |
+
"loss": 3.628,
|
| 3503 |
+
"step": 499
|
| 3504 |
+
},
|
| 3505 |
+
{
|
| 3506 |
+
"epoch": 6.668896321070234,
|
| 3507 |
+
"grad_norm": 1.0427212715148926,
|
| 3508 |
+
"learning_rate": 0.00017802002224694106,
|
| 3509 |
+
"loss": 3.6073,
|
| 3510 |
+
"step": 500
|
| 3511 |
+
}
|
| 3512 |
+
],
|
| 3513 |
+
"logging_steps": 1,
|
| 3514 |
+
"max_steps": 4500,
|
| 3515 |
+
"num_input_tokens_seen": 0,
|
| 3516 |
+
"num_train_epochs": 60,
|
| 3517 |
+
"save_steps": 500,
|
| 3518 |
+
"stateful_callbacks": {
|
| 3519 |
+
"TrainerControl": {
|
| 3520 |
+
"args": {
|
| 3521 |
+
"should_epoch_stop": false,
|
| 3522 |
+
"should_evaluate": false,
|
| 3523 |
+
"should_log": false,
|
| 3524 |
+
"should_save": true,
|
| 3525 |
+
"should_training_stop": false
|
| 3526 |
+
},
|
| 3527 |
+
"attributes": {}
|
| 3528 |
+
}
|
| 3529 |
+
},
|
| 3530 |
+
"total_flos": 1.54743987923712e+16,
|
| 3531 |
+
"train_batch_size": 4,
|
| 3532 |
+
"trial_name": null,
|
| 3533 |
+
"trial_params": null
|
| 3534 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28567294f409dde284d2f90b22df15721d73c352863bf2ce625e292ccb0f6eaa
|
| 3 |
+
size 5649
|