Training in progress, step 365, checkpoint
Browse files- last-checkpoint/README.md +202 -0
- last-checkpoint/adapter_config.json +30 -0
- last-checkpoint/adapter_model.safetensors +3 -0
- last-checkpoint/added_tokens.json +4 -0
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +30 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +205 -0
- last-checkpoint/trainer_state.json +2604 -0
- last-checkpoint/training_args.bin +3 -0
- last-checkpoint/vocab.json +0 -0
last-checkpoint/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: katuni4ka/tiny-random-dbrx
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.13.2
|
last-checkpoint/adapter_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "katuni4ka/tiny-random-dbrx",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"layer",
|
| 24 |
+
"out_proj",
|
| 25 |
+
"Wqkv"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_dora": false,
|
| 29 |
+
"use_rslora": false
|
| 30 |
+
}
|
last-checkpoint/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb782cbdf99c1a1e902a330bb365a1298c4d159ee62de373e5e828ff27ab9634
|
| 3 |
+
size 5752
|
last-checkpoint/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|im_end|>": 100279,
|
| 3 |
+
"<|im_start|>": 100278
|
| 4 |
+
}
|
last-checkpoint/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f435ce850777e13d0d23fc42025258ccda567de6f2c0b4fe7d7997231c816891
|
| 3 |
+
size 15814
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a5df6564cf48a50ae92cee490ec0d4eed87ac68b09129926b4f67ec9bc9b051
|
| 3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:635160eaaf28a686b3665877a41b33c5d5f3ffb6419262657260d434b3f7650e
|
| 3 |
+
size 1064
|
last-checkpoint/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100256": {
|
| 5 |
+
"content": "<||_unused_0_||>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"100257": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100258": {
|
| 21 |
+
"content": "<|fim_prefix|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100259": {
|
| 29 |
+
"content": "<|fim_middle|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100260": {
|
| 37 |
+
"content": "<|fim_suffix|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100261": {
|
| 45 |
+
"content": "<||_unused_1_||>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"100262": {
|
| 53 |
+
"content": "<||_unused_2_||>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"100263": {
|
| 61 |
+
"content": "<||_unused_3_||>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"100264": {
|
| 69 |
+
"content": "<||_unused_4_||>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"100265": {
|
| 77 |
+
"content": "<||_unused_5_||>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"100266": {
|
| 85 |
+
"content": "<||_unused_6_||>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"100267": {
|
| 93 |
+
"content": "<||_unused_7_||>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"100268": {
|
| 101 |
+
"content": "<||_unused_8_||>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"100269": {
|
| 109 |
+
"content": "<||_unused_9_||>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"100270": {
|
| 117 |
+
"content": "<||_unused_10_||>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"100271": {
|
| 125 |
+
"content": "<||_unused_11_||>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"100272": {
|
| 133 |
+
"content": "<||_unused_12_||>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"100273": {
|
| 141 |
+
"content": "<||_unused_13_||>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"100274": {
|
| 149 |
+
"content": "<||_unused_14_||>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"100275": {
|
| 157 |
+
"content": "<||_unused_15_||>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"100276": {
|
| 165 |
+
"content": "<|endofprompt|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"100277": {
|
| 173 |
+
"content": "<|pad|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"100278": {
|
| 181 |
+
"content": "<|im_start|>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"100279": {
|
| 189 |
+
"content": "<|im_end|>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
}
|
| 196 |
+
},
|
| 197 |
+
"bos_token": "<|endoftext|>",
|
| 198 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 199 |
+
"clean_up_tokenization_spaces": true,
|
| 200 |
+
"eos_token": "<|endoftext|>",
|
| 201 |
+
"model_max_length": 32768,
|
| 202 |
+
"pad_token": "<|pad|>",
|
| 203 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 204 |
+
"unk_token": "<|endoftext|>"
|
| 205 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,2604 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.061595578618740245,
|
| 5 |
+
"eval_steps": 365,
|
| 6 |
+
"global_step": 365,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00016875500991435683,
|
| 13 |
+
"grad_norm": 1.940874608408194e-05,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 46.0,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.00016875500991435683,
|
| 20 |
+
"eval_loss": 11.5,
|
| 21 |
+
"eval_runtime": 14.7961,
|
| 22 |
+
"eval_samples_per_second": 168.625,
|
| 23 |
+
"eval_steps_per_second": 84.346,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00033751001982871366,
|
| 28 |
+
"grad_norm": 1.7339452824671753e-05,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 46.0,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0005062650297430705,
|
| 35 |
+
"grad_norm": 9.871354450297076e-06,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 46.0,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0006750200396574273,
|
| 42 |
+
"grad_norm": 1.9611639800132252e-05,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 46.0,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0008437750495717841,
|
| 49 |
+
"grad_norm": 1.9497307221172377e-05,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 46.0,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.001012530059486141,
|
| 56 |
+
"grad_norm": 1.4163069863570854e-05,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 46.0,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0011812850694004977,
|
| 63 |
+
"grad_norm": 2.7470567147247493e-05,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 46.0,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0013500400793148546,
|
| 70 |
+
"grad_norm": 1.262454861716833e-05,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 46.0,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0015187950892292116,
|
| 77 |
+
"grad_norm": 1.2461353435355704e-05,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 46.0,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0016875500991435683,
|
| 84 |
+
"grad_norm": 1.924686148413457e-05,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 46.0,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0018563051090579252,
|
| 91 |
+
"grad_norm": 1.5145715224207379e-05,
|
| 92 |
+
"learning_rate": 0.0001999997643146886,
|
| 93 |
+
"loss": 46.0,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.002025060118972282,
|
| 98 |
+
"grad_norm": 8.845885531627573e-06,
|
| 99 |
+
"learning_rate": 0.0001999990572598653,
|
| 100 |
+
"loss": 46.0,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0021938151288866388,
|
| 105 |
+
"grad_norm": 1.8190678019891493e-05,
|
| 106 |
+
"learning_rate": 0.00019999787883886297,
|
| 107 |
+
"loss": 46.0,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.0023625701388009955,
|
| 112 |
+
"grad_norm": 1.827279083954636e-05,
|
| 113 |
+
"learning_rate": 0.00019999622905723634,
|
| 114 |
+
"loss": 46.0,
|
| 115 |
+
"step": 14
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.0025313251487153526,
|
| 119 |
+
"grad_norm": 1.6565853002248332e-05,
|
| 120 |
+
"learning_rate": 0.00019999410792276198,
|
| 121 |
+
"loss": 46.0,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.0027000801586297093,
|
| 126 |
+
"grad_norm": 1.0454502444190439e-05,
|
| 127 |
+
"learning_rate": 0.00019999151544543832,
|
| 128 |
+
"loss": 46.0,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.002868835168544066,
|
| 133 |
+
"grad_norm": 1.3837036021868698e-05,
|
| 134 |
+
"learning_rate": 0.00019998845163748553,
|
| 135 |
+
"loss": 46.0,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.003037590178458423,
|
| 140 |
+
"grad_norm": 1.835626426327508e-05,
|
| 141 |
+
"learning_rate": 0.0001999849165133455,
|
| 142 |
+
"loss": 46.0,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.00320634518837278,
|
| 147 |
+
"grad_norm": 1.9169588995282538e-05,
|
| 148 |
+
"learning_rate": 0.00019998091008968175,
|
| 149 |
+
"loss": 46.0,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.0033751001982871365,
|
| 154 |
+
"grad_norm": 9.931905879057012e-06,
|
| 155 |
+
"learning_rate": 0.0001999764323853794,
|
| 156 |
+
"loss": 46.0,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.0035438552082014936,
|
| 161 |
+
"grad_norm": 1.246378269570414e-05,
|
| 162 |
+
"learning_rate": 0.00019997148342154502,
|
| 163 |
+
"loss": 46.0,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.0037126102181158503,
|
| 168 |
+
"grad_norm": 1.627793062652927e-05,
|
| 169 |
+
"learning_rate": 0.0001999660632215066,
|
| 170 |
+
"loss": 46.0,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.003881365228030207,
|
| 175 |
+
"grad_norm": 1.6465271983179264e-05,
|
| 176 |
+
"learning_rate": 0.00019996017181081336,
|
| 177 |
+
"loss": 46.0,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.004050120237944564,
|
| 182 |
+
"grad_norm": 1.4562248907168396e-05,
|
| 183 |
+
"learning_rate": 0.00019995380921723562,
|
| 184 |
+
"loss": 46.0,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.00421887524785892,
|
| 189 |
+
"grad_norm": 1.0674185432435479e-05,
|
| 190 |
+
"learning_rate": 0.00019994697547076487,
|
| 191 |
+
"loss": 46.0,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.0043876302577732776,
|
| 196 |
+
"grad_norm": 1.2923982467327733e-05,
|
| 197 |
+
"learning_rate": 0.00019993967060361335,
|
| 198 |
+
"loss": 46.0,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.004556385267687635,
|
| 203 |
+
"grad_norm": 1.9432607587077655e-05,
|
| 204 |
+
"learning_rate": 0.00019993189465021405,
|
| 205 |
+
"loss": 46.0,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.004725140277601991,
|
| 210 |
+
"grad_norm": 1.4471233043877874e-05,
|
| 211 |
+
"learning_rate": 0.0001999236476472205,
|
| 212 |
+
"loss": 46.0,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.004893895287516348,
|
| 217 |
+
"grad_norm": 2.0513718482106924e-05,
|
| 218 |
+
"learning_rate": 0.0001999149296335067,
|
| 219 |
+
"loss": 46.0,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.005062650297430705,
|
| 224 |
+
"grad_norm": 2.3202137526823208e-05,
|
| 225 |
+
"learning_rate": 0.00019990574065016677,
|
| 226 |
+
"loss": 46.0,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.0052314053073450615,
|
| 231 |
+
"grad_norm": 2.1836229279870167e-05,
|
| 232 |
+
"learning_rate": 0.00019989608074051489,
|
| 233 |
+
"loss": 46.0,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.005400160317259419,
|
| 238 |
+
"grad_norm": 1.5274166798917577e-05,
|
| 239 |
+
"learning_rate": 0.00019988594995008505,
|
| 240 |
+
"loss": 46.0,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.005568915327173776,
|
| 245 |
+
"grad_norm": 1.919052010634914e-05,
|
| 246 |
+
"learning_rate": 0.00019987534832663082,
|
| 247 |
+
"loss": 46.0,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.005737670337088132,
|
| 252 |
+
"grad_norm": 1.5861112842685543e-05,
|
| 253 |
+
"learning_rate": 0.0001998642759201251,
|
| 254 |
+
"loss": 46.0,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.005906425347002489,
|
| 259 |
+
"grad_norm": 1.185925975732971e-05,
|
| 260 |
+
"learning_rate": 0.00019985273278276,
|
| 261 |
+
"loss": 46.0,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.006075180356916846,
|
| 266 |
+
"grad_norm": 1.6194346244446933e-05,
|
| 267 |
+
"learning_rate": 0.00019984071896894646,
|
| 268 |
+
"loss": 46.0,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.0062439353668312025,
|
| 273 |
+
"grad_norm": 1.961121779459063e-05,
|
| 274 |
+
"learning_rate": 0.0001998282345353141,
|
| 275 |
+
"loss": 46.0,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.00641269037674556,
|
| 280 |
+
"grad_norm": 2.1559202650678344e-05,
|
| 281 |
+
"learning_rate": 0.0001998152795407108,
|
| 282 |
+
"loss": 46.0,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.006581445386659917,
|
| 287 |
+
"grad_norm": 2.8157497581560165e-05,
|
| 288 |
+
"learning_rate": 0.00019980185404620268,
|
| 289 |
+
"loss": 46.0,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.006750200396574273,
|
| 294 |
+
"grad_norm": 2.1486024706973694e-05,
|
| 295 |
+
"learning_rate": 0.00019978795811507354,
|
| 296 |
+
"loss": 46.0,
|
| 297 |
+
"step": 40
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.00691895540648863,
|
| 301 |
+
"grad_norm": 2.3358212274615653e-05,
|
| 302 |
+
"learning_rate": 0.00019977359181282473,
|
| 303 |
+
"loss": 46.0,
|
| 304 |
+
"step": 41
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.007087710416402987,
|
| 308 |
+
"grad_norm": 1.6756239347159863e-05,
|
| 309 |
+
"learning_rate": 0.00019975875520717479,
|
| 310 |
+
"loss": 46.0,
|
| 311 |
+
"step": 42
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.0072564654263173435,
|
| 315 |
+
"grad_norm": 1.7175016182591207e-05,
|
| 316 |
+
"learning_rate": 0.00019974344836805905,
|
| 317 |
+
"loss": 46.0,
|
| 318 |
+
"step": 43
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.007425220436231701,
|
| 322 |
+
"grad_norm": 1.2200899618619587e-05,
|
| 323 |
+
"learning_rate": 0.00019972767136762953,
|
| 324 |
+
"loss": 46.0,
|
| 325 |
+
"step": 44
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.007593975446146058,
|
| 329 |
+
"grad_norm": 1.7348913388559595e-05,
|
| 330 |
+
"learning_rate": 0.00019971142428025433,
|
| 331 |
+
"loss": 46.0,
|
| 332 |
+
"step": 45
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.007762730456060414,
|
| 336 |
+
"grad_norm": 9.565149412082974e-06,
|
| 337 |
+
"learning_rate": 0.00019969470718251748,
|
| 338 |
+
"loss": 46.0,
|
| 339 |
+
"step": 46
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.007931485465974771,
|
| 343 |
+
"grad_norm": 1.5444033124367706e-05,
|
| 344 |
+
"learning_rate": 0.00019967752015321845,
|
| 345 |
+
"loss": 46.0,
|
| 346 |
+
"step": 47
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.008100240475889128,
|
| 350 |
+
"grad_norm": 1.9607326976256445e-05,
|
| 351 |
+
"learning_rate": 0.00019965986327337185,
|
| 352 |
+
"loss": 46.0,
|
| 353 |
+
"step": 48
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.008268995485803485,
|
| 357 |
+
"grad_norm": 1.6280893760267645e-05,
|
| 358 |
+
"learning_rate": 0.00019964173662620702,
|
| 359 |
+
"loss": 46.0,
|
| 360 |
+
"step": 49
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.00843775049571784,
|
| 364 |
+
"grad_norm": 2.2253505449043587e-05,
|
| 365 |
+
"learning_rate": 0.00019962314029716766,
|
| 366 |
+
"loss": 46.0,
|
| 367 |
+
"step": 50
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.008606505505632198,
|
| 371 |
+
"grad_norm": 1.3872278032067697e-05,
|
| 372 |
+
"learning_rate": 0.0001996040743739114,
|
| 373 |
+
"loss": 46.0,
|
| 374 |
+
"step": 51
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.008775260515546555,
|
| 378 |
+
"grad_norm": 3.644825119408779e-05,
|
| 379 |
+
"learning_rate": 0.0001995845389463094,
|
| 380 |
+
"loss": 46.0,
|
| 381 |
+
"step": 52
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.008944015525460912,
|
| 385 |
+
"grad_norm": 1.858348332461901e-05,
|
| 386 |
+
"learning_rate": 0.00019956453410644592,
|
| 387 |
+
"loss": 46.0,
|
| 388 |
+
"step": 53
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.00911277053537527,
|
| 392 |
+
"grad_norm": 1.7900563761941157e-05,
|
| 393 |
+
"learning_rate": 0.0001995440599486179,
|
| 394 |
+
"loss": 46.0,
|
| 395 |
+
"step": 54
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.009281525545289626,
|
| 399 |
+
"grad_norm": 4.377702498459257e-05,
|
| 400 |
+
"learning_rate": 0.0001995231165693345,
|
| 401 |
+
"loss": 46.0,
|
| 402 |
+
"step": 55
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.009450280555203982,
|
| 406 |
+
"grad_norm": 2.3857590349507518e-05,
|
| 407 |
+
"learning_rate": 0.00019950170406731667,
|
| 408 |
+
"loss": 46.0,
|
| 409 |
+
"step": 56
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.009619035565118339,
|
| 413 |
+
"grad_norm": 1.2674429854087066e-05,
|
| 414 |
+
"learning_rate": 0.00019947982254349666,
|
| 415 |
+
"loss": 46.0,
|
| 416 |
+
"step": 57
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.009787790575032696,
|
| 420 |
+
"grad_norm": 2.890539326472208e-05,
|
| 421 |
+
"learning_rate": 0.00019945747210101754,
|
| 422 |
+
"loss": 46.0,
|
| 423 |
+
"step": 58
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.009956545584947053,
|
| 427 |
+
"grad_norm": 1.9787186829489656e-05,
|
| 428 |
+
"learning_rate": 0.0001994346528452327,
|
| 429 |
+
"loss": 46.0,
|
| 430 |
+
"step": 59
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.01012530059486141,
|
| 434 |
+
"grad_norm": 2.427671461191494e-05,
|
| 435 |
+
"learning_rate": 0.00019941136488370542,
|
| 436 |
+
"loss": 46.0,
|
| 437 |
+
"step": 60
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.010294055604775768,
|
| 441 |
+
"grad_norm": 1.2431184586603194e-05,
|
| 442 |
+
"learning_rate": 0.00019938760832620834,
|
| 443 |
+
"loss": 46.0,
|
| 444 |
+
"step": 61
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.010462810614690123,
|
| 448 |
+
"grad_norm": 2.0812987713725306e-05,
|
| 449 |
+
"learning_rate": 0.00019936338328472287,
|
| 450 |
+
"loss": 46.0,
|
| 451 |
+
"step": 62
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.01063156562460448,
|
| 455 |
+
"grad_norm": 2.8024591301800683e-05,
|
| 456 |
+
"learning_rate": 0.00019933868987343875,
|
| 457 |
+
"loss": 46.0,
|
| 458 |
+
"step": 63
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.010800320634518837,
|
| 462 |
+
"grad_norm": 2.2569249267689884e-05,
|
| 463 |
+
"learning_rate": 0.0001993135282087535,
|
| 464 |
+
"loss": 46.0,
|
| 465 |
+
"step": 64
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.010969075644433194,
|
| 469 |
+
"grad_norm": 1.9383338440093212e-05,
|
| 470 |
+
"learning_rate": 0.0001992878984092717,
|
| 471 |
+
"loss": 46.0,
|
| 472 |
+
"step": 65
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.011137830654347551,
|
| 476 |
+
"grad_norm": 2.542112815717701e-05,
|
| 477 |
+
"learning_rate": 0.00019926180059580482,
|
| 478 |
+
"loss": 46.0,
|
| 479 |
+
"step": 66
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.011306585664261909,
|
| 483 |
+
"grad_norm": 1.598012568138074e-05,
|
| 484 |
+
"learning_rate": 0.00019923523489137024,
|
| 485 |
+
"loss": 46.0,
|
| 486 |
+
"step": 67
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.011475340674176264,
|
| 490 |
+
"grad_norm": 1.4789104170631617e-05,
|
| 491 |
+
"learning_rate": 0.00019920820142119085,
|
| 492 |
+
"loss": 46.0,
|
| 493 |
+
"step": 68
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.011644095684090621,
|
| 497 |
+
"grad_norm": 1.9799528672592714e-05,
|
| 498 |
+
"learning_rate": 0.00019918070031269453,
|
| 499 |
+
"loss": 46.0,
|
| 500 |
+
"step": 69
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.011812850694004978,
|
| 504 |
+
"grad_norm": 3.249241126468405e-05,
|
| 505 |
+
"learning_rate": 0.00019915273169551342,
|
| 506 |
+
"loss": 46.0,
|
| 507 |
+
"step": 70
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.011981605703919335,
|
| 511 |
+
"grad_norm": 2.287813367729541e-05,
|
| 512 |
+
"learning_rate": 0.00019912429570148339,
|
| 513 |
+
"loss": 46.0,
|
| 514 |
+
"step": 71
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.012150360713833692,
|
| 518 |
+
"grad_norm": 3.186216781614348e-05,
|
| 519 |
+
"learning_rate": 0.0001990953924646433,
|
| 520 |
+
"loss": 46.0,
|
| 521 |
+
"step": 72
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.01231911572374805,
|
| 525 |
+
"grad_norm": 4.087354682269506e-05,
|
| 526 |
+
"learning_rate": 0.00019906602212123455,
|
| 527 |
+
"loss": 46.0,
|
| 528 |
+
"step": 73
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.012487870733662405,
|
| 532 |
+
"grad_norm": 2.5896191800711676e-05,
|
| 533 |
+
"learning_rate": 0.00019903618480970035,
|
| 534 |
+
"loss": 46.0,
|
| 535 |
+
"step": 74
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.012656625743576762,
|
| 539 |
+
"grad_norm": 2.6261466700816527e-05,
|
| 540 |
+
"learning_rate": 0.00019900588067068493,
|
| 541 |
+
"loss": 46.0,
|
| 542 |
+
"step": 75
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.01282538075349112,
|
| 546 |
+
"grad_norm": 1.815898940549232e-05,
|
| 547 |
+
"learning_rate": 0.0001989751098470332,
|
| 548 |
+
"loss": 46.0,
|
| 549 |
+
"step": 76
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.012994135763405476,
|
| 553 |
+
"grad_norm": 1.682456240814645e-05,
|
| 554 |
+
"learning_rate": 0.0001989438724837897,
|
| 555 |
+
"loss": 46.0,
|
| 556 |
+
"step": 77
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.013162890773319834,
|
| 560 |
+
"grad_norm": 2.581811168056447e-05,
|
| 561 |
+
"learning_rate": 0.00019891216872819825,
|
| 562 |
+
"loss": 46.0,
|
| 563 |
+
"step": 78
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.013331645783234189,
|
| 567 |
+
"grad_norm": 3.8674785173498094e-05,
|
| 568 |
+
"learning_rate": 0.00019887999872970097,
|
| 569 |
+
"loss": 46.0,
|
| 570 |
+
"step": 79
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.013500400793148546,
|
| 574 |
+
"grad_norm": 3.877016933984123e-05,
|
| 575 |
+
"learning_rate": 0.00019884736263993784,
|
| 576 |
+
"loss": 46.0,
|
| 577 |
+
"step": 80
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.013669155803062903,
|
| 581 |
+
"grad_norm": 1.5791521946084686e-05,
|
| 582 |
+
"learning_rate": 0.0001988142606127458,
|
| 583 |
+
"loss": 46.0,
|
| 584 |
+
"step": 81
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.01383791081297726,
|
| 588 |
+
"grad_norm": 2.4946857593022287e-05,
|
| 589 |
+
"learning_rate": 0.00019878069280415803,
|
| 590 |
+
"loss": 46.0,
|
| 591 |
+
"step": 82
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.014006665822891617,
|
| 595 |
+
"grad_norm": 4.878333129454404e-05,
|
| 596 |
+
"learning_rate": 0.00019874665937240335,
|
| 597 |
+
"loss": 46.0,
|
| 598 |
+
"step": 83
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.014175420832805975,
|
| 602 |
+
"grad_norm": 2.5513558284728788e-05,
|
| 603 |
+
"learning_rate": 0.00019871216047790538,
|
| 604 |
+
"loss": 46.0,
|
| 605 |
+
"step": 84
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.01434417584272033,
|
| 609 |
+
"grad_norm": 5.085681550554e-05,
|
| 610 |
+
"learning_rate": 0.00019867719628328175,
|
| 611 |
+
"loss": 46.0,
|
| 612 |
+
"step": 85
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.014512930852634687,
|
| 616 |
+
"grad_norm": 4.014965088572353e-05,
|
| 617 |
+
"learning_rate": 0.0001986417669533434,
|
| 618 |
+
"loss": 46.0,
|
| 619 |
+
"step": 86
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.014681685862549044,
|
| 623 |
+
"grad_norm": 2.0565448721754365e-05,
|
| 624 |
+
"learning_rate": 0.0001986058726550938,
|
| 625 |
+
"loss": 46.0,
|
| 626 |
+
"step": 87
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.014850440872463401,
|
| 630 |
+
"grad_norm": 4.422978236107156e-05,
|
| 631 |
+
"learning_rate": 0.00019856951355772814,
|
| 632 |
+
"loss": 46.0,
|
| 633 |
+
"step": 88
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.015019195882377758,
|
| 637 |
+
"grad_norm": 2.699590550037101e-05,
|
| 638 |
+
"learning_rate": 0.00019853268983263244,
|
| 639 |
+
"loss": 46.0,
|
| 640 |
+
"step": 89
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.015187950892292116,
|
| 644 |
+
"grad_norm": 1.274027908948483e-05,
|
| 645 |
+
"learning_rate": 0.000198495401653383,
|
| 646 |
+
"loss": 46.0,
|
| 647 |
+
"step": 90
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.015356705902206471,
|
| 651 |
+
"grad_norm": 4.096307384315878e-05,
|
| 652 |
+
"learning_rate": 0.00019845764919574537,
|
| 653 |
+
"loss": 46.0,
|
| 654 |
+
"step": 91
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.015525460912120828,
|
| 658 |
+
"grad_norm": 3.1611998565495014e-05,
|
| 659 |
+
"learning_rate": 0.00019841943263767346,
|
| 660 |
+
"loss": 46.0,
|
| 661 |
+
"step": 92
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.015694215922035185,
|
| 665 |
+
"grad_norm": 2.0112831407459453e-05,
|
| 666 |
+
"learning_rate": 0.00019838075215930894,
|
| 667 |
+
"loss": 46.0,
|
| 668 |
+
"step": 93
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.015862970931949542,
|
| 672 |
+
"grad_norm": 6.471107190009207e-05,
|
| 673 |
+
"learning_rate": 0.00019834160794298024,
|
| 674 |
+
"loss": 46.0,
|
| 675 |
+
"step": 94
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.0160317259418639,
|
| 679 |
+
"grad_norm": 3.331500920467079e-05,
|
| 680 |
+
"learning_rate": 0.00019830200017320168,
|
| 681 |
+
"loss": 46.0,
|
| 682 |
+
"step": 95
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.016200480951778257,
|
| 686 |
+
"grad_norm": 3.4283220884390175e-05,
|
| 687 |
+
"learning_rate": 0.0001982619290366726,
|
| 688 |
+
"loss": 46.0,
|
| 689 |
+
"step": 96
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.016369235961692614,
|
| 693 |
+
"grad_norm": 4.784906195709482e-05,
|
| 694 |
+
"learning_rate": 0.00019822139472227665,
|
| 695 |
+
"loss": 46.0,
|
| 696 |
+
"step": 97
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.01653799097160697,
|
| 700 |
+
"grad_norm": 4.9155318265547976e-05,
|
| 701 |
+
"learning_rate": 0.00019818039742108064,
|
| 702 |
+
"loss": 46.0,
|
| 703 |
+
"step": 98
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.016706745981521328,
|
| 707 |
+
"grad_norm": 4.837827509618364e-05,
|
| 708 |
+
"learning_rate": 0.00019813893732633378,
|
| 709 |
+
"loss": 46.0,
|
| 710 |
+
"step": 99
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.01687550099143568,
|
| 714 |
+
"grad_norm": 4.3958363676210865e-05,
|
| 715 |
+
"learning_rate": 0.00019809701463346683,
|
| 716 |
+
"loss": 46.0,
|
| 717 |
+
"step": 100
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.01704425600135004,
|
| 721 |
+
"grad_norm": 5.13470804435201e-05,
|
| 722 |
+
"learning_rate": 0.000198054629540091,
|
| 723 |
+
"loss": 46.0,
|
| 724 |
+
"step": 101
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.017213011011264396,
|
| 728 |
+
"grad_norm": 3.207432382623665e-05,
|
| 729 |
+
"learning_rate": 0.00019801178224599722,
|
| 730 |
+
"loss": 46.0,
|
| 731 |
+
"step": 102
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.017381766021178753,
|
| 735 |
+
"grad_norm": 3.24075881508179e-05,
|
| 736 |
+
"learning_rate": 0.00019796847295315502,
|
| 737 |
+
"loss": 46.0,
|
| 738 |
+
"step": 103
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.01755052103109311,
|
| 742 |
+
"grad_norm": 5.3687395848101005e-05,
|
| 743 |
+
"learning_rate": 0.00019792470186571167,
|
| 744 |
+
"loss": 46.0,
|
| 745 |
+
"step": 104
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.017719276041007467,
|
| 749 |
+
"grad_norm": 2.9774340873700567e-05,
|
| 750 |
+
"learning_rate": 0.00019788046918999122,
|
| 751 |
+
"loss": 46.0,
|
| 752 |
+
"step": 105
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.017888031050921824,
|
| 756 |
+
"grad_norm": 7.565080159110948e-05,
|
| 757 |
+
"learning_rate": 0.00019783577513449353,
|
| 758 |
+
"loss": 46.0,
|
| 759 |
+
"step": 106
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.01805678606083618,
|
| 763 |
+
"grad_norm": 5.2741965191671625e-05,
|
| 764 |
+
"learning_rate": 0.0001977906199098932,
|
| 765 |
+
"loss": 46.0,
|
| 766 |
+
"step": 107
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.01822554107075054,
|
| 770 |
+
"grad_norm": 3.216122786398046e-05,
|
| 771 |
+
"learning_rate": 0.0001977450037290388,
|
| 772 |
+
"loss": 46.0,
|
| 773 |
+
"step": 108
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.018394296080664896,
|
| 777 |
+
"grad_norm": 5.457305451272987e-05,
|
| 778 |
+
"learning_rate": 0.00019769892680695147,
|
| 779 |
+
"loss": 46.0,
|
| 780 |
+
"step": 109
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.018563051090579253,
|
| 784 |
+
"grad_norm": 3.489471419015899e-05,
|
| 785 |
+
"learning_rate": 0.00019765238936082438,
|
| 786 |
+
"loss": 46.0,
|
| 787 |
+
"step": 110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.01873180610049361,
|
| 791 |
+
"grad_norm": 1.886937752715312e-05,
|
| 792 |
+
"learning_rate": 0.00019760539161002135,
|
| 793 |
+
"loss": 46.0,
|
| 794 |
+
"step": 111
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.018900561110407964,
|
| 798 |
+
"grad_norm": 3.381875285413116e-05,
|
| 799 |
+
"learning_rate": 0.00019755793377607597,
|
| 800 |
+
"loss": 46.0,
|
| 801 |
+
"step": 112
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.01906931612032232,
|
| 805 |
+
"grad_norm": 3.3628173696342856e-05,
|
| 806 |
+
"learning_rate": 0.00019751001608269052,
|
| 807 |
+
"loss": 46.0,
|
| 808 |
+
"step": 113
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.019238071130236678,
|
| 812 |
+
"grad_norm": 5.391196464188397e-05,
|
| 813 |
+
"learning_rate": 0.00019746163875573492,
|
| 814 |
+
"loss": 46.0,
|
| 815 |
+
"step": 114
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.019406826140151035,
|
| 819 |
+
"grad_norm": 4.308508141548373e-05,
|
| 820 |
+
"learning_rate": 0.0001974128020232457,
|
| 821 |
+
"loss": 46.0,
|
| 822 |
+
"step": 115
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.019575581150065392,
|
| 826 |
+
"grad_norm": 0.00010606838623061776,
|
| 827 |
+
"learning_rate": 0.00019736350611542487,
|
| 828 |
+
"loss": 46.0,
|
| 829 |
+
"step": 116
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.01974433615997975,
|
| 833 |
+
"grad_norm": 4.744268153444864e-05,
|
| 834 |
+
"learning_rate": 0.00019731375126463886,
|
| 835 |
+
"loss": 46.0,
|
| 836 |
+
"step": 117
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.019913091169894107,
|
| 840 |
+
"grad_norm": 3.2672236557118595e-05,
|
| 841 |
+
"learning_rate": 0.00019726353770541742,
|
| 842 |
+
"loss": 46.0,
|
| 843 |
+
"step": 118
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.020081846179808464,
|
| 847 |
+
"grad_norm": 1.8585633370094e-05,
|
| 848 |
+
"learning_rate": 0.0001972128656744525,
|
| 849 |
+
"loss": 46.0,
|
| 850 |
+
"step": 119
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.02025060118972282,
|
| 854 |
+
"grad_norm": 3.3655844163149595e-05,
|
| 855 |
+
"learning_rate": 0.0001971617354105972,
|
| 856 |
+
"loss": 46.0,
|
| 857 |
+
"step": 120
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.020419356199637178,
|
| 861 |
+
"grad_norm": 4.9799295084085315e-05,
|
| 862 |
+
"learning_rate": 0.00019711014715486448,
|
| 863 |
+
"loss": 46.0,
|
| 864 |
+
"step": 121
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.020588111209551535,
|
| 868 |
+
"grad_norm": 7.914419256849214e-05,
|
| 869 |
+
"learning_rate": 0.00019705810115042634,
|
| 870 |
+
"loss": 46.0,
|
| 871 |
+
"step": 122
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.02075686621946589,
|
| 875 |
+
"grad_norm": 4.802920011570677e-05,
|
| 876 |
+
"learning_rate": 0.00019700559764261225,
|
| 877 |
+
"loss": 46.0,
|
| 878 |
+
"step": 123
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.020925621229380246,
|
| 882 |
+
"grad_norm": 3.76962598238606e-05,
|
| 883 |
+
"learning_rate": 0.0001969526368789084,
|
| 884 |
+
"loss": 46.0,
|
| 885 |
+
"step": 124
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.021094376239294603,
|
| 889 |
+
"grad_norm": 3.57206336047966e-05,
|
| 890 |
+
"learning_rate": 0.00019689921910895627,
|
| 891 |
+
"loss": 46.0,
|
| 892 |
+
"step": 125
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.02126313124920896,
|
| 896 |
+
"grad_norm": 0.0001358168519800529,
|
| 897 |
+
"learning_rate": 0.00019684534458455145,
|
| 898 |
+
"loss": 46.0,
|
| 899 |
+
"step": 126
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.021431886259123317,
|
| 903 |
+
"grad_norm": 3.319705865578726e-05,
|
| 904 |
+
"learning_rate": 0.0001967910135596427,
|
| 905 |
+
"loss": 46.0,
|
| 906 |
+
"step": 127
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.021600641269037674,
|
| 910 |
+
"grad_norm": 9.154703002423048e-05,
|
| 911 |
+
"learning_rate": 0.0001967362262903305,
|
| 912 |
+
"loss": 46.0,
|
| 913 |
+
"step": 128
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.02176939627895203,
|
| 917 |
+
"grad_norm": 0.00012708237045444548,
|
| 918 |
+
"learning_rate": 0.00019668098303486593,
|
| 919 |
+
"loss": 46.0,
|
| 920 |
+
"step": 129
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.02193815128886639,
|
| 924 |
+
"grad_norm": 5.1937749958597124e-05,
|
| 925 |
+
"learning_rate": 0.00019662528405364947,
|
| 926 |
+
"loss": 46.0,
|
| 927 |
+
"step": 130
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.022106906298780746,
|
| 931 |
+
"grad_norm": 6.14839227637276e-05,
|
| 932 |
+
"learning_rate": 0.00019656912960922974,
|
| 933 |
+
"loss": 46.0,
|
| 934 |
+
"step": 131
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.022275661308695103,
|
| 938 |
+
"grad_norm": 5.0448226829757914e-05,
|
| 939 |
+
"learning_rate": 0.0001965125199663023,
|
| 940 |
+
"loss": 46.0,
|
| 941 |
+
"step": 132
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.02244441631860946,
|
| 945 |
+
"grad_norm": 0.00013035547453910112,
|
| 946 |
+
"learning_rate": 0.0001964554553917084,
|
| 947 |
+
"loss": 46.0,
|
| 948 |
+
"step": 133
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.022613171328523817,
|
| 952 |
+
"grad_norm": 5.22616392117925e-05,
|
| 953 |
+
"learning_rate": 0.00019639793615443366,
|
| 954 |
+
"loss": 46.0,
|
| 955 |
+
"step": 134
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.02278192633843817,
|
| 959 |
+
"grad_norm": 7.795252167852595e-05,
|
| 960 |
+
"learning_rate": 0.00019633996252560687,
|
| 961 |
+
"loss": 46.0,
|
| 962 |
+
"step": 135
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.022950681348352528,
|
| 966 |
+
"grad_norm": 0.0001024070952553302,
|
| 967 |
+
"learning_rate": 0.00019628153477849867,
|
| 968 |
+
"loss": 46.0,
|
| 969 |
+
"step": 136
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.023119436358266885,
|
| 973 |
+
"grad_norm": 6.724517152179033e-05,
|
| 974 |
+
"learning_rate": 0.00019622265318852033,
|
| 975 |
+
"loss": 46.0,
|
| 976 |
+
"step": 137
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.023288191368181242,
|
| 980 |
+
"grad_norm": 6.319572275970131e-05,
|
| 981 |
+
"learning_rate": 0.00019616331803322236,
|
| 982 |
+
"loss": 46.0,
|
| 983 |
+
"step": 138
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.0234569463780956,
|
| 987 |
+
"grad_norm": 6.086541907279752e-05,
|
| 988 |
+
"learning_rate": 0.0001961035295922932,
|
| 989 |
+
"loss": 46.0,
|
| 990 |
+
"step": 139
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.023625701388009956,
|
| 994 |
+
"grad_norm": 5.147139745531604e-05,
|
| 995 |
+
"learning_rate": 0.00019604328814755808,
|
| 996 |
+
"loss": 46.0,
|
| 997 |
+
"step": 140
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.023794456397924314,
|
| 1001 |
+
"grad_norm": 6.334174395306036e-05,
|
| 1002 |
+
"learning_rate": 0.0001959825939829774,
|
| 1003 |
+
"loss": 46.0,
|
| 1004 |
+
"step": 141
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.02396321140783867,
|
| 1008 |
+
"grad_norm": 8.245484787039459e-05,
|
| 1009 |
+
"learning_rate": 0.00019592144738464566,
|
| 1010 |
+
"loss": 46.0,
|
| 1011 |
+
"step": 142
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.024131966417753028,
|
| 1015 |
+
"grad_norm": 3.768013630178757e-05,
|
| 1016 |
+
"learning_rate": 0.00019585984864078996,
|
| 1017 |
+
"loss": 46.0,
|
| 1018 |
+
"step": 143
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.024300721427667385,
|
| 1022 |
+
"grad_norm": 5.31747609784361e-05,
|
| 1023 |
+
"learning_rate": 0.0001957977980417687,
|
| 1024 |
+
"loss": 46.0,
|
| 1025 |
+
"step": 144
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.024469476437581742,
|
| 1029 |
+
"grad_norm": 6.340059917420149e-05,
|
| 1030 |
+
"learning_rate": 0.00019573529588007011,
|
| 1031 |
+
"loss": 46.0,
|
| 1032 |
+
"step": 145
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.0246382314474961,
|
| 1036 |
+
"grad_norm": 8.484098361805081e-05,
|
| 1037 |
+
"learning_rate": 0.00019567234245031106,
|
| 1038 |
+
"loss": 46.0,
|
| 1039 |
+
"step": 146
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.024806986457410453,
|
| 1043 |
+
"grad_norm": 7.689618360018358e-05,
|
| 1044 |
+
"learning_rate": 0.00019560893804923554,
|
| 1045 |
+
"loss": 46.0,
|
| 1046 |
+
"step": 147
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.02497574146732481,
|
| 1050 |
+
"grad_norm": 6.701362144667655e-05,
|
| 1051 |
+
"learning_rate": 0.00019554508297571328,
|
| 1052 |
+
"loss": 46.0,
|
| 1053 |
+
"step": 148
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.025144496477239167,
|
| 1057 |
+
"grad_norm": 4.832363629247993e-05,
|
| 1058 |
+
"learning_rate": 0.00019548077753073827,
|
| 1059 |
+
"loss": 46.0,
|
| 1060 |
+
"step": 149
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.025313251487153524,
|
| 1064 |
+
"grad_norm": 0.00010464687511557713,
|
| 1065 |
+
"learning_rate": 0.00019541602201742755,
|
| 1066 |
+
"loss": 46.0,
|
| 1067 |
+
"step": 150
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.02548200649706788,
|
| 1071 |
+
"grad_norm": 5.5594293371541426e-05,
|
| 1072 |
+
"learning_rate": 0.00019535081674101955,
|
| 1073 |
+
"loss": 46.0,
|
| 1074 |
+
"step": 151
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.02565076150698224,
|
| 1078 |
+
"grad_norm": 0.00010436464071972296,
|
| 1079 |
+
"learning_rate": 0.0001952851620088728,
|
| 1080 |
+
"loss": 46.0,
|
| 1081 |
+
"step": 152
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.025819516516896596,
|
| 1085 |
+
"grad_norm": 7.730885408818722e-05,
|
| 1086 |
+
"learning_rate": 0.00019521905813046445,
|
| 1087 |
+
"loss": 46.0,
|
| 1088 |
+
"step": 153
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.025988271526810953,
|
| 1092 |
+
"grad_norm": 0.0002586382324807346,
|
| 1093 |
+
"learning_rate": 0.00019515250541738872,
|
| 1094 |
+
"loss": 46.0,
|
| 1095 |
+
"step": 154
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.02615702653672531,
|
| 1099 |
+
"grad_norm": 5.2660256187664345e-05,
|
| 1100 |
+
"learning_rate": 0.00019508550418335555,
|
| 1101 |
+
"loss": 46.0,
|
| 1102 |
+
"step": 155
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.026325781546639667,
|
| 1106 |
+
"grad_norm": 6.58825520076789e-05,
|
| 1107 |
+
"learning_rate": 0.00019501805474418912,
|
| 1108 |
+
"loss": 46.0,
|
| 1109 |
+
"step": 156
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.026494536556554024,
|
| 1113 |
+
"grad_norm": 9.116072760662064e-05,
|
| 1114 |
+
"learning_rate": 0.00019495015741782622,
|
| 1115 |
+
"loss": 46.0,
|
| 1116 |
+
"step": 157
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.026663291566468378,
|
| 1120 |
+
"grad_norm": 0.00010203113924944773,
|
| 1121 |
+
"learning_rate": 0.00019488181252431489,
|
| 1122 |
+
"loss": 46.0,
|
| 1123 |
+
"step": 158
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.026832046576382735,
|
| 1127 |
+
"grad_norm": 9.367840539198369e-05,
|
| 1128 |
+
"learning_rate": 0.00019481302038581294,
|
| 1129 |
+
"loss": 46.0,
|
| 1130 |
+
"step": 159
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.027000801586297092,
|
| 1134 |
+
"grad_norm": 5.867075742571615e-05,
|
| 1135 |
+
"learning_rate": 0.00019474378132658626,
|
| 1136 |
+
"loss": 46.0,
|
| 1137 |
+
"step": 160
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.02716955659621145,
|
| 1141 |
+
"grad_norm": 0.0001331541279796511,
|
| 1142 |
+
"learning_rate": 0.00019467409567300745,
|
| 1143 |
+
"loss": 46.0,
|
| 1144 |
+
"step": 161
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.027338311606125806,
|
| 1148 |
+
"grad_norm": 9.494357800576836e-05,
|
| 1149 |
+
"learning_rate": 0.0001946039637535542,
|
| 1150 |
+
"loss": 46.0,
|
| 1151 |
+
"step": 162
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.027507066616040163,
|
| 1155 |
+
"grad_norm": 0.00018060464935842901,
|
| 1156 |
+
"learning_rate": 0.0001945333858988078,
|
| 1157 |
+
"loss": 46.0,
|
| 1158 |
+
"step": 163
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.02767582162595452,
|
| 1162 |
+
"grad_norm": 9.109014354180545e-05,
|
| 1163 |
+
"learning_rate": 0.0001944623624414515,
|
| 1164 |
+
"loss": 46.0,
|
| 1165 |
+
"step": 164
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.027844576635868878,
|
| 1169 |
+
"grad_norm": 0.00021458794071804732,
|
| 1170 |
+
"learning_rate": 0.00019439089371626903,
|
| 1171 |
+
"loss": 46.0,
|
| 1172 |
+
"step": 165
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.028013331645783235,
|
| 1176 |
+
"grad_norm": 0.00023161491844803095,
|
| 1177 |
+
"learning_rate": 0.0001943189800601429,
|
| 1178 |
+
"loss": 46.0,
|
| 1179 |
+
"step": 166
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.028182086655697592,
|
| 1183 |
+
"grad_norm": 0.0001091673257178627,
|
| 1184 |
+
"learning_rate": 0.00019424662181205307,
|
| 1185 |
+
"loss": 46.0,
|
| 1186 |
+
"step": 167
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.02835084166561195,
|
| 1190 |
+
"grad_norm": 9.839528502197936e-05,
|
| 1191 |
+
"learning_rate": 0.00019417381931307497,
|
| 1192 |
+
"loss": 46.0,
|
| 1193 |
+
"step": 168
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.028519596675526306,
|
| 1197 |
+
"grad_norm": 0.0001077549095498398,
|
| 1198 |
+
"learning_rate": 0.00019410057290637824,
|
| 1199 |
+
"loss": 46.0,
|
| 1200 |
+
"step": 169
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.02868835168544066,
|
| 1204 |
+
"grad_norm": 0.00011080451076850295,
|
| 1205 |
+
"learning_rate": 0.0001940268829372249,
|
| 1206 |
+
"loss": 46.0,
|
| 1207 |
+
"step": 170
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.028857106695355017,
|
| 1211 |
+
"grad_norm": 0.00010105837282026187,
|
| 1212 |
+
"learning_rate": 0.00019395274975296786,
|
| 1213 |
+
"loss": 46.0,
|
| 1214 |
+
"step": 171
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.029025861705269374,
|
| 1218 |
+
"grad_norm": 0.00012236724433023483,
|
| 1219 |
+
"learning_rate": 0.0001938781737030491,
|
| 1220 |
+
"loss": 46.0,
|
| 1221 |
+
"step": 172
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.02919461671518373,
|
| 1225 |
+
"grad_norm": 8.416602213401347e-05,
|
| 1226 |
+
"learning_rate": 0.00019380315513899826,
|
| 1227 |
+
"loss": 46.0,
|
| 1228 |
+
"step": 173
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.02936337172509809,
|
| 1232 |
+
"grad_norm": 0.00017547875177115202,
|
| 1233 |
+
"learning_rate": 0.00019372769441443083,
|
| 1234 |
+
"loss": 46.0,
|
| 1235 |
+
"step": 174
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.029532126735012446,
|
| 1239 |
+
"grad_norm": 0.00010037582251243293,
|
| 1240 |
+
"learning_rate": 0.00019365179188504647,
|
| 1241 |
+
"loss": 46.0,
|
| 1242 |
+
"step": 175
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.029700881744926803,
|
| 1246 |
+
"grad_norm": 0.0001204924556077458,
|
| 1247 |
+
"learning_rate": 0.0001935754479086274,
|
| 1248 |
+
"loss": 46.0,
|
| 1249 |
+
"step": 176
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.02986963675484116,
|
| 1253 |
+
"grad_norm": 0.00014140504936221987,
|
| 1254 |
+
"learning_rate": 0.00019349866284503674,
|
| 1255 |
+
"loss": 46.0,
|
| 1256 |
+
"step": 177
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.030038391764755517,
|
| 1260 |
+
"grad_norm": 9.342600969830528e-05,
|
| 1261 |
+
"learning_rate": 0.00019342143705621662,
|
| 1262 |
+
"loss": 46.0,
|
| 1263 |
+
"step": 178
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.030207146774669874,
|
| 1267 |
+
"grad_norm": 4.463369259610772e-05,
|
| 1268 |
+
"learning_rate": 0.00019334377090618682,
|
| 1269 |
+
"loss": 46.0,
|
| 1270 |
+
"step": 179
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.03037590178458423,
|
| 1274 |
+
"grad_norm": 8.116533717839047e-05,
|
| 1275 |
+
"learning_rate": 0.00019326566476104274,
|
| 1276 |
+
"loss": 46.0,
|
| 1277 |
+
"step": 180
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.03054465679449859,
|
| 1281 |
+
"grad_norm": 0.00013790494995191693,
|
| 1282 |
+
"learning_rate": 0.00019318711898895377,
|
| 1283 |
+
"loss": 46.0,
|
| 1284 |
+
"step": 181
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.030713411804412942,
|
| 1288 |
+
"grad_norm": 0.0002199001028202474,
|
| 1289 |
+
"learning_rate": 0.00019310813396016162,
|
| 1290 |
+
"loss": 46.0,
|
| 1291 |
+
"step": 182
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.0308821668143273,
|
| 1295 |
+
"grad_norm": 0.0002289148687850684,
|
| 1296 |
+
"learning_rate": 0.0001930287100469785,
|
| 1297 |
+
"loss": 46.0,
|
| 1298 |
+
"step": 183
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.031050921824241656,
|
| 1302 |
+
"grad_norm": 0.00022609223378822207,
|
| 1303 |
+
"learning_rate": 0.00019294884762378547,
|
| 1304 |
+
"loss": 46.0,
|
| 1305 |
+
"step": 184
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.031219676834156013,
|
| 1309 |
+
"grad_norm": 0.00014787810505367815,
|
| 1310 |
+
"learning_rate": 0.00019286854706703044,
|
| 1311 |
+
"loss": 46.0,
|
| 1312 |
+
"step": 185
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.03138843184407037,
|
| 1316 |
+
"grad_norm": 0.00017034618940670043,
|
| 1317 |
+
"learning_rate": 0.00019278780875522667,
|
| 1318 |
+
"loss": 46.0,
|
| 1319 |
+
"step": 186
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.03155718685398473,
|
| 1323 |
+
"grad_norm": 0.0001577001967234537,
|
| 1324 |
+
"learning_rate": 0.0001927066330689509,
|
| 1325 |
+
"loss": 46.0,
|
| 1326 |
+
"step": 187
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.031725941863899085,
|
| 1330 |
+
"grad_norm": 0.0001635671651456505,
|
| 1331 |
+
"learning_rate": 0.0001926250203908414,
|
| 1332 |
+
"loss": 46.0,
|
| 1333 |
+
"step": 188
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.03189469687381344,
|
| 1337 |
+
"grad_norm": 0.00011218619329156354,
|
| 1338 |
+
"learning_rate": 0.00019254297110559638,
|
| 1339 |
+
"loss": 46.0,
|
| 1340 |
+
"step": 189
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.0320634518837278,
|
| 1344 |
+
"grad_norm": 0.0001787557266652584,
|
| 1345 |
+
"learning_rate": 0.0001924604855999721,
|
| 1346 |
+
"loss": 46.0,
|
| 1347 |
+
"step": 190
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.03223220689364215,
|
| 1351 |
+
"grad_norm": 0.00014260809984989464,
|
| 1352 |
+
"learning_rate": 0.00019237756426278095,
|
| 1353 |
+
"loss": 46.0,
|
| 1354 |
+
"step": 191
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.03240096190355651,
|
| 1358 |
+
"grad_norm": 0.00012893076927866787,
|
| 1359 |
+
"learning_rate": 0.00019229420748488978,
|
| 1360 |
+
"loss": 46.0,
|
| 1361 |
+
"step": 192
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.03256971691347087,
|
| 1365 |
+
"grad_norm": 0.00022735691163688898,
|
| 1366 |
+
"learning_rate": 0.00019221041565921796,
|
| 1367 |
+
"loss": 46.0,
|
| 1368 |
+
"step": 193
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.03273847192338523,
|
| 1372 |
+
"grad_norm": 0.00011990263010375202,
|
| 1373 |
+
"learning_rate": 0.0001921261891807355,
|
| 1374 |
+
"loss": 46.0,
|
| 1375 |
+
"step": 194
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.03290722693329958,
|
| 1379 |
+
"grad_norm": 0.00017182013834826648,
|
| 1380 |
+
"learning_rate": 0.00019204152844646134,
|
| 1381 |
+
"loss": 46.0,
|
| 1382 |
+
"step": 195
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.03307598194321394,
|
| 1386 |
+
"grad_norm": 0.00017154582019429654,
|
| 1387 |
+
"learning_rate": 0.00019195643385546126,
|
| 1388 |
+
"loss": 46.0,
|
| 1389 |
+
"step": 196
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.033244736953128295,
|
| 1393 |
+
"grad_norm": 0.0001479845232097432,
|
| 1394 |
+
"learning_rate": 0.00019187090580884622,
|
| 1395 |
+
"loss": 46.0,
|
| 1396 |
+
"step": 197
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.033413491963042656,
|
| 1400 |
+
"grad_norm": 0.00010758084681583568,
|
| 1401 |
+
"learning_rate": 0.00019178494470977023,
|
| 1402 |
+
"loss": 46.0,
|
| 1403 |
+
"step": 198
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.03358224697295701,
|
| 1407 |
+
"grad_norm": 0.0001167198788607493,
|
| 1408 |
+
"learning_rate": 0.0001916985509634287,
|
| 1409 |
+
"loss": 46.0,
|
| 1410 |
+
"step": 199
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.03375100198287136,
|
| 1414 |
+
"grad_norm": 0.00015376460214611143,
|
| 1415 |
+
"learning_rate": 0.00019161172497705637,
|
| 1416 |
+
"loss": 46.0,
|
| 1417 |
+
"step": 200
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.033919756992785724,
|
| 1421 |
+
"grad_norm": 0.0001339185400865972,
|
| 1422 |
+
"learning_rate": 0.00019152446715992543,
|
| 1423 |
+
"loss": 46.0,
|
| 1424 |
+
"step": 201
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.03408851200270008,
|
| 1428 |
+
"grad_norm": 0.00018876604735851288,
|
| 1429 |
+
"learning_rate": 0.0001914367779233436,
|
| 1430 |
+
"loss": 46.0,
|
| 1431 |
+
"step": 202
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.03425726701261444,
|
| 1435 |
+
"grad_norm": 0.00017353007569909096,
|
| 1436 |
+
"learning_rate": 0.00019134865768065216,
|
| 1437 |
+
"loss": 46.0,
|
| 1438 |
+
"step": 203
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.03442602202252879,
|
| 1442 |
+
"grad_norm": 0.00011807784903794527,
|
| 1443 |
+
"learning_rate": 0.00019126010684722406,
|
| 1444 |
+
"loss": 46.0,
|
| 1445 |
+
"step": 204
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.03459477703244315,
|
| 1449 |
+
"grad_norm": 0.00010566677519818768,
|
| 1450 |
+
"learning_rate": 0.00019117112584046193,
|
| 1451 |
+
"loss": 46.0,
|
| 1452 |
+
"step": 205
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.034763532042357506,
|
| 1456 |
+
"grad_norm": 0.0001312542735831812,
|
| 1457 |
+
"learning_rate": 0.00019108171507979606,
|
| 1458 |
+
"loss": 46.0,
|
| 1459 |
+
"step": 206
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.03493228705227187,
|
| 1463 |
+
"grad_norm": 5.670605969498865e-05,
|
| 1464 |
+
"learning_rate": 0.00019099187498668256,
|
| 1465 |
+
"loss": 46.0,
|
| 1466 |
+
"step": 207
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.03510104206218622,
|
| 1470 |
+
"grad_norm": 8.242291369242594e-05,
|
| 1471 |
+
"learning_rate": 0.0001909016059846012,
|
| 1472 |
+
"loss": 46.0,
|
| 1473 |
+
"step": 208
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.03526979707210058,
|
| 1477 |
+
"grad_norm": 0.0001418525935150683,
|
| 1478 |
+
"learning_rate": 0.00019081090849905355,
|
| 1479 |
+
"loss": 46.0,
|
| 1480 |
+
"step": 209
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.035438552082014935,
|
| 1484 |
+
"grad_norm": 0.0002694391005206853,
|
| 1485 |
+
"learning_rate": 0.00019071978295756087,
|
| 1486 |
+
"loss": 46.0,
|
| 1487 |
+
"step": 210
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.03560730709192929,
|
| 1491 |
+
"grad_norm": 0.00015816248196642846,
|
| 1492 |
+
"learning_rate": 0.0001906282297896623,
|
| 1493 |
+
"loss": 46.0,
|
| 1494 |
+
"step": 211
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.03577606210184365,
|
| 1498 |
+
"grad_norm": 0.00011155927495565265,
|
| 1499 |
+
"learning_rate": 0.00019053624942691247,
|
| 1500 |
+
"loss": 46.0,
|
| 1501 |
+
"step": 212
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.035944817111758,
|
| 1505 |
+
"grad_norm": 0.00010293432569596916,
|
| 1506 |
+
"learning_rate": 0.0001904438423028798,
|
| 1507 |
+
"loss": 46.0,
|
| 1508 |
+
"step": 213
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.03611357212167236,
|
| 1512 |
+
"grad_norm": 0.00017549478798173368,
|
| 1513 |
+
"learning_rate": 0.00019035100885314438,
|
| 1514 |
+
"loss": 46.0,
|
| 1515 |
+
"step": 214
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.03628232713158672,
|
| 1519 |
+
"grad_norm": 8.048818563111126e-05,
|
| 1520 |
+
"learning_rate": 0.0001902577495152958,
|
| 1521 |
+
"loss": 46.0,
|
| 1522 |
+
"step": 215
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.03645108214150108,
|
| 1526 |
+
"grad_norm": 7.043426012387499e-05,
|
| 1527 |
+
"learning_rate": 0.0001901640647289312,
|
| 1528 |
+
"loss": 46.0,
|
| 1529 |
+
"step": 216
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.03661983715141543,
|
| 1533 |
+
"grad_norm": 0.00022185473062563688,
|
| 1534 |
+
"learning_rate": 0.00019006995493565305,
|
| 1535 |
+
"loss": 46.0,
|
| 1536 |
+
"step": 217
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.03678859216132979,
|
| 1540 |
+
"grad_norm": 0.0002446068392600864,
|
| 1541 |
+
"learning_rate": 0.0001899754205790674,
|
| 1542 |
+
"loss": 46.0,
|
| 1543 |
+
"step": 218
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.036957347171244145,
|
| 1547 |
+
"grad_norm": 0.0002539333945605904,
|
| 1548 |
+
"learning_rate": 0.00018988046210478132,
|
| 1549 |
+
"loss": 46.0,
|
| 1550 |
+
"step": 219
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.037126102181158506,
|
| 1554 |
+
"grad_norm": 0.0001403048081556335,
|
| 1555 |
+
"learning_rate": 0.00018978507996040124,
|
| 1556 |
+
"loss": 46.0,
|
| 1557 |
+
"step": 220
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.03729485719107286,
|
| 1561 |
+
"grad_norm": 0.00014873422333039343,
|
| 1562 |
+
"learning_rate": 0.00018968927459553055,
|
| 1563 |
+
"loss": 46.0,
|
| 1564 |
+
"step": 221
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.03746361220098722,
|
| 1568 |
+
"grad_norm": 0.00015955405251588672,
|
| 1569 |
+
"learning_rate": 0.00018959304646176754,
|
| 1570 |
+
"loss": 46.0,
|
| 1571 |
+
"step": 222
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.037632367210901574,
|
| 1575 |
+
"grad_norm": 0.0003200356150045991,
|
| 1576 |
+
"learning_rate": 0.00018949639601270347,
|
| 1577 |
+
"loss": 46.0,
|
| 1578 |
+
"step": 223
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.03780112222081593,
|
| 1582 |
+
"grad_norm": 0.00014675638522021472,
|
| 1583 |
+
"learning_rate": 0.00018939932370392004,
|
| 1584 |
+
"loss": 46.0,
|
| 1585 |
+
"step": 224
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.03796987723073029,
|
| 1589 |
+
"grad_norm": 0.00022176875791046768,
|
| 1590 |
+
"learning_rate": 0.00018930182999298768,
|
| 1591 |
+
"loss": 46.0,
|
| 1592 |
+
"step": 225
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.03813863224064464,
|
| 1596 |
+
"grad_norm": 0.00029244759934954345,
|
| 1597 |
+
"learning_rate": 0.0001892039153394631,
|
| 1598 |
+
"loss": 46.0,
|
| 1599 |
+
"step": 226
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.038307387250559,
|
| 1603 |
+
"grad_norm": 0.00019421910110395402,
|
| 1604 |
+
"learning_rate": 0.0001891055802048872,
|
| 1605 |
+
"loss": 46.0,
|
| 1606 |
+
"step": 227
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.038476142260473356,
|
| 1610 |
+
"grad_norm": 0.00012899210560135543,
|
| 1611 |
+
"learning_rate": 0.00018900682505278287,
|
| 1612 |
+
"loss": 46.0,
|
| 1613 |
+
"step": 228
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.03864489727038772,
|
| 1617 |
+
"grad_norm": 0.00016150598821695894,
|
| 1618 |
+
"learning_rate": 0.00018890765034865295,
|
| 1619 |
+
"loss": 46.0,
|
| 1620 |
+
"step": 229
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.03881365228030207,
|
| 1624 |
+
"grad_norm": 0.0004213732318021357,
|
| 1625 |
+
"learning_rate": 0.00018880805655997784,
|
| 1626 |
+
"loss": 46.0,
|
| 1627 |
+
"step": 230
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.03898240729021643,
|
| 1631 |
+
"grad_norm": 0.0001324907352682203,
|
| 1632 |
+
"learning_rate": 0.0001887080441562134,
|
| 1633 |
+
"loss": 46.0,
|
| 1634 |
+
"step": 231
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.039151162300130785,
|
| 1638 |
+
"grad_norm": 0.00029545003781095147,
|
| 1639 |
+
"learning_rate": 0.0001886076136087887,
|
| 1640 |
+
"loss": 46.0,
|
| 1641 |
+
"step": 232
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.039319917310045145,
|
| 1645 |
+
"grad_norm": 0.00018010212806984782,
|
| 1646 |
+
"learning_rate": 0.00018850676539110386,
|
| 1647 |
+
"loss": 46.0,
|
| 1648 |
+
"step": 233
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.0394886723199595,
|
| 1652 |
+
"grad_norm": 0.00014782045036554337,
|
| 1653 |
+
"learning_rate": 0.00018840549997852776,
|
| 1654 |
+
"loss": 46.0,
|
| 1655 |
+
"step": 234
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.03965742732987385,
|
| 1659 |
+
"grad_norm": 0.0002910486946348101,
|
| 1660 |
+
"learning_rate": 0.0001883038178483958,
|
| 1661 |
+
"loss": 46.0,
|
| 1662 |
+
"step": 235
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.03982618233978821,
|
| 1666 |
+
"grad_norm": 0.00010300084977643564,
|
| 1667 |
+
"learning_rate": 0.00018820171948000764,
|
| 1668 |
+
"loss": 46.0,
|
| 1669 |
+
"step": 236
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.03999493734970257,
|
| 1673 |
+
"grad_norm": 0.00029963982524350286,
|
| 1674 |
+
"learning_rate": 0.00018809920535462502,
|
| 1675 |
+
"loss": 46.0,
|
| 1676 |
+
"step": 237
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.04016369235961693,
|
| 1680 |
+
"grad_norm": 0.0002475226647220552,
|
| 1681 |
+
"learning_rate": 0.00018799627595546942,
|
| 1682 |
+
"loss": 46.0,
|
| 1683 |
+
"step": 238
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.04033244736953128,
|
| 1687 |
+
"grad_norm": 9.632138244342059e-05,
|
| 1688 |
+
"learning_rate": 0.00018789293176771978,
|
| 1689 |
+
"loss": 46.0,
|
| 1690 |
+
"step": 239
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.04050120237944564,
|
| 1694 |
+
"grad_norm": 0.00018374540377408266,
|
| 1695 |
+
"learning_rate": 0.00018778917327851025,
|
| 1696 |
+
"loss": 46.0,
|
| 1697 |
+
"step": 240
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.040669957389359995,
|
| 1701 |
+
"grad_norm": 0.0005576743860729039,
|
| 1702 |
+
"learning_rate": 0.00018768500097692784,
|
| 1703 |
+
"loss": 46.0,
|
| 1704 |
+
"step": 241
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.040838712399274356,
|
| 1708 |
+
"grad_norm": 0.0002332236763322726,
|
| 1709 |
+
"learning_rate": 0.00018758041535401018,
|
| 1710 |
+
"loss": 46.0,
|
| 1711 |
+
"step": 242
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.04100746740918871,
|
| 1715 |
+
"grad_norm": 0.00021743084653280675,
|
| 1716 |
+
"learning_rate": 0.00018747541690274325,
|
| 1717 |
+
"loss": 46.0,
|
| 1718 |
+
"step": 243
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.04117622241910307,
|
| 1722 |
+
"grad_norm": 0.00037613531458191574,
|
| 1723 |
+
"learning_rate": 0.00018737000611805877,
|
| 1724 |
+
"loss": 46.0,
|
| 1725 |
+
"step": 244
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.041344977429017424,
|
| 1729 |
+
"grad_norm": 0.00017969420878216624,
|
| 1730 |
+
"learning_rate": 0.00018726418349683231,
|
| 1731 |
+
"loss": 46.0,
|
| 1732 |
+
"step": 245
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.04151373243893178,
|
| 1736 |
+
"grad_norm": 0.00021221920906100422,
|
| 1737 |
+
"learning_rate": 0.00018715794953788059,
|
| 1738 |
+
"loss": 46.0,
|
| 1739 |
+
"step": 246
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.04168248744884614,
|
| 1743 |
+
"grad_norm": 0.0002182903845096007,
|
| 1744 |
+
"learning_rate": 0.0001870513047419593,
|
| 1745 |
+
"loss": 46.0,
|
| 1746 |
+
"step": 247
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.04185124245876049,
|
| 1750 |
+
"grad_norm": 0.00023534568026661873,
|
| 1751 |
+
"learning_rate": 0.00018694424961176065,
|
| 1752 |
+
"loss": 46.0,
|
| 1753 |
+
"step": 248
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.04201999746867485,
|
| 1757 |
+
"grad_norm": 0.00013651238987222314,
|
| 1758 |
+
"learning_rate": 0.00018683678465191108,
|
| 1759 |
+
"loss": 46.0,
|
| 1760 |
+
"step": 249
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.042188752478589206,
|
| 1764 |
+
"grad_norm": 0.000251735036727041,
|
| 1765 |
+
"learning_rate": 0.00018672891036896884,
|
| 1766 |
+
"loss": 46.0,
|
| 1767 |
+
"step": 250
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.04235750748850357,
|
| 1771 |
+
"grad_norm": 0.0005651676910929382,
|
| 1772 |
+
"learning_rate": 0.00018662062727142165,
|
| 1773 |
+
"loss": 46.0,
|
| 1774 |
+
"step": 251
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.04252626249841792,
|
| 1778 |
+
"grad_norm": 0.00027543309261091053,
|
| 1779 |
+
"learning_rate": 0.00018651193586968417,
|
| 1780 |
+
"loss": 46.0,
|
| 1781 |
+
"step": 252
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.04269501750833228,
|
| 1785 |
+
"grad_norm": 0.00025643999106250703,
|
| 1786 |
+
"learning_rate": 0.00018640283667609574,
|
| 1787 |
+
"loss": 46.0,
|
| 1788 |
+
"step": 253
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.042863772518246634,
|
| 1792 |
+
"grad_norm": 0.00026899727527052164,
|
| 1793 |
+
"learning_rate": 0.00018629333020491796,
|
| 1794 |
+
"loss": 46.0,
|
| 1795 |
+
"step": 254
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.043032527528160995,
|
| 1799 |
+
"grad_norm": 0.0002454131608828902,
|
| 1800 |
+
"learning_rate": 0.00018618341697233213,
|
| 1801 |
+
"loss": 46.0,
|
| 1802 |
+
"step": 255
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.04320128253807535,
|
| 1806 |
+
"grad_norm": 0.00020008228602819145,
|
| 1807 |
+
"learning_rate": 0.0001860730974964369,
|
| 1808 |
+
"loss": 46.0,
|
| 1809 |
+
"step": 256
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.04337003754798971,
|
| 1813 |
+
"grad_norm": 0.0003180755884386599,
|
| 1814 |
+
"learning_rate": 0.00018596237229724595,
|
| 1815 |
+
"loss": 46.0,
|
| 1816 |
+
"step": 257
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.04353879255790406,
|
| 1820 |
+
"grad_norm": 0.00027137139113619924,
|
| 1821 |
+
"learning_rate": 0.0001858512418966853,
|
| 1822 |
+
"loss": 46.0,
|
| 1823 |
+
"step": 258
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.04370754756781842,
|
| 1827 |
+
"grad_norm": 0.0003248886205255985,
|
| 1828 |
+
"learning_rate": 0.000185739706818591,
|
| 1829 |
+
"loss": 46.0,
|
| 1830 |
+
"step": 259
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.04387630257773278,
|
| 1834 |
+
"grad_norm": 0.00022937578614801168,
|
| 1835 |
+
"learning_rate": 0.00018562776758870663,
|
| 1836 |
+
"loss": 46.0,
|
| 1837 |
+
"step": 260
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.04404505758764713,
|
| 1841 |
+
"grad_norm": 0.00026010029250755906,
|
| 1842 |
+
"learning_rate": 0.0001855154247346809,
|
| 1843 |
+
"loss": 46.0,
|
| 1844 |
+
"step": 261
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.04421381259756149,
|
| 1848 |
+
"grad_norm": 0.00012881477596238256,
|
| 1849 |
+
"learning_rate": 0.00018540267878606497,
|
| 1850 |
+
"loss": 46.0,
|
| 1851 |
+
"step": 262
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.044382567607475845,
|
| 1855 |
+
"grad_norm": 0.0001669221237534657,
|
| 1856 |
+
"learning_rate": 0.0001852895302743101,
|
| 1857 |
+
"loss": 46.0,
|
| 1858 |
+
"step": 263
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.044551322617390206,
|
| 1862 |
+
"grad_norm": 8.989863272290677e-05,
|
| 1863 |
+
"learning_rate": 0.0001851759797327652,
|
| 1864 |
+
"loss": 46.0,
|
| 1865 |
+
"step": 264
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.04472007762730456,
|
| 1869 |
+
"grad_norm": 0.00043415901018306613,
|
| 1870 |
+
"learning_rate": 0.00018506202769667413,
|
| 1871 |
+
"loss": 46.0,
|
| 1872 |
+
"step": 265
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.04488883263721892,
|
| 1876 |
+
"grad_norm": 0.00018308595463167876,
|
| 1877 |
+
"learning_rate": 0.00018494767470317333,
|
| 1878 |
+
"loss": 46.0,
|
| 1879 |
+
"step": 266
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.045057587647133274,
|
| 1883 |
+
"grad_norm": 0.0005433953483588994,
|
| 1884 |
+
"learning_rate": 0.00018483292129128914,
|
| 1885 |
+
"loss": 46.0,
|
| 1886 |
+
"step": 267
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.045226342657047634,
|
| 1890 |
+
"grad_norm": 0.0001997397339437157,
|
| 1891 |
+
"learning_rate": 0.00018471776800193553,
|
| 1892 |
+
"loss": 46.0,
|
| 1893 |
+
"step": 268
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.04539509766696199,
|
| 1897 |
+
"grad_norm": 0.0002549294731579721,
|
| 1898 |
+
"learning_rate": 0.00018460221537791122,
|
| 1899 |
+
"loss": 46.0,
|
| 1900 |
+
"step": 269
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.04556385267687634,
|
| 1904 |
+
"grad_norm": 0.0004634494544006884,
|
| 1905 |
+
"learning_rate": 0.00018448626396389738,
|
| 1906 |
+
"loss": 46.0,
|
| 1907 |
+
"step": 270
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.0457326076867907,
|
| 1911 |
+
"grad_norm": 0.00015057041309773922,
|
| 1912 |
+
"learning_rate": 0.00018436991430645488,
|
| 1913 |
+
"loss": 46.0,
|
| 1914 |
+
"step": 271
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.045901362696705056,
|
| 1918 |
+
"grad_norm": 0.00030916737159714103,
|
| 1919 |
+
"learning_rate": 0.00018425316695402181,
|
| 1920 |
+
"loss": 46.0,
|
| 1921 |
+
"step": 272
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.046070117706619416,
|
| 1925 |
+
"grad_norm": 0.0003056859422940761,
|
| 1926 |
+
"learning_rate": 0.00018413602245691092,
|
| 1927 |
+
"loss": 46.0,
|
| 1928 |
+
"step": 273
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.04623887271653377,
|
| 1932 |
+
"grad_norm": 0.00028438231674954295,
|
| 1933 |
+
"learning_rate": 0.00018401848136730698,
|
| 1934 |
+
"loss": 46.0,
|
| 1935 |
+
"step": 274
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.04640762772644813,
|
| 1939 |
+
"grad_norm": 0.00034854307887144387,
|
| 1940 |
+
"learning_rate": 0.00018390054423926406,
|
| 1941 |
+
"loss": 46.0,
|
| 1942 |
+
"step": 275
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.046576382736362484,
|
| 1946 |
+
"grad_norm": 0.00025173407630063593,
|
| 1947 |
+
"learning_rate": 0.00018378221162870326,
|
| 1948 |
+
"loss": 46.0,
|
| 1949 |
+
"step": 276
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.046745137746276845,
|
| 1953 |
+
"grad_norm": 0.0006683963001705706,
|
| 1954 |
+
"learning_rate": 0.00018366348409340965,
|
| 1955 |
+
"loss": 46.0,
|
| 1956 |
+
"step": 277
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.0469138927561912,
|
| 1960 |
+
"grad_norm": 0.00017825645045377314,
|
| 1961 |
+
"learning_rate": 0.00018354436219303,
|
| 1962 |
+
"loss": 46.0,
|
| 1963 |
+
"step": 278
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.04708264776610556,
|
| 1967 |
+
"grad_norm": 0.00026973988860845566,
|
| 1968 |
+
"learning_rate": 0.00018342484648906996,
|
| 1969 |
+
"loss": 46.0,
|
| 1970 |
+
"step": 279
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.04725140277601991,
|
| 1974 |
+
"grad_norm": 0.00027474435046315193,
|
| 1975 |
+
"learning_rate": 0.00018330493754489138,
|
| 1976 |
+
"loss": 46.0,
|
| 1977 |
+
"step": 280
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.04742015778593427,
|
| 1981 |
+
"grad_norm": 0.00025235096109099686,
|
| 1982 |
+
"learning_rate": 0.00018318463592570988,
|
| 1983 |
+
"loss": 46.0,
|
| 1984 |
+
"step": 281
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.04758891279584863,
|
| 1988 |
+
"grad_norm": 0.00020448811119422317,
|
| 1989 |
+
"learning_rate": 0.0001830639421985919,
|
| 1990 |
+
"loss": 46.0,
|
| 1991 |
+
"step": 282
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.04775766780576298,
|
| 1995 |
+
"grad_norm": 0.00028648230363614857,
|
| 1996 |
+
"learning_rate": 0.00018294285693245223,
|
| 1997 |
+
"loss": 46.0,
|
| 1998 |
+
"step": 283
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.04792642281567734,
|
| 2002 |
+
"grad_norm": 0.00027214092551730573,
|
| 2003 |
+
"learning_rate": 0.00018282138069805127,
|
| 2004 |
+
"loss": 46.0,
|
| 2005 |
+
"step": 284
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.048095177825591695,
|
| 2009 |
+
"grad_norm": 0.00021831200865563005,
|
| 2010 |
+
"learning_rate": 0.00018269951406799223,
|
| 2011 |
+
"loss": 46.0,
|
| 2012 |
+
"step": 285
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.048263932835506056,
|
| 2016 |
+
"grad_norm": 0.000336469296598807,
|
| 2017 |
+
"learning_rate": 0.00018257725761671866,
|
| 2018 |
+
"loss": 46.0,
|
| 2019 |
+
"step": 286
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.04843268784542041,
|
| 2023 |
+
"grad_norm": 0.00034162108204327524,
|
| 2024 |
+
"learning_rate": 0.00018245461192051157,
|
| 2025 |
+
"loss": 46.0,
|
| 2026 |
+
"step": 287
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.04860144285533477,
|
| 2030 |
+
"grad_norm": 0.00035298787406645715,
|
| 2031 |
+
"learning_rate": 0.00018233157755748669,
|
| 2032 |
+
"loss": 46.0,
|
| 2033 |
+
"step": 288
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.048770197865249124,
|
| 2037 |
+
"grad_norm": 0.00015676271868869662,
|
| 2038 |
+
"learning_rate": 0.0001822081551075919,
|
| 2039 |
+
"loss": 46.0,
|
| 2040 |
+
"step": 289
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.048938952875163484,
|
| 2044 |
+
"grad_norm": 0.00023883357062004507,
|
| 2045 |
+
"learning_rate": 0.0001820843451526044,
|
| 2046 |
+
"loss": 46.0,
|
| 2047 |
+
"step": 290
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.04910770788507784,
|
| 2051 |
+
"grad_norm": 0.0002669495588634163,
|
| 2052 |
+
"learning_rate": 0.0001819601482761278,
|
| 2053 |
+
"loss": 46.0,
|
| 2054 |
+
"step": 291
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.0492764628949922,
|
| 2058 |
+
"grad_norm": 0.00034910603426396847,
|
| 2059 |
+
"learning_rate": 0.0001818355650635899,
|
| 2060 |
+
"loss": 46.0,
|
| 2061 |
+
"step": 292
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.04944521790490655,
|
| 2065 |
+
"grad_norm": 0.00024713424500077963,
|
| 2066 |
+
"learning_rate": 0.0001817105961022392,
|
| 2067 |
+
"loss": 46.0,
|
| 2068 |
+
"step": 293
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.049613972914820906,
|
| 2072 |
+
"grad_norm": 0.0002389974833931774,
|
| 2073 |
+
"learning_rate": 0.00018158524198114278,
|
| 2074 |
+
"loss": 46.0,
|
| 2075 |
+
"step": 294
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.049782727924735266,
|
| 2079 |
+
"grad_norm": 0.00028152199229225516,
|
| 2080 |
+
"learning_rate": 0.0001814595032911831,
|
| 2081 |
+
"loss": 46.0,
|
| 2082 |
+
"step": 295
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.04995148293464962,
|
| 2086 |
+
"grad_norm": 0.0004107706481590867,
|
| 2087 |
+
"learning_rate": 0.00018133338062505534,
|
| 2088 |
+
"loss": 46.0,
|
| 2089 |
+
"step": 296
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.05012023794456398,
|
| 2093 |
+
"grad_norm": 0.00032018640195019543,
|
| 2094 |
+
"learning_rate": 0.00018120687457726478,
|
| 2095 |
+
"loss": 46.0,
|
| 2096 |
+
"step": 297
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.050288992954478334,
|
| 2100 |
+
"grad_norm": 0.0003432031662669033,
|
| 2101 |
+
"learning_rate": 0.00018107998574412376,
|
| 2102 |
+
"loss": 46.0,
|
| 2103 |
+
"step": 298
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.050457747964392695,
|
| 2107 |
+
"grad_norm": 0.00042492407374083996,
|
| 2108 |
+
"learning_rate": 0.00018095271472374892,
|
| 2109 |
+
"loss": 46.0,
|
| 2110 |
+
"step": 299
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.05062650297430705,
|
| 2114 |
+
"grad_norm": 0.0004913901793770492,
|
| 2115 |
+
"learning_rate": 0.00018082506211605852,
|
| 2116 |
+
"loss": 46.0,
|
| 2117 |
+
"step": 300
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.05079525798422141,
|
| 2121 |
+
"grad_norm": 0.00045284689986146986,
|
| 2122 |
+
"learning_rate": 0.00018069702852276941,
|
| 2123 |
+
"loss": 46.0,
|
| 2124 |
+
"step": 301
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.05096401299413576,
|
| 2128 |
+
"grad_norm": 0.0002827131829690188,
|
| 2129 |
+
"learning_rate": 0.00018056861454739432,
|
| 2130 |
+
"loss": 46.0,
|
| 2131 |
+
"step": 302
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.05113276800405012,
|
| 2135 |
+
"grad_norm": 0.000371127447579056,
|
| 2136 |
+
"learning_rate": 0.00018043982079523905,
|
| 2137 |
+
"loss": 46.0,
|
| 2138 |
+
"step": 303
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.05130152301396448,
|
| 2142 |
+
"grad_norm": 0.0001193537755170837,
|
| 2143 |
+
"learning_rate": 0.00018031064787339947,
|
| 2144 |
+
"loss": 46.0,
|
| 2145 |
+
"step": 304
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.05147027802387883,
|
| 2149 |
+
"grad_norm": 0.0002617594145704061,
|
| 2150 |
+
"learning_rate": 0.00018018109639075886,
|
| 2151 |
+
"loss": 46.0,
|
| 2152 |
+
"step": 305
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.05163903303379319,
|
| 2156 |
+
"grad_norm": 0.0003127566596958786,
|
| 2157 |
+
"learning_rate": 0.00018005116695798476,
|
| 2158 |
+
"loss": 46.0,
|
| 2159 |
+
"step": 306
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.051807788043707545,
|
| 2163 |
+
"grad_norm": 0.0003426918410696089,
|
| 2164 |
+
"learning_rate": 0.00017992086018752638,
|
| 2165 |
+
"loss": 46.0,
|
| 2166 |
+
"step": 307
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.051976543053621906,
|
| 2170 |
+
"grad_norm": 0.000528005592059344,
|
| 2171 |
+
"learning_rate": 0.0001797901766936116,
|
| 2172 |
+
"loss": 46.0,
|
| 2173 |
+
"step": 308
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.05214529806353626,
|
| 2177 |
+
"grad_norm": 0.00044293675455264747,
|
| 2178 |
+
"learning_rate": 0.00017965911709224395,
|
| 2179 |
+
"loss": 46.0,
|
| 2180 |
+
"step": 309
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.05231405307345062,
|
| 2184 |
+
"grad_norm": 0.0004309279902372509,
|
| 2185 |
+
"learning_rate": 0.00017952768200119992,
|
| 2186 |
+
"loss": 46.0,
|
| 2187 |
+
"step": 310
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.052482808083364973,
|
| 2191 |
+
"grad_norm": 0.00038651516661047935,
|
| 2192 |
+
"learning_rate": 0.0001793958720400259,
|
| 2193 |
+
"loss": 46.0,
|
| 2194 |
+
"step": 311
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.052651563093279334,
|
| 2198 |
+
"grad_norm": 0.000503813847899437,
|
| 2199 |
+
"learning_rate": 0.00017926368783003537,
|
| 2200 |
+
"loss": 46.0,
|
| 2201 |
+
"step": 312
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.05282031810319369,
|
| 2205 |
+
"grad_norm": 0.0007580111850984395,
|
| 2206 |
+
"learning_rate": 0.00017913112999430584,
|
| 2207 |
+
"loss": 46.0,
|
| 2208 |
+
"step": 313
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.05298907311310805,
|
| 2212 |
+
"grad_norm": 0.0003376993117853999,
|
| 2213 |
+
"learning_rate": 0.00017899819915767598,
|
| 2214 |
+
"loss": 46.0,
|
| 2215 |
+
"step": 314
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.0531578281230224,
|
| 2219 |
+
"grad_norm": 0.0003070792299695313,
|
| 2220 |
+
"learning_rate": 0.00017886489594674273,
|
| 2221 |
+
"loss": 46.0,
|
| 2222 |
+
"step": 315
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.053326583132936756,
|
| 2226 |
+
"grad_norm": 0.0006369905895553529,
|
| 2227 |
+
"learning_rate": 0.00017873122098985826,
|
| 2228 |
+
"loss": 46.0,
|
| 2229 |
+
"step": 316
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.053495338142851116,
|
| 2233 |
+
"grad_norm": 0.0005446787690743804,
|
| 2234 |
+
"learning_rate": 0.00017859717491712707,
|
| 2235 |
+
"loss": 46.0,
|
| 2236 |
+
"step": 317
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.05366409315276547,
|
| 2240 |
+
"grad_norm": 0.0003436711267568171,
|
| 2241 |
+
"learning_rate": 0.0001784627583604029,
|
| 2242 |
+
"loss": 46.0,
|
| 2243 |
+
"step": 318
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.05383284816267983,
|
| 2247 |
+
"grad_norm": 0.0004495533648878336,
|
| 2248 |
+
"learning_rate": 0.000178327971953286,
|
| 2249 |
+
"loss": 46.0,
|
| 2250 |
+
"step": 319
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.054001603172594184,
|
| 2254 |
+
"grad_norm": 0.0004997072974219918,
|
| 2255 |
+
"learning_rate": 0.00017819281633111984,
|
| 2256 |
+
"loss": 46.0,
|
| 2257 |
+
"step": 320
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.054170358182508545,
|
| 2261 |
+
"grad_norm": 0.00040087226079776883,
|
| 2262 |
+
"learning_rate": 0.0001780572921309883,
|
| 2263 |
+
"loss": 46.0,
|
| 2264 |
+
"step": 321
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.0543391131924229,
|
| 2268 |
+
"grad_norm": 0.0005316153983585536,
|
| 2269 |
+
"learning_rate": 0.0001779213999917127,
|
| 2270 |
+
"loss": 46.0,
|
| 2271 |
+
"step": 322
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.05450786820233726,
|
| 2275 |
+
"grad_norm": 0.0006078218575567007,
|
| 2276 |
+
"learning_rate": 0.00017778514055384866,
|
| 2277 |
+
"loss": 46.0,
|
| 2278 |
+
"step": 323
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.05467662321225161,
|
| 2282 |
+
"grad_norm": 0.0004828522796742618,
|
| 2283 |
+
"learning_rate": 0.00017764851445968308,
|
| 2284 |
+
"loss": 46.0,
|
| 2285 |
+
"step": 324
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.05484537822216597,
|
| 2289 |
+
"grad_norm": 0.00032997396192513406,
|
| 2290 |
+
"learning_rate": 0.0001775115223532313,
|
| 2291 |
+
"loss": 46.0,
|
| 2292 |
+
"step": 325
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.05501413323208033,
|
| 2296 |
+
"grad_norm": 0.00033607761724852026,
|
| 2297 |
+
"learning_rate": 0.00017737416488023384,
|
| 2298 |
+
"loss": 46.0,
|
| 2299 |
+
"step": 326
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.05518288824199469,
|
| 2303 |
+
"grad_norm": 0.0004014720907434821,
|
| 2304 |
+
"learning_rate": 0.00017723644268815344,
|
| 2305 |
+
"loss": 46.0,
|
| 2306 |
+
"step": 327
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.05535164325190904,
|
| 2310 |
+
"grad_norm": 0.000525740790180862,
|
| 2311 |
+
"learning_rate": 0.00017709835642617212,
|
| 2312 |
+
"loss": 46.0,
|
| 2313 |
+
"step": 328
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.055520398261823395,
|
| 2317 |
+
"grad_norm": 0.0007568416767753661,
|
| 2318 |
+
"learning_rate": 0.00017695990674518788,
|
| 2319 |
+
"loss": 46.0,
|
| 2320 |
+
"step": 329
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.055689153271737755,
|
| 2324 |
+
"grad_norm": 0.0004670285852625966,
|
| 2325 |
+
"learning_rate": 0.0001768210942978119,
|
| 2326 |
+
"loss": 46.0,
|
| 2327 |
+
"step": 330
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.05585790828165211,
|
| 2331 |
+
"grad_norm": 0.0005972511135041714,
|
| 2332 |
+
"learning_rate": 0.00017668191973836529,
|
| 2333 |
+
"loss": 46.0,
|
| 2334 |
+
"step": 331
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.05602666329156647,
|
| 2338 |
+
"grad_norm": 0.00048381276428699493,
|
| 2339 |
+
"learning_rate": 0.000176542383722876,
|
| 2340 |
+
"loss": 46.0,
|
| 2341 |
+
"step": 332
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.05619541830148082,
|
| 2345 |
+
"grad_norm": 0.0007428377284668386,
|
| 2346 |
+
"learning_rate": 0.0001764024869090758,
|
| 2347 |
+
"loss": 46.0,
|
| 2348 |
+
"step": 333
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.056364173311395184,
|
| 2352 |
+
"grad_norm": 0.000608109578024596,
|
| 2353 |
+
"learning_rate": 0.00017626222995639724,
|
| 2354 |
+
"loss": 46.0,
|
| 2355 |
+
"step": 334
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.05653292832130954,
|
| 2359 |
+
"grad_norm": 0.0006571222911588848,
|
| 2360 |
+
"learning_rate": 0.00017612161352597032,
|
| 2361 |
+
"loss": 46.0,
|
| 2362 |
+
"step": 335
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.0567016833312239,
|
| 2366 |
+
"grad_norm": 0.0007276976830326021,
|
| 2367 |
+
"learning_rate": 0.00017598063828061958,
|
| 2368 |
+
"loss": 46.0,
|
| 2369 |
+
"step": 336
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.05687043834113825,
|
| 2373 |
+
"grad_norm": 0.0007646044250577688,
|
| 2374 |
+
"learning_rate": 0.000175839304884861,
|
| 2375 |
+
"loss": 46.0,
|
| 2376 |
+
"step": 337
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.05703919335105261,
|
| 2380 |
+
"grad_norm": 0.0004487757687456906,
|
| 2381 |
+
"learning_rate": 0.00017569761400489862,
|
| 2382 |
+
"loss": 46.0,
|
| 2383 |
+
"step": 338
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.057207948360966966,
|
| 2387 |
+
"grad_norm": 0.0004590119933709502,
|
| 2388 |
+
"learning_rate": 0.0001755555663086216,
|
| 2389 |
+
"loss": 46.0,
|
| 2390 |
+
"step": 339
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.05737670337088132,
|
| 2394 |
+
"grad_norm": 0.00019634263298939914,
|
| 2395 |
+
"learning_rate": 0.0001754131624656011,
|
| 2396 |
+
"loss": 46.0,
|
| 2397 |
+
"step": 340
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.05754545838079568,
|
| 2401 |
+
"grad_norm": 0.0008665765053592622,
|
| 2402 |
+
"learning_rate": 0.00017527040314708702,
|
| 2403 |
+
"loss": 46.0,
|
| 2404 |
+
"step": 341
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.057714213390710034,
|
| 2408 |
+
"grad_norm": 0.0010710041970014572,
|
| 2409 |
+
"learning_rate": 0.0001751272890260048,
|
| 2410 |
+
"loss": 46.0,
|
| 2411 |
+
"step": 342
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.057882968400624395,
|
| 2415 |
+
"grad_norm": 0.0010121267987415195,
|
| 2416 |
+
"learning_rate": 0.0001749838207769524,
|
| 2417 |
+
"loss": 46.0,
|
| 2418 |
+
"step": 343
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.05805172341053875,
|
| 2422 |
+
"grad_norm": 0.0006279960507526994,
|
| 2423 |
+
"learning_rate": 0.00017483999907619695,
|
| 2424 |
+
"loss": 46.0,
|
| 2425 |
+
"step": 344
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.05822047842045311,
|
| 2429 |
+
"grad_norm": 0.0006246848497539759,
|
| 2430 |
+
"learning_rate": 0.00017469582460167174,
|
| 2431 |
+
"loss": 46.0,
|
| 2432 |
+
"step": 345
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.05838923343036746,
|
| 2436 |
+
"grad_norm": 0.000596629804931581,
|
| 2437 |
+
"learning_rate": 0.00017455129803297287,
|
| 2438 |
+
"loss": 46.0,
|
| 2439 |
+
"step": 346
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.05855798844028182,
|
| 2443 |
+
"grad_norm": 0.0008878617081791162,
|
| 2444 |
+
"learning_rate": 0.00017440642005135614,
|
| 2445 |
+
"loss": 46.0,
|
| 2446 |
+
"step": 347
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.05872674345019618,
|
| 2450 |
+
"grad_norm": 0.0003601356002036482,
|
| 2451 |
+
"learning_rate": 0.0001742611913397338,
|
| 2452 |
+
"loss": 46.0,
|
| 2453 |
+
"step": 348
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.05889549846011054,
|
| 2457 |
+
"grad_norm": 0.0003498071455396712,
|
| 2458 |
+
"learning_rate": 0.00017411561258267127,
|
| 2459 |
+
"loss": 46.0,
|
| 2460 |
+
"step": 349
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.05906425347002489,
|
| 2464 |
+
"grad_norm": 0.0007128751021809876,
|
| 2465 |
+
"learning_rate": 0.0001739696844663841,
|
| 2466 |
+
"loss": 46.0,
|
| 2467 |
+
"step": 350
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.059233008479939245,
|
| 2471 |
+
"grad_norm": 0.00047719714348204434,
|
| 2472 |
+
"learning_rate": 0.0001738234076787346,
|
| 2473 |
+
"loss": 46.0,
|
| 2474 |
+
"step": 351
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.059401763489853605,
|
| 2478 |
+
"grad_norm": 0.0006972616538405418,
|
| 2479 |
+
"learning_rate": 0.00017367678290922852,
|
| 2480 |
+
"loss": 46.0,
|
| 2481 |
+
"step": 352
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.05957051849976796,
|
| 2485 |
+
"grad_norm": 0.0005275082658044994,
|
| 2486 |
+
"learning_rate": 0.00017352981084901194,
|
| 2487 |
+
"loss": 46.0,
|
| 2488 |
+
"step": 353
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.05973927350968232,
|
| 2492 |
+
"grad_norm": 0.001250717556104064,
|
| 2493 |
+
"learning_rate": 0.000173382492190868,
|
| 2494 |
+
"loss": 46.0,
|
| 2495 |
+
"step": 354
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.05990802851959667,
|
| 2499 |
+
"grad_norm": 0.0008419329533353448,
|
| 2500 |
+
"learning_rate": 0.00017323482762921354,
|
| 2501 |
+
"loss": 46.0,
|
| 2502 |
+
"step": 355
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.060076783529511034,
|
| 2506 |
+
"grad_norm": 0.0008670453680679202,
|
| 2507 |
+
"learning_rate": 0.000173086817860096,
|
| 2508 |
+
"loss": 46.0,
|
| 2509 |
+
"step": 356
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.06024553853942539,
|
| 2513 |
+
"grad_norm": 0.0014900369569659233,
|
| 2514 |
+
"learning_rate": 0.00017293846358118988,
|
| 2515 |
+
"loss": 46.0,
|
| 2516 |
+
"step": 357
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.06041429354933975,
|
| 2520 |
+
"grad_norm": 0.001586690079420805,
|
| 2521 |
+
"learning_rate": 0.0001727897654917937,
|
| 2522 |
+
"loss": 46.0,
|
| 2523 |
+
"step": 358
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.0605830485592541,
|
| 2527 |
+
"grad_norm": 0.0009236481855623424,
|
| 2528 |
+
"learning_rate": 0.00017264072429282656,
|
| 2529 |
+
"loss": 46.0,
|
| 2530 |
+
"step": 359
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.06075180356916846,
|
| 2534 |
+
"grad_norm": 0.0011958472896367311,
|
| 2535 |
+
"learning_rate": 0.00017249134068682487,
|
| 2536 |
+
"loss": 46.0,
|
| 2537 |
+
"step": 360
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.060920558579082816,
|
| 2541 |
+
"grad_norm": 0.0006783442222513258,
|
| 2542 |
+
"learning_rate": 0.00017234161537793913,
|
| 2543 |
+
"loss": 46.0,
|
| 2544 |
+
"step": 361
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.06108931358899718,
|
| 2548 |
+
"grad_norm": 0.0010664722649380565,
|
| 2549 |
+
"learning_rate": 0.0001721915490719304,
|
| 2550 |
+
"loss": 46.0,
|
| 2551 |
+
"step": 362
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.06125806859891153,
|
| 2555 |
+
"grad_norm": 0.0012871964136138558,
|
| 2556 |
+
"learning_rate": 0.00017204114247616715,
|
| 2557 |
+
"loss": 46.0,
|
| 2558 |
+
"step": 363
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.061426823608825884,
|
| 2562 |
+
"grad_norm": 0.0006326769944280386,
|
| 2563 |
+
"learning_rate": 0.00017189039629962193,
|
| 2564 |
+
"loss": 46.0,
|
| 2565 |
+
"step": 364
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.061595578618740245,
|
| 2569 |
+
"grad_norm": 0.0005951938219368458,
|
| 2570 |
+
"learning_rate": 0.00017173931125286792,
|
| 2571 |
+
"loss": 46.0,
|
| 2572 |
+
"step": 365
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.061595578618740245,
|
| 2576 |
+
"eval_loss": 11.5,
|
| 2577 |
+
"eval_runtime": 14.8849,
|
| 2578 |
+
"eval_samples_per_second": 167.619,
|
| 2579 |
+
"eval_steps_per_second": 83.843,
|
| 2580 |
+
"step": 365
|
| 2581 |
+
}
|
| 2582 |
+
],
|
| 2583 |
+
"logging_steps": 1,
|
| 2584 |
+
"max_steps": 1457,
|
| 2585 |
+
"num_input_tokens_seen": 0,
|
| 2586 |
+
"num_train_epochs": 1,
|
| 2587 |
+
"save_steps": 365,
|
| 2588 |
+
"stateful_callbacks": {
|
| 2589 |
+
"TrainerControl": {
|
| 2590 |
+
"args": {
|
| 2591 |
+
"should_epoch_stop": false,
|
| 2592 |
+
"should_evaluate": false,
|
| 2593 |
+
"should_log": false,
|
| 2594 |
+
"should_save": true,
|
| 2595 |
+
"should_training_stop": false
|
| 2596 |
+
},
|
| 2597 |
+
"attributes": {}
|
| 2598 |
+
}
|
| 2599 |
+
},
|
| 2600 |
+
"total_flos": 7271850639360.0,
|
| 2601 |
+
"train_batch_size": 2,
|
| 2602 |
+
"trial_name": null,
|
| 2603 |
+
"trial_params": null
|
| 2604 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39f2c53575314be409a7340b1ffac25d9f3a8a9e4813e050819956978b358f81
|
| 3 |
+
size 6776
|
last-checkpoint/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|