Upload 26 files
Browse files- tinyllama-lora-finetuned/checkpoint-4706/README.md +202 -0
- tinyllama-lora-finetuned/checkpoint-4706/adapter_config.json +34 -0
- tinyllama-lora-finetuned/checkpoint-4706/adapter_model.safetensors +3 -0
- tinyllama-lora-finetuned/checkpoint-4706/optimizer.pt +3 -0
- tinyllama-lora-finetuned/checkpoint-4706/rng_state.pth +3 -0
- tinyllama-lora-finetuned/checkpoint-4706/scaler.pt +3 -0
- tinyllama-lora-finetuned/checkpoint-4706/scheduler.pt +3 -0
- tinyllama-lora-finetuned/checkpoint-4706/special_tokens_map.json +24 -0
- tinyllama-lora-finetuned/checkpoint-4706/tokenizer.json +0 -0
- tinyllama-lora-finetuned/checkpoint-4706/tokenizer.model +3 -0
- tinyllama-lora-finetuned/checkpoint-4706/tokenizer_config.json +44 -0
- tinyllama-lora-finetuned/checkpoint-4706/trainer_state.json +1679 -0
- tinyllama-lora-finetuned/checkpoint-4706/training_args.bin +3 -0
- tinyllama-lora-finetuned/checkpoint-7059/README.md +202 -0
- tinyllama-lora-finetuned/checkpoint-7059/adapter_config.json +34 -0
- tinyllama-lora-finetuned/checkpoint-7059/adapter_model.safetensors +3 -0
- tinyllama-lora-finetuned/checkpoint-7059/optimizer.pt +3 -0
- tinyllama-lora-finetuned/checkpoint-7059/rng_state.pth +3 -0
- tinyllama-lora-finetuned/checkpoint-7059/scaler.pt +3 -0
- tinyllama-lora-finetuned/checkpoint-7059/scheduler.pt +3 -0
- tinyllama-lora-finetuned/checkpoint-7059/special_tokens_map.json +24 -0
- tinyllama-lora-finetuned/checkpoint-7059/tokenizer.json +0 -0
- tinyllama-lora-finetuned/checkpoint-7059/tokenizer.model +3 -0
- tinyllama-lora-finetuned/checkpoint-7059/tokenizer_config.json +44 -0
- tinyllama-lora-finetuned/checkpoint-7059/trainer_state.json +2498 -0
- tinyllama-lora-finetuned/checkpoint-7059/training_args.bin +3 -0
tinyllama-lora-finetuned/checkpoint-4706/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.15.2
|
tinyllama-lora-finetuned/checkpoint-4706/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.1,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 16,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"v_proj",
|
| 28 |
+
"q_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"trainable_token_indices": null,
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
tinyllama-lora-finetuned/checkpoint-4706/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a03f9fe5a795b8ddff1fb2226e37eb7df60c2dac17ea99e0f1a9985584d57c5
|
| 3 |
+
size 9022864
|
tinyllama-lora-finetuned/checkpoint-4706/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cefc93a39af6182f78f286b71170117c179e59605b663ab45c48f65d2c22e9a5
|
| 3 |
+
size 18096570
|
tinyllama-lora-finetuned/checkpoint-4706/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c584307684d968aca52148948545374b3367dba87f3fcf85395b87b488dd9bcf
|
| 3 |
+
size 14244
|
tinyllama-lora-finetuned/checkpoint-4706/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0e57fc822cae603542453ce834ab7d91378cdff04ad8bd2c3e5ec87bd5f66dc
|
| 3 |
+
size 988
|
tinyllama-lora-finetuned/checkpoint-4706/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31c891b9346c8dcc7999087526c82dc11ff9de250c4c17471f20e568a36c5028
|
| 3 |
+
size 1064
|
tinyllama-lora-finetuned/checkpoint-4706/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tinyllama-lora-finetuned/checkpoint-4706/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tinyllama-lora-finetuned/checkpoint-4706/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tinyllama-lora-finetuned/checkpoint-4706/tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"extra_special_tokens": {},
|
| 36 |
+
"legacy": false,
|
| 37 |
+
"model_max_length": 2048,
|
| 38 |
+
"pad_token": "</s>",
|
| 39 |
+
"padding_side": "right",
|
| 40 |
+
"sp_model_kwargs": {},
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false
|
| 44 |
+
}
|
tinyllama-lora-finetuned/checkpoint-4706/trainer_state.json
ADDED
|
@@ -0,0 +1,1679 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4706,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.008499787505312367,
|
| 14 |
+
"grad_norm": 1.8467686176300049,
|
| 15 |
+
"learning_rate": 0.00019946168012466354,
|
| 16 |
+
"loss": 2.1643,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.016999575010624733,
|
| 21 |
+
"grad_norm": 2.2261719703674316,
|
| 22 |
+
"learning_rate": 0.0001988950276243094,
|
| 23 |
+
"loss": 1.7448,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.025499362515937103,
|
| 28 |
+
"grad_norm": 1.9097844362258911,
|
| 29 |
+
"learning_rate": 0.00019832837512395523,
|
| 30 |
+
"loss": 1.702,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.033999150021249466,
|
| 35 |
+
"grad_norm": 1.676216721534729,
|
| 36 |
+
"learning_rate": 0.00019776172262360109,
|
| 37 |
+
"loss": 1.7414,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.042498937526561836,
|
| 42 |
+
"grad_norm": 1.7480692863464355,
|
| 43 |
+
"learning_rate": 0.00019719507012324694,
|
| 44 |
+
"loss": 1.6,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.050998725031874206,
|
| 49 |
+
"grad_norm": 1.603786826133728,
|
| 50 |
+
"learning_rate": 0.00019662841762289277,
|
| 51 |
+
"loss": 1.72,
|
| 52 |
+
"step": 120
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.05949851253718657,
|
| 56 |
+
"grad_norm": 1.577128529548645,
|
| 57 |
+
"learning_rate": 0.00019606176512253863,
|
| 58 |
+
"loss": 1.6804,
|
| 59 |
+
"step": 140
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06799830004249893,
|
| 63 |
+
"grad_norm": 1.5658762454986572,
|
| 64 |
+
"learning_rate": 0.00019549511262218446,
|
| 65 |
+
"loss": 1.6582,
|
| 66 |
+
"step": 160
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0764980875478113,
|
| 70 |
+
"grad_norm": 1.7549939155578613,
|
| 71 |
+
"learning_rate": 0.00019492846012183031,
|
| 72 |
+
"loss": 1.6238,
|
| 73 |
+
"step": 180
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.08499787505312367,
|
| 77 |
+
"grad_norm": 1.490046501159668,
|
| 78 |
+
"learning_rate": 0.00019436180762147614,
|
| 79 |
+
"loss": 1.6661,
|
| 80 |
+
"step": 200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.09349766255843604,
|
| 84 |
+
"grad_norm": 1.7966225147247314,
|
| 85 |
+
"learning_rate": 0.00019379515512112197,
|
| 86 |
+
"loss": 1.6258,
|
| 87 |
+
"step": 220
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.10199745006374841,
|
| 91 |
+
"grad_norm": 1.6181796789169312,
|
| 92 |
+
"learning_rate": 0.00019322850262076783,
|
| 93 |
+
"loss": 1.6042,
|
| 94 |
+
"step": 240
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.11049723756906077,
|
| 98 |
+
"grad_norm": 1.4492865800857544,
|
| 99 |
+
"learning_rate": 0.00019266185012041366,
|
| 100 |
+
"loss": 1.5649,
|
| 101 |
+
"step": 260
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.11899702507437314,
|
| 105 |
+
"grad_norm": 2.01737117767334,
|
| 106 |
+
"learning_rate": 0.0001920951976200595,
|
| 107 |
+
"loss": 1.6877,
|
| 108 |
+
"step": 280
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1274968125796855,
|
| 112 |
+
"grad_norm": 1.4284173250198364,
|
| 113 |
+
"learning_rate": 0.00019152854511970534,
|
| 114 |
+
"loss": 1.5727,
|
| 115 |
+
"step": 300
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.13599660008499787,
|
| 119 |
+
"grad_norm": 1.4602673053741455,
|
| 120 |
+
"learning_rate": 0.0001909618926193512,
|
| 121 |
+
"loss": 1.5837,
|
| 122 |
+
"step": 320
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14449638759031025,
|
| 126 |
+
"grad_norm": 1.6680593490600586,
|
| 127 |
+
"learning_rate": 0.00019039524011899703,
|
| 128 |
+
"loss": 1.6122,
|
| 129 |
+
"step": 340
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1529961750956226,
|
| 133 |
+
"grad_norm": 1.4604177474975586,
|
| 134 |
+
"learning_rate": 0.00018982858761864288,
|
| 135 |
+
"loss": 1.6064,
|
| 136 |
+
"step": 360
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.161495962600935,
|
| 140 |
+
"grad_norm": 1.4658399820327759,
|
| 141 |
+
"learning_rate": 0.00018926193511828871,
|
| 142 |
+
"loss": 1.5842,
|
| 143 |
+
"step": 380
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.16999575010624735,
|
| 147 |
+
"grad_norm": 1.2307661771774292,
|
| 148 |
+
"learning_rate": 0.00018869528261793457,
|
| 149 |
+
"loss": 1.6023,
|
| 150 |
+
"step": 400
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.1784955376115597,
|
| 154 |
+
"grad_norm": 1.4648102521896362,
|
| 155 |
+
"learning_rate": 0.0001881286301175804,
|
| 156 |
+
"loss": 1.5484,
|
| 157 |
+
"step": 420
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.18699532511687209,
|
| 161 |
+
"grad_norm": 1.4780811071395874,
|
| 162 |
+
"learning_rate": 0.00018756197761722626,
|
| 163 |
+
"loss": 1.5009,
|
| 164 |
+
"step": 440
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.19549511262218444,
|
| 168 |
+
"grad_norm": 1.4852784872055054,
|
| 169 |
+
"learning_rate": 0.00018699532511687208,
|
| 170 |
+
"loss": 1.6116,
|
| 171 |
+
"step": 460
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.20399490012749683,
|
| 175 |
+
"grad_norm": 1.4338926076889038,
|
| 176 |
+
"learning_rate": 0.00018642867261651794,
|
| 177 |
+
"loss": 1.6025,
|
| 178 |
+
"step": 480
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.21249468763280918,
|
| 182 |
+
"grad_norm": 1.5596784353256226,
|
| 183 |
+
"learning_rate": 0.00018586202011616377,
|
| 184 |
+
"loss": 1.6212,
|
| 185 |
+
"step": 500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.22099447513812154,
|
| 189 |
+
"grad_norm": 1.2840818166732788,
|
| 190 |
+
"learning_rate": 0.0001852953676158096,
|
| 191 |
+
"loss": 1.6135,
|
| 192 |
+
"step": 520
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.22949426264343392,
|
| 196 |
+
"grad_norm": 1.5443825721740723,
|
| 197 |
+
"learning_rate": 0.00018472871511545546,
|
| 198 |
+
"loss": 1.5785,
|
| 199 |
+
"step": 540
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.23799405014874628,
|
| 203 |
+
"grad_norm": 1.5090241432189941,
|
| 204 |
+
"learning_rate": 0.00018416206261510129,
|
| 205 |
+
"loss": 1.5871,
|
| 206 |
+
"step": 560
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.24649383765405866,
|
| 210 |
+
"grad_norm": 1.613731861114502,
|
| 211 |
+
"learning_rate": 0.00018359541011474714,
|
| 212 |
+
"loss": 1.604,
|
| 213 |
+
"step": 580
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.254993625159371,
|
| 217 |
+
"grad_norm": 1.354567289352417,
|
| 218 |
+
"learning_rate": 0.00018302875761439297,
|
| 219 |
+
"loss": 1.4996,
|
| 220 |
+
"step": 600
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.2634934126646834,
|
| 224 |
+
"grad_norm": 1.5025413036346436,
|
| 225 |
+
"learning_rate": 0.00018246210511403883,
|
| 226 |
+
"loss": 1.5923,
|
| 227 |
+
"step": 620
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.27199320016999573,
|
| 231 |
+
"grad_norm": 1.3449057340621948,
|
| 232 |
+
"learning_rate": 0.00018189545261368466,
|
| 233 |
+
"loss": 1.5435,
|
| 234 |
+
"step": 640
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2804929876753081,
|
| 238 |
+
"grad_norm": 1.2846812009811401,
|
| 239 |
+
"learning_rate": 0.0001813288001133305,
|
| 240 |
+
"loss": 1.536,
|
| 241 |
+
"step": 660
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2889927751806205,
|
| 245 |
+
"grad_norm": 1.3012146949768066,
|
| 246 |
+
"learning_rate": 0.00018076214761297634,
|
| 247 |
+
"loss": 1.539,
|
| 248 |
+
"step": 680
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.2974925626859328,
|
| 252 |
+
"grad_norm": 1.5017261505126953,
|
| 253 |
+
"learning_rate": 0.0001801954951126222,
|
| 254 |
+
"loss": 1.5727,
|
| 255 |
+
"step": 700
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3059923501912452,
|
| 259 |
+
"grad_norm": 1.3044496774673462,
|
| 260 |
+
"learning_rate": 0.00017962884261226805,
|
| 261 |
+
"loss": 1.6619,
|
| 262 |
+
"step": 720
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.3144921376965576,
|
| 266 |
+
"grad_norm": 1.6723718643188477,
|
| 267 |
+
"learning_rate": 0.00017906219011191388,
|
| 268 |
+
"loss": 1.5572,
|
| 269 |
+
"step": 740
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.32299192520187,
|
| 273 |
+
"grad_norm": 1.5928444862365723,
|
| 274 |
+
"learning_rate": 0.00017849553761155974,
|
| 275 |
+
"loss": 1.4755,
|
| 276 |
+
"step": 760
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.3314917127071823,
|
| 280 |
+
"grad_norm": 1.2782012224197388,
|
| 281 |
+
"learning_rate": 0.00017792888511120557,
|
| 282 |
+
"loss": 1.592,
|
| 283 |
+
"step": 780
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3399915002124947,
|
| 287 |
+
"grad_norm": 1.349767804145813,
|
| 288 |
+
"learning_rate": 0.0001773622326108514,
|
| 289 |
+
"loss": 1.5436,
|
| 290 |
+
"step": 800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.3484912877178071,
|
| 294 |
+
"grad_norm": 1.4979254007339478,
|
| 295 |
+
"learning_rate": 0.00017679558011049723,
|
| 296 |
+
"loss": 1.6191,
|
| 297 |
+
"step": 820
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3569910752231194,
|
| 301 |
+
"grad_norm": 1.5227205753326416,
|
| 302 |
+
"learning_rate": 0.00017622892761014308,
|
| 303 |
+
"loss": 1.6074,
|
| 304 |
+
"step": 840
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3654908627284318,
|
| 308 |
+
"grad_norm": 1.300671100616455,
|
| 309 |
+
"learning_rate": 0.0001756622751097889,
|
| 310 |
+
"loss": 1.5877,
|
| 311 |
+
"step": 860
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.37399065023374417,
|
| 315 |
+
"grad_norm": 1.1968013048171997,
|
| 316 |
+
"learning_rate": 0.00017509562260943477,
|
| 317 |
+
"loss": 1.5343,
|
| 318 |
+
"step": 880
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3824904377390565,
|
| 322 |
+
"grad_norm": 1.4233676195144653,
|
| 323 |
+
"learning_rate": 0.00017452897010908063,
|
| 324 |
+
"loss": 1.5093,
|
| 325 |
+
"step": 900
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.3909902252443689,
|
| 329 |
+
"grad_norm": 1.5608493089675903,
|
| 330 |
+
"learning_rate": 0.00017396231760872645,
|
| 331 |
+
"loss": 1.552,
|
| 332 |
+
"step": 920
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.39949001274968127,
|
| 336 |
+
"grad_norm": 1.6073567867279053,
|
| 337 |
+
"learning_rate": 0.0001733956651083723,
|
| 338 |
+
"loss": 1.551,
|
| 339 |
+
"step": 940
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.40798980025499365,
|
| 343 |
+
"grad_norm": 1.1513320207595825,
|
| 344 |
+
"learning_rate": 0.00017282901260801814,
|
| 345 |
+
"loss": 1.51,
|
| 346 |
+
"step": 960
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.416489587760306,
|
| 350 |
+
"grad_norm": 1.3810391426086426,
|
| 351 |
+
"learning_rate": 0.000172262360107664,
|
| 352 |
+
"loss": 1.5447,
|
| 353 |
+
"step": 980
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.42498937526561836,
|
| 357 |
+
"grad_norm": 1.4732245206832886,
|
| 358 |
+
"learning_rate": 0.00017169570760730983,
|
| 359 |
+
"loss": 1.5781,
|
| 360 |
+
"step": 1000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.43348916277093075,
|
| 364 |
+
"grad_norm": 1.1698389053344727,
|
| 365 |
+
"learning_rate": 0.00017112905510695568,
|
| 366 |
+
"loss": 1.5205,
|
| 367 |
+
"step": 1020
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.4419889502762431,
|
| 371 |
+
"grad_norm": 1.49894118309021,
|
| 372 |
+
"learning_rate": 0.0001705624026066015,
|
| 373 |
+
"loss": 1.6071,
|
| 374 |
+
"step": 1040
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.45048873778155546,
|
| 378 |
+
"grad_norm": 1.3100991249084473,
|
| 379 |
+
"learning_rate": 0.00016999575010624734,
|
| 380 |
+
"loss": 1.6148,
|
| 381 |
+
"step": 1060
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.45898852528686784,
|
| 385 |
+
"grad_norm": 1.5139139890670776,
|
| 386 |
+
"learning_rate": 0.0001694290976058932,
|
| 387 |
+
"loss": 1.5657,
|
| 388 |
+
"step": 1080
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.46748831279218017,
|
| 392 |
+
"grad_norm": 1.3952980041503906,
|
| 393 |
+
"learning_rate": 0.00016886244510553903,
|
| 394 |
+
"loss": 1.5596,
|
| 395 |
+
"step": 1100
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.47598810029749256,
|
| 399 |
+
"grad_norm": 1.2251731157302856,
|
| 400 |
+
"learning_rate": 0.00016829579260518488,
|
| 401 |
+
"loss": 1.5207,
|
| 402 |
+
"step": 1120
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.48448788780280494,
|
| 406 |
+
"grad_norm": 1.4944117069244385,
|
| 407 |
+
"learning_rate": 0.0001677291401048307,
|
| 408 |
+
"loss": 1.562,
|
| 409 |
+
"step": 1140
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.4929876753081173,
|
| 413 |
+
"grad_norm": 1.2576520442962646,
|
| 414 |
+
"learning_rate": 0.00016716248760447657,
|
| 415 |
+
"loss": 1.5362,
|
| 416 |
+
"step": 1160
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5014874628134297,
|
| 420 |
+
"grad_norm": 1.3012641668319702,
|
| 421 |
+
"learning_rate": 0.0001665958351041224,
|
| 422 |
+
"loss": 1.5384,
|
| 423 |
+
"step": 1180
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.509987250318742,
|
| 427 |
+
"grad_norm": 1.3370224237442017,
|
| 428 |
+
"learning_rate": 0.00016602918260376825,
|
| 429 |
+
"loss": 1.5406,
|
| 430 |
+
"step": 1200
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5184870378240544,
|
| 434 |
+
"grad_norm": 1.4711674451828003,
|
| 435 |
+
"learning_rate": 0.00016546253010341408,
|
| 436 |
+
"loss": 1.5489,
|
| 437 |
+
"step": 1220
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.5269868253293668,
|
| 441 |
+
"grad_norm": 1.3889433145523071,
|
| 442 |
+
"learning_rate": 0.00016489587760305994,
|
| 443 |
+
"loss": 1.5683,
|
| 444 |
+
"step": 1240
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5354866128346791,
|
| 448 |
+
"grad_norm": 1.181380271911621,
|
| 449 |
+
"learning_rate": 0.00016432922510270577,
|
| 450 |
+
"loss": 1.5282,
|
| 451 |
+
"step": 1260
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5439864003399915,
|
| 455 |
+
"grad_norm": 1.2874456644058228,
|
| 456 |
+
"learning_rate": 0.00016376257260235162,
|
| 457 |
+
"loss": 1.5642,
|
| 458 |
+
"step": 1280
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.5524861878453039,
|
| 462 |
+
"grad_norm": 1.2181987762451172,
|
| 463 |
+
"learning_rate": 0.00016319592010199748,
|
| 464 |
+
"loss": 1.5324,
|
| 465 |
+
"step": 1300
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.5609859753506162,
|
| 469 |
+
"grad_norm": 1.4149408340454102,
|
| 470 |
+
"learning_rate": 0.0001626292676016433,
|
| 471 |
+
"loss": 1.5366,
|
| 472 |
+
"step": 1320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5694857628559286,
|
| 476 |
+
"grad_norm": 1.1893357038497925,
|
| 477 |
+
"learning_rate": 0.00016206261510128914,
|
| 478 |
+
"loss": 1.5386,
|
| 479 |
+
"step": 1340
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.577985550361241,
|
| 483 |
+
"grad_norm": 1.4138270616531372,
|
| 484 |
+
"learning_rate": 0.00016149596260093497,
|
| 485 |
+
"loss": 1.4789,
|
| 486 |
+
"step": 1360
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.5864853378665533,
|
| 490 |
+
"grad_norm": 1.5200152397155762,
|
| 491 |
+
"learning_rate": 0.00016092931010058082,
|
| 492 |
+
"loss": 1.5012,
|
| 493 |
+
"step": 1380
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.5949851253718657,
|
| 497 |
+
"grad_norm": 1.2447080612182617,
|
| 498 |
+
"learning_rate": 0.00016036265760022665,
|
| 499 |
+
"loss": 1.498,
|
| 500 |
+
"step": 1400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6034849128771781,
|
| 504 |
+
"grad_norm": 1.4135057926177979,
|
| 505 |
+
"learning_rate": 0.0001597960050998725,
|
| 506 |
+
"loss": 1.4519,
|
| 507 |
+
"step": 1420
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.6119847003824904,
|
| 511 |
+
"grad_norm": 1.2652864456176758,
|
| 512 |
+
"learning_rate": 0.00015922935259951834,
|
| 513 |
+
"loss": 1.5595,
|
| 514 |
+
"step": 1440
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6204844878878029,
|
| 518 |
+
"grad_norm": 1.356728434562683,
|
| 519 |
+
"learning_rate": 0.0001586627000991642,
|
| 520 |
+
"loss": 1.4859,
|
| 521 |
+
"step": 1460
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.6289842753931152,
|
| 525 |
+
"grad_norm": 1.3269623517990112,
|
| 526 |
+
"learning_rate": 0.00015809604759881002,
|
| 527 |
+
"loss": 1.5002,
|
| 528 |
+
"step": 1480
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.6374840628984275,
|
| 532 |
+
"grad_norm": 1.5896166563034058,
|
| 533 |
+
"learning_rate": 0.00015752939509845588,
|
| 534 |
+
"loss": 1.4852,
|
| 535 |
+
"step": 1500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.64598385040374,
|
| 539 |
+
"grad_norm": 1.5948361158370972,
|
| 540 |
+
"learning_rate": 0.00015696274259810174,
|
| 541 |
+
"loss": 1.5728,
|
| 542 |
+
"step": 1520
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.6544836379090523,
|
| 546 |
+
"grad_norm": 1.3188483715057373,
|
| 547 |
+
"learning_rate": 0.00015639609009774757,
|
| 548 |
+
"loss": 1.5287,
|
| 549 |
+
"step": 1540
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6629834254143646,
|
| 553 |
+
"grad_norm": 1.2547403573989868,
|
| 554 |
+
"learning_rate": 0.00015582943759739342,
|
| 555 |
+
"loss": 1.4523,
|
| 556 |
+
"step": 1560
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.671483212919677,
|
| 560 |
+
"grad_norm": 1.3939685821533203,
|
| 561 |
+
"learning_rate": 0.00015526278509703925,
|
| 562 |
+
"loss": 1.4659,
|
| 563 |
+
"step": 1580
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6799830004249894,
|
| 567 |
+
"grad_norm": 1.1834455728530884,
|
| 568 |
+
"learning_rate": 0.0001546961325966851,
|
| 569 |
+
"loss": 1.4674,
|
| 570 |
+
"step": 1600
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6884827879303017,
|
| 574 |
+
"grad_norm": 1.5032856464385986,
|
| 575 |
+
"learning_rate": 0.00015412948009633094,
|
| 576 |
+
"loss": 1.6103,
|
| 577 |
+
"step": 1620
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6969825754356141,
|
| 581 |
+
"grad_norm": 1.4383857250213623,
|
| 582 |
+
"learning_rate": 0.00015356282759597677,
|
| 583 |
+
"loss": 1.5483,
|
| 584 |
+
"step": 1640
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.7054823629409265,
|
| 588 |
+
"grad_norm": 1.2931615114212036,
|
| 589 |
+
"learning_rate": 0.0001529961750956226,
|
| 590 |
+
"loss": 1.5219,
|
| 591 |
+
"step": 1660
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.7139821504462388,
|
| 595 |
+
"grad_norm": 1.3393011093139648,
|
| 596 |
+
"learning_rate": 0.00015242952259526845,
|
| 597 |
+
"loss": 1.4984,
|
| 598 |
+
"step": 1680
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.7224819379515512,
|
| 602 |
+
"grad_norm": 1.372475266456604,
|
| 603 |
+
"learning_rate": 0.0001518628700949143,
|
| 604 |
+
"loss": 1.4966,
|
| 605 |
+
"step": 1700
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.7309817254568636,
|
| 609 |
+
"grad_norm": 1.4294521808624268,
|
| 610 |
+
"learning_rate": 0.00015129621759456014,
|
| 611 |
+
"loss": 1.4844,
|
| 612 |
+
"step": 1720
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.7394815129621759,
|
| 616 |
+
"grad_norm": 1.5531823635101318,
|
| 617 |
+
"learning_rate": 0.000150729565094206,
|
| 618 |
+
"loss": 1.5581,
|
| 619 |
+
"step": 1740
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.7479813004674883,
|
| 623 |
+
"grad_norm": 1.5481995344161987,
|
| 624 |
+
"learning_rate": 0.00015016291259385182,
|
| 625 |
+
"loss": 1.5487,
|
| 626 |
+
"step": 1760
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.7564810879728007,
|
| 630 |
+
"grad_norm": 1.4445319175720215,
|
| 631 |
+
"learning_rate": 0.00014959626009349768,
|
| 632 |
+
"loss": 1.5389,
|
| 633 |
+
"step": 1780
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.764980875478113,
|
| 637 |
+
"grad_norm": 1.538258671760559,
|
| 638 |
+
"learning_rate": 0.0001490296075931435,
|
| 639 |
+
"loss": 1.5034,
|
| 640 |
+
"step": 1800
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.7734806629834254,
|
| 644 |
+
"grad_norm": 1.4794244766235352,
|
| 645 |
+
"learning_rate": 0.00014846295509278936,
|
| 646 |
+
"loss": 1.4403,
|
| 647 |
+
"step": 1820
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.7819804504887378,
|
| 651 |
+
"grad_norm": 1.3663828372955322,
|
| 652 |
+
"learning_rate": 0.0001478963025924352,
|
| 653 |
+
"loss": 1.5626,
|
| 654 |
+
"step": 1840
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7904802379940501,
|
| 658 |
+
"grad_norm": 1.6889076232910156,
|
| 659 |
+
"learning_rate": 0.00014732965009208105,
|
| 660 |
+
"loss": 1.4974,
|
| 661 |
+
"step": 1860
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.7989800254993625,
|
| 665 |
+
"grad_norm": 1.4024620056152344,
|
| 666 |
+
"learning_rate": 0.00014676299759172688,
|
| 667 |
+
"loss": 1.5809,
|
| 668 |
+
"step": 1880
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8074798130046749,
|
| 672 |
+
"grad_norm": 1.3137383460998535,
|
| 673 |
+
"learning_rate": 0.00014619634509137274,
|
| 674 |
+
"loss": 1.5202,
|
| 675 |
+
"step": 1900
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.8159796005099873,
|
| 679 |
+
"grad_norm": 1.5561782121658325,
|
| 680 |
+
"learning_rate": 0.00014562969259101856,
|
| 681 |
+
"loss": 1.4611,
|
| 682 |
+
"step": 1920
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.8244793880152996,
|
| 686 |
+
"grad_norm": 1.4386446475982666,
|
| 687 |
+
"learning_rate": 0.0001450630400906644,
|
| 688 |
+
"loss": 1.5364,
|
| 689 |
+
"step": 1940
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.832979175520612,
|
| 693 |
+
"grad_norm": 1.4223254919052124,
|
| 694 |
+
"learning_rate": 0.00014452472021532796,
|
| 695 |
+
"loss": 1.4866,
|
| 696 |
+
"step": 1960
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.8414789630259244,
|
| 700 |
+
"grad_norm": 1.290819525718689,
|
| 701 |
+
"learning_rate": 0.0001439580677149738,
|
| 702 |
+
"loss": 1.5182,
|
| 703 |
+
"step": 1980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.8499787505312367,
|
| 707 |
+
"grad_norm": 1.3473018407821655,
|
| 708 |
+
"learning_rate": 0.00014339141521461964,
|
| 709 |
+
"loss": 1.4962,
|
| 710 |
+
"step": 2000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.858478538036549,
|
| 714 |
+
"grad_norm": 1.480664849281311,
|
| 715 |
+
"learning_rate": 0.00014282476271426547,
|
| 716 |
+
"loss": 1.5277,
|
| 717 |
+
"step": 2020
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8669783255418615,
|
| 721 |
+
"grad_norm": 1.4417237043380737,
|
| 722 |
+
"learning_rate": 0.00014225811021391133,
|
| 723 |
+
"loss": 1.4646,
|
| 724 |
+
"step": 2040
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.8754781130471738,
|
| 728 |
+
"grad_norm": 1.3464792966842651,
|
| 729 |
+
"learning_rate": 0.00014169145771355716,
|
| 730 |
+
"loss": 1.5028,
|
| 731 |
+
"step": 2060
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.8839779005524862,
|
| 735 |
+
"grad_norm": 1.4068652391433716,
|
| 736 |
+
"learning_rate": 0.000141124805213203,
|
| 737 |
+
"loss": 1.5142,
|
| 738 |
+
"step": 2080
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.8924776880577986,
|
| 742 |
+
"grad_norm": 1.321798324584961,
|
| 743 |
+
"learning_rate": 0.00014055815271284884,
|
| 744 |
+
"loss": 1.5505,
|
| 745 |
+
"step": 2100
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.9009774755631109,
|
| 749 |
+
"grad_norm": 1.38119375705719,
|
| 750 |
+
"learning_rate": 0.0001399915002124947,
|
| 751 |
+
"loss": 1.5606,
|
| 752 |
+
"step": 2120
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.9094772630684232,
|
| 756 |
+
"grad_norm": 1.4736709594726562,
|
| 757 |
+
"learning_rate": 0.00013942484771214053,
|
| 758 |
+
"loss": 1.5104,
|
| 759 |
+
"step": 2140
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.9179770505737357,
|
| 763 |
+
"grad_norm": 1.5708409547805786,
|
| 764 |
+
"learning_rate": 0.00013885819521178638,
|
| 765 |
+
"loss": 1.5129,
|
| 766 |
+
"step": 2160
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.926476838079048,
|
| 770 |
+
"grad_norm": 1.2119626998901367,
|
| 771 |
+
"learning_rate": 0.00013829154271143224,
|
| 772 |
+
"loss": 1.5139,
|
| 773 |
+
"step": 2180
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.9349766255843603,
|
| 777 |
+
"grad_norm": 1.4460374116897583,
|
| 778 |
+
"learning_rate": 0.00013772489021107807,
|
| 779 |
+
"loss": 1.5176,
|
| 780 |
+
"step": 2200
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.9434764130896728,
|
| 784 |
+
"grad_norm": 1.377457618713379,
|
| 785 |
+
"learning_rate": 0.00013715823771072392,
|
| 786 |
+
"loss": 1.4846,
|
| 787 |
+
"step": 2220
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.9519762005949851,
|
| 791 |
+
"grad_norm": 1.5439783334732056,
|
| 792 |
+
"learning_rate": 0.00013659158521036975,
|
| 793 |
+
"loss": 1.4432,
|
| 794 |
+
"step": 2240
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.9604759881002974,
|
| 798 |
+
"grad_norm": 1.3697561025619507,
|
| 799 |
+
"learning_rate": 0.00013602493271001558,
|
| 800 |
+
"loss": 1.5054,
|
| 801 |
+
"step": 2260
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.9689757756056099,
|
| 805 |
+
"grad_norm": 1.6576790809631348,
|
| 806 |
+
"learning_rate": 0.0001354582802096614,
|
| 807 |
+
"loss": 1.5202,
|
| 808 |
+
"step": 2280
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.9774755631109222,
|
| 812 |
+
"grad_norm": 1.2522470951080322,
|
| 813 |
+
"learning_rate": 0.00013489162770930727,
|
| 814 |
+
"loss": 1.5237,
|
| 815 |
+
"step": 2300
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.9859753506162346,
|
| 819 |
+
"grad_norm": 1.316643476486206,
|
| 820 |
+
"learning_rate": 0.0001343249752089531,
|
| 821 |
+
"loss": 1.4693,
|
| 822 |
+
"step": 2320
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.994475138121547,
|
| 826 |
+
"grad_norm": 1.415403127670288,
|
| 827 |
+
"learning_rate": 0.00013375832270859895,
|
| 828 |
+
"loss": 1.5064,
|
| 829 |
+
"step": 2340
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0029749256268594,
|
| 833 |
+
"grad_norm": 1.2021781206130981,
|
| 834 |
+
"learning_rate": 0.00013319167020824478,
|
| 835 |
+
"loss": 1.4576,
|
| 836 |
+
"step": 2360
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.0114747131321717,
|
| 840 |
+
"grad_norm": 1.391981840133667,
|
| 841 |
+
"learning_rate": 0.00013262501770789064,
|
| 842 |
+
"loss": 1.4672,
|
| 843 |
+
"step": 2380
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.019974500637484,
|
| 847 |
+
"grad_norm": 1.6223762035369873,
|
| 848 |
+
"learning_rate": 0.0001320583652075365,
|
| 849 |
+
"loss": 1.4746,
|
| 850 |
+
"step": 2400
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.0284742881427964,
|
| 854 |
+
"grad_norm": 1.584978699684143,
|
| 855 |
+
"learning_rate": 0.00013149171270718233,
|
| 856 |
+
"loss": 1.446,
|
| 857 |
+
"step": 2420
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.0369740756481087,
|
| 861 |
+
"grad_norm": 1.3905613422393799,
|
| 862 |
+
"learning_rate": 0.00013092506020682818,
|
| 863 |
+
"loss": 1.4673,
|
| 864 |
+
"step": 2440
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.045473863153421,
|
| 868 |
+
"grad_norm": 1.3543156385421753,
|
| 869 |
+
"learning_rate": 0.000130358407706474,
|
| 870 |
+
"loss": 1.4774,
|
| 871 |
+
"step": 2460
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.0539736506587336,
|
| 875 |
+
"grad_norm": 1.4284417629241943,
|
| 876 |
+
"learning_rate": 0.00012979175520611987,
|
| 877 |
+
"loss": 1.4828,
|
| 878 |
+
"step": 2480
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.062473438164046,
|
| 882 |
+
"grad_norm": 1.2880805730819702,
|
| 883 |
+
"learning_rate": 0.0001292251027057657,
|
| 884 |
+
"loss": 1.4688,
|
| 885 |
+
"step": 2500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.0709732256693583,
|
| 889 |
+
"grad_norm": 1.4029446840286255,
|
| 890 |
+
"learning_rate": 0.00012865845020541155,
|
| 891 |
+
"loss": 1.4667,
|
| 892 |
+
"step": 2520
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.0794730131746706,
|
| 896 |
+
"grad_norm": 1.4345691204071045,
|
| 897 |
+
"learning_rate": 0.00012809179770505738,
|
| 898 |
+
"loss": 1.4268,
|
| 899 |
+
"step": 2540
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.087972800679983,
|
| 903 |
+
"grad_norm": 1.5828334093093872,
|
| 904 |
+
"learning_rate": 0.0001275251452047032,
|
| 905 |
+
"loss": 1.3897,
|
| 906 |
+
"step": 2560
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.0964725881852955,
|
| 910 |
+
"grad_norm": 1.8496978282928467,
|
| 911 |
+
"learning_rate": 0.00012695849270434907,
|
| 912 |
+
"loss": 1.4783,
|
| 913 |
+
"step": 2580
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.1049723756906078,
|
| 917 |
+
"grad_norm": 1.756039023399353,
|
| 918 |
+
"learning_rate": 0.0001263918402039949,
|
| 919 |
+
"loss": 1.4611,
|
| 920 |
+
"step": 2600
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.1134721631959201,
|
| 924 |
+
"grad_norm": 1.3964674472808838,
|
| 925 |
+
"learning_rate": 0.00012582518770364075,
|
| 926 |
+
"loss": 1.4139,
|
| 927 |
+
"step": 2620
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.1219719507012325,
|
| 931 |
+
"grad_norm": 1.7207622528076172,
|
| 932 |
+
"learning_rate": 0.00012525853520328658,
|
| 933 |
+
"loss": 1.4206,
|
| 934 |
+
"step": 2640
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.1304717382065448,
|
| 938 |
+
"grad_norm": 1.4870052337646484,
|
| 939 |
+
"learning_rate": 0.00012469188270293244,
|
| 940 |
+
"loss": 1.3631,
|
| 941 |
+
"step": 2660
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.1389715257118571,
|
| 945 |
+
"grad_norm": 1.4430071115493774,
|
| 946 |
+
"learning_rate": 0.00012412523020257827,
|
| 947 |
+
"loss": 1.4766,
|
| 948 |
+
"step": 2680
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.1474713132171697,
|
| 952 |
+
"grad_norm": 1.5112409591674805,
|
| 953 |
+
"learning_rate": 0.00012355857770222412,
|
| 954 |
+
"loss": 1.461,
|
| 955 |
+
"step": 2700
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.155971100722482,
|
| 959 |
+
"grad_norm": 1.4189656972885132,
|
| 960 |
+
"learning_rate": 0.00012299192520186995,
|
| 961 |
+
"loss": 1.389,
|
| 962 |
+
"step": 2720
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.1644708882277943,
|
| 966 |
+
"grad_norm": 1.543331265449524,
|
| 967 |
+
"learning_rate": 0.0001224252727015158,
|
| 968 |
+
"loss": 1.4474,
|
| 969 |
+
"step": 2740
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.1729706757331066,
|
| 973 |
+
"grad_norm": 1.398582100868225,
|
| 974 |
+
"learning_rate": 0.00012185862020116164,
|
| 975 |
+
"loss": 1.4047,
|
| 976 |
+
"step": 2760
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.181470463238419,
|
| 980 |
+
"grad_norm": 1.3756153583526611,
|
| 981 |
+
"learning_rate": 0.00012129196770080748,
|
| 982 |
+
"loss": 1.4086,
|
| 983 |
+
"step": 2780
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.1899702507437313,
|
| 987 |
+
"grad_norm": 1.5835983753204346,
|
| 988 |
+
"learning_rate": 0.00012072531520045334,
|
| 989 |
+
"loss": 1.4855,
|
| 990 |
+
"step": 2800
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.1984700382490439,
|
| 994 |
+
"grad_norm": 1.516381025314331,
|
| 995 |
+
"learning_rate": 0.00012015866270009917,
|
| 996 |
+
"loss": 1.455,
|
| 997 |
+
"step": 2820
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.2069698257543562,
|
| 1001 |
+
"grad_norm": 1.2615922689437866,
|
| 1002 |
+
"learning_rate": 0.00011959201019974502,
|
| 1003 |
+
"loss": 1.4531,
|
| 1004 |
+
"step": 2840
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.2154696132596685,
|
| 1008 |
+
"grad_norm": 1.5319349765777588,
|
| 1009 |
+
"learning_rate": 0.00011902535769939085,
|
| 1010 |
+
"loss": 1.4098,
|
| 1011 |
+
"step": 2860
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.2239694007649808,
|
| 1015 |
+
"grad_norm": 1.384494423866272,
|
| 1016 |
+
"learning_rate": 0.0001184587051990367,
|
| 1017 |
+
"loss": 1.424,
|
| 1018 |
+
"step": 2880
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.2324691882702932,
|
| 1022 |
+
"grad_norm": 1.4936223030090332,
|
| 1023 |
+
"learning_rate": 0.00011789205269868254,
|
| 1024 |
+
"loss": 1.4409,
|
| 1025 |
+
"step": 2900
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.2409689757756057,
|
| 1029 |
+
"grad_norm": 1.8717914819717407,
|
| 1030 |
+
"learning_rate": 0.00011732540019832838,
|
| 1031 |
+
"loss": 1.4478,
|
| 1032 |
+
"step": 2920
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.249468763280918,
|
| 1036 |
+
"grad_norm": 1.5673747062683105,
|
| 1037 |
+
"learning_rate": 0.00011675874769797421,
|
| 1038 |
+
"loss": 1.4076,
|
| 1039 |
+
"step": 2940
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.2579685507862304,
|
| 1043 |
+
"grad_norm": 1.5353143215179443,
|
| 1044 |
+
"learning_rate": 0.00011619209519762007,
|
| 1045 |
+
"loss": 1.4527,
|
| 1046 |
+
"step": 2960
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.2664683382915427,
|
| 1050 |
+
"grad_norm": 1.5840922594070435,
|
| 1051 |
+
"learning_rate": 0.00011562544269726592,
|
| 1052 |
+
"loss": 1.4547,
|
| 1053 |
+
"step": 2980
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.274968125796855,
|
| 1057 |
+
"grad_norm": 1.432485580444336,
|
| 1058 |
+
"learning_rate": 0.00011505879019691175,
|
| 1059 |
+
"loss": 1.3915,
|
| 1060 |
+
"step": 3000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.2834679133021676,
|
| 1064 |
+
"grad_norm": 1.6025019884109497,
|
| 1065 |
+
"learning_rate": 0.0001144921376965576,
|
| 1066 |
+
"loss": 1.4778,
|
| 1067 |
+
"step": 3020
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.2919677008074797,
|
| 1071 |
+
"grad_norm": 1.446283221244812,
|
| 1072 |
+
"learning_rate": 0.00011392548519620342,
|
| 1073 |
+
"loss": 1.4232,
|
| 1074 |
+
"step": 3040
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.3004674883127922,
|
| 1078 |
+
"grad_norm": 1.770347237586975,
|
| 1079 |
+
"learning_rate": 0.00011335883269584928,
|
| 1080 |
+
"loss": 1.4471,
|
| 1081 |
+
"step": 3060
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.3089672758181046,
|
| 1085 |
+
"grad_norm": 1.6366223096847534,
|
| 1086 |
+
"learning_rate": 0.00011279218019549511,
|
| 1087 |
+
"loss": 1.3898,
|
| 1088 |
+
"step": 3080
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.317467063323417,
|
| 1092 |
+
"grad_norm": 1.6164251565933228,
|
| 1093 |
+
"learning_rate": 0.00011222552769514096,
|
| 1094 |
+
"loss": 1.4911,
|
| 1095 |
+
"step": 3100
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.3259668508287292,
|
| 1099 |
+
"grad_norm": 1.72907292842865,
|
| 1100 |
+
"learning_rate": 0.0001116588751947868,
|
| 1101 |
+
"loss": 1.4324,
|
| 1102 |
+
"step": 3120
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.3344666383340416,
|
| 1106 |
+
"grad_norm": 1.5645689964294434,
|
| 1107 |
+
"learning_rate": 0.00011109222269443265,
|
| 1108 |
+
"loss": 1.4571,
|
| 1109 |
+
"step": 3140
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.342966425839354,
|
| 1113 |
+
"grad_norm": 1.6170058250427246,
|
| 1114 |
+
"learning_rate": 0.00011052557019407848,
|
| 1115 |
+
"loss": 1.4016,
|
| 1116 |
+
"step": 3160
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.3514662133446664,
|
| 1120 |
+
"grad_norm": 1.806199312210083,
|
| 1121 |
+
"learning_rate": 0.00010995891769372432,
|
| 1122 |
+
"loss": 1.3691,
|
| 1123 |
+
"step": 3180
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.3599660008499788,
|
| 1127 |
+
"grad_norm": 1.3674649000167847,
|
| 1128 |
+
"learning_rate": 0.00010939226519337018,
|
| 1129 |
+
"loss": 1.3924,
|
| 1130 |
+
"step": 3200
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.368465788355291,
|
| 1134 |
+
"grad_norm": 1.7301322221755981,
|
| 1135 |
+
"learning_rate": 0.00010882561269301601,
|
| 1136 |
+
"loss": 1.4296,
|
| 1137 |
+
"step": 3220
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.3769655758606034,
|
| 1141 |
+
"grad_norm": 1.4442013502120972,
|
| 1142 |
+
"learning_rate": 0.00010825896019266186,
|
| 1143 |
+
"loss": 1.4403,
|
| 1144 |
+
"step": 3240
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.385465363365916,
|
| 1148 |
+
"grad_norm": 1.838722586631775,
|
| 1149 |
+
"learning_rate": 0.0001076923076923077,
|
| 1150 |
+
"loss": 1.4345,
|
| 1151 |
+
"step": 3260
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.3939651508712283,
|
| 1155 |
+
"grad_norm": 1.4899051189422607,
|
| 1156 |
+
"learning_rate": 0.00010712565519195355,
|
| 1157 |
+
"loss": 1.4075,
|
| 1158 |
+
"step": 3280
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.4024649383765406,
|
| 1162 |
+
"grad_norm": 1.5684807300567627,
|
| 1163 |
+
"learning_rate": 0.00010655900269159938,
|
| 1164 |
+
"loss": 1.3676,
|
| 1165 |
+
"step": 3300
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.410964725881853,
|
| 1169 |
+
"grad_norm": 1.5851366519927979,
|
| 1170 |
+
"learning_rate": 0.00010599235019124522,
|
| 1171 |
+
"loss": 1.4093,
|
| 1172 |
+
"step": 3320
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.4194645133871653,
|
| 1176 |
+
"grad_norm": 1.5306929349899292,
|
| 1177 |
+
"learning_rate": 0.00010542569769089105,
|
| 1178 |
+
"loss": 1.4281,
|
| 1179 |
+
"step": 3340
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.4279643008924776,
|
| 1183 |
+
"grad_norm": 1.798202633857727,
|
| 1184 |
+
"learning_rate": 0.00010485904519053691,
|
| 1185 |
+
"loss": 1.405,
|
| 1186 |
+
"step": 3360
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.43646408839779,
|
| 1190 |
+
"grad_norm": 1.725794792175293,
|
| 1191 |
+
"learning_rate": 0.00010429239269018276,
|
| 1192 |
+
"loss": 1.4055,
|
| 1193 |
+
"step": 3380
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.4449638759031025,
|
| 1197 |
+
"grad_norm": 1.4544621706008911,
|
| 1198 |
+
"learning_rate": 0.00010372574018982859,
|
| 1199 |
+
"loss": 1.4608,
|
| 1200 |
+
"step": 3400
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.4534636634084148,
|
| 1204 |
+
"grad_norm": 1.6607258319854736,
|
| 1205 |
+
"learning_rate": 0.00010315908768947445,
|
| 1206 |
+
"loss": 1.3565,
|
| 1207 |
+
"step": 3420
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.4619634509137271,
|
| 1211 |
+
"grad_norm": 1.3560140132904053,
|
| 1212 |
+
"learning_rate": 0.00010259243518912028,
|
| 1213 |
+
"loss": 1.4086,
|
| 1214 |
+
"step": 3440
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.4704632384190395,
|
| 1218 |
+
"grad_norm": 1.5847728252410889,
|
| 1219 |
+
"learning_rate": 0.00010202578268876612,
|
| 1220 |
+
"loss": 1.4006,
|
| 1221 |
+
"step": 3460
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.4789630259243518,
|
| 1225 |
+
"grad_norm": 1.555255651473999,
|
| 1226 |
+
"learning_rate": 0.00010145913018841195,
|
| 1227 |
+
"loss": 1.4639,
|
| 1228 |
+
"step": 3480
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.4874628134296644,
|
| 1232 |
+
"grad_norm": 1.389131784439087,
|
| 1233 |
+
"learning_rate": 0.0001008924776880578,
|
| 1234 |
+
"loss": 1.4167,
|
| 1235 |
+
"step": 3500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.4959626009349767,
|
| 1239 |
+
"grad_norm": 1.435861349105835,
|
| 1240 |
+
"learning_rate": 0.00010032582518770364,
|
| 1241 |
+
"loss": 1.4018,
|
| 1242 |
+
"step": 3520
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.504462388440289,
|
| 1246 |
+
"grad_norm": 2.1325809955596924,
|
| 1247 |
+
"learning_rate": 9.975917268734949e-05,
|
| 1248 |
+
"loss": 1.4261,
|
| 1249 |
+
"step": 3540
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.5129621759456013,
|
| 1253 |
+
"grad_norm": 1.6307079792022705,
|
| 1254 |
+
"learning_rate": 9.919252018699533e-05,
|
| 1255 |
+
"loss": 1.4596,
|
| 1256 |
+
"step": 3560
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.5214619634509137,
|
| 1260 |
+
"grad_norm": 1.5455667972564697,
|
| 1261 |
+
"learning_rate": 9.862586768664118e-05,
|
| 1262 |
+
"loss": 1.4111,
|
| 1263 |
+
"step": 3580
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.5299617509562262,
|
| 1267 |
+
"grad_norm": 1.3528661727905273,
|
| 1268 |
+
"learning_rate": 9.8059215186287e-05,
|
| 1269 |
+
"loss": 1.4634,
|
| 1270 |
+
"step": 3600
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.5384615384615383,
|
| 1274 |
+
"grad_norm": 1.477866768836975,
|
| 1275 |
+
"learning_rate": 9.749256268593285e-05,
|
| 1276 |
+
"loss": 1.503,
|
| 1277 |
+
"step": 3620
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.5469613259668509,
|
| 1281 |
+
"grad_norm": 1.5204942226409912,
|
| 1282 |
+
"learning_rate": 9.692591018557869e-05,
|
| 1283 |
+
"loss": 1.4811,
|
| 1284 |
+
"step": 3640
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.5554611134721632,
|
| 1288 |
+
"grad_norm": 1.5966800451278687,
|
| 1289 |
+
"learning_rate": 9.635925768522453e-05,
|
| 1290 |
+
"loss": 1.4768,
|
| 1291 |
+
"step": 3660
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.5639609009774755,
|
| 1295 |
+
"grad_norm": 1.538609504699707,
|
| 1296 |
+
"learning_rate": 9.579260518487039e-05,
|
| 1297 |
+
"loss": 1.4379,
|
| 1298 |
+
"step": 3680
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.572460688482788,
|
| 1302 |
+
"grad_norm": 1.6952332258224487,
|
| 1303 |
+
"learning_rate": 9.522595268451623e-05,
|
| 1304 |
+
"loss": 1.4503,
|
| 1305 |
+
"step": 3700
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.5809604759881002,
|
| 1309 |
+
"grad_norm": 1.4433083534240723,
|
| 1310 |
+
"learning_rate": 9.465930018416208e-05,
|
| 1311 |
+
"loss": 1.4461,
|
| 1312 |
+
"step": 3720
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.5894602634934127,
|
| 1316 |
+
"grad_norm": 1.6331605911254883,
|
| 1317 |
+
"learning_rate": 9.40926476838079e-05,
|
| 1318 |
+
"loss": 1.4212,
|
| 1319 |
+
"step": 3740
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.597960050998725,
|
| 1323 |
+
"grad_norm": 2.1244919300079346,
|
| 1324 |
+
"learning_rate": 9.352599518345375e-05,
|
| 1325 |
+
"loss": 1.3775,
|
| 1326 |
+
"step": 3760
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.6064598385040374,
|
| 1330 |
+
"grad_norm": 1.6804299354553223,
|
| 1331 |
+
"learning_rate": 9.295934268309959e-05,
|
| 1332 |
+
"loss": 1.4365,
|
| 1333 |
+
"step": 3780
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.6149596260093497,
|
| 1337 |
+
"grad_norm": 1.5793712139129639,
|
| 1338 |
+
"learning_rate": 9.239269018274543e-05,
|
| 1339 |
+
"loss": 1.3996,
|
| 1340 |
+
"step": 3800
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.623459413514662,
|
| 1344 |
+
"grad_norm": 1.646560788154602,
|
| 1345 |
+
"learning_rate": 9.182603768239128e-05,
|
| 1346 |
+
"loss": 1.4735,
|
| 1347 |
+
"step": 3820
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.6319592010199746,
|
| 1351 |
+
"grad_norm": 1.6244877576828003,
|
| 1352 |
+
"learning_rate": 9.125938518203712e-05,
|
| 1353 |
+
"loss": 1.4646,
|
| 1354 |
+
"step": 3840
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.6404589885252867,
|
| 1358 |
+
"grad_norm": 1.4168405532836914,
|
| 1359 |
+
"learning_rate": 9.069273268168296e-05,
|
| 1360 |
+
"loss": 1.3962,
|
| 1361 |
+
"step": 3860
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.6489587760305993,
|
| 1365 |
+
"grad_norm": 1.4018287658691406,
|
| 1366 |
+
"learning_rate": 9.01260801813288e-05,
|
| 1367 |
+
"loss": 1.3747,
|
| 1368 |
+
"step": 3880
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.6574585635359116,
|
| 1372 |
+
"grad_norm": 1.3393577337265015,
|
| 1373 |
+
"learning_rate": 8.955942768097465e-05,
|
| 1374 |
+
"loss": 1.3644,
|
| 1375 |
+
"step": 3900
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.665958351041224,
|
| 1379 |
+
"grad_norm": 1.5588535070419312,
|
| 1380 |
+
"learning_rate": 8.899277518062049e-05,
|
| 1381 |
+
"loss": 1.417,
|
| 1382 |
+
"step": 3920
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.6744581385465365,
|
| 1386 |
+
"grad_norm": 1.4518215656280518,
|
| 1387 |
+
"learning_rate": 8.842612268026633e-05,
|
| 1388 |
+
"loss": 1.4177,
|
| 1389 |
+
"step": 3940
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.6829579260518486,
|
| 1393 |
+
"grad_norm": 1.593959093093872,
|
| 1394 |
+
"learning_rate": 8.785947017991218e-05,
|
| 1395 |
+
"loss": 1.4692,
|
| 1396 |
+
"step": 3960
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.6914577135571611,
|
| 1400 |
+
"grad_norm": 1.61430025100708,
|
| 1401 |
+
"learning_rate": 8.729281767955802e-05,
|
| 1402 |
+
"loss": 1.4231,
|
| 1403 |
+
"step": 3980
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.6999575010624735,
|
| 1407 |
+
"grad_norm": 1.5006210803985596,
|
| 1408 |
+
"learning_rate": 8.672616517920386e-05,
|
| 1409 |
+
"loss": 1.4632,
|
| 1410 |
+
"step": 4000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.7084572885677858,
|
| 1414 |
+
"grad_norm": 1.5484602451324463,
|
| 1415 |
+
"learning_rate": 8.615951267884969e-05,
|
| 1416 |
+
"loss": 1.4282,
|
| 1417 |
+
"step": 4020
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.7169570760730983,
|
| 1421 |
+
"grad_norm": 1.667822003364563,
|
| 1422 |
+
"learning_rate": 8.559286017849553e-05,
|
| 1423 |
+
"loss": 1.3641,
|
| 1424 |
+
"step": 4040
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.7254568635784104,
|
| 1428 |
+
"grad_norm": 1.6226531267166138,
|
| 1429 |
+
"learning_rate": 8.502620767814138e-05,
|
| 1430 |
+
"loss": 1.4197,
|
| 1431 |
+
"step": 4060
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.733956651083723,
|
| 1435 |
+
"grad_norm": 2.0089526176452637,
|
| 1436 |
+
"learning_rate": 8.445955517778723e-05,
|
| 1437 |
+
"loss": 1.4129,
|
| 1438 |
+
"step": 4080
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.7424564385890353,
|
| 1442 |
+
"grad_norm": 1.3930327892303467,
|
| 1443 |
+
"learning_rate": 8.389290267743307e-05,
|
| 1444 |
+
"loss": 1.3614,
|
| 1445 |
+
"step": 4100
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.7509562260943476,
|
| 1449 |
+
"grad_norm": 1.890655755996704,
|
| 1450 |
+
"learning_rate": 8.332625017707892e-05,
|
| 1451 |
+
"loss": 1.4578,
|
| 1452 |
+
"step": 4120
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.75945601359966,
|
| 1456 |
+
"grad_norm": 1.7144534587860107,
|
| 1457 |
+
"learning_rate": 8.275959767672476e-05,
|
| 1458 |
+
"loss": 1.4148,
|
| 1459 |
+
"step": 4140
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.7679558011049723,
|
| 1463 |
+
"grad_norm": 1.5091826915740967,
|
| 1464 |
+
"learning_rate": 8.219294517637059e-05,
|
| 1465 |
+
"loss": 1.4203,
|
| 1466 |
+
"step": 4160
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.7764555886102849,
|
| 1470 |
+
"grad_norm": 1.7839044332504272,
|
| 1471 |
+
"learning_rate": 8.162629267601643e-05,
|
| 1472 |
+
"loss": 1.3824,
|
| 1473 |
+
"step": 4180
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.784955376115597,
|
| 1477 |
+
"grad_norm": 1.661871075630188,
|
| 1478 |
+
"learning_rate": 8.105964017566228e-05,
|
| 1479 |
+
"loss": 1.4356,
|
| 1480 |
+
"step": 4200
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.7934551636209095,
|
| 1484 |
+
"grad_norm": 1.4366284608840942,
|
| 1485 |
+
"learning_rate": 8.049298767530812e-05,
|
| 1486 |
+
"loss": 1.3839,
|
| 1487 |
+
"step": 4220
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.8019549511262218,
|
| 1491 |
+
"grad_norm": 1.5518572330474854,
|
| 1492 |
+
"learning_rate": 7.992633517495396e-05,
|
| 1493 |
+
"loss": 1.4134,
|
| 1494 |
+
"step": 4240
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.8104547386315342,
|
| 1498 |
+
"grad_norm": 1.652972936630249,
|
| 1499 |
+
"learning_rate": 7.93596826745998e-05,
|
| 1500 |
+
"loss": 1.4234,
|
| 1501 |
+
"step": 4260
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.8189545261368467,
|
| 1505 |
+
"grad_norm": 1.4948612451553345,
|
| 1506 |
+
"learning_rate": 7.879303017424565e-05,
|
| 1507 |
+
"loss": 1.3798,
|
| 1508 |
+
"step": 4280
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.8274543136421588,
|
| 1512 |
+
"grad_norm": 1.6756293773651123,
|
| 1513 |
+
"learning_rate": 7.822637767389149e-05,
|
| 1514 |
+
"loss": 1.4239,
|
| 1515 |
+
"step": 4300
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.8359541011474714,
|
| 1519 |
+
"grad_norm": 1.7066694498062134,
|
| 1520 |
+
"learning_rate": 7.765972517353733e-05,
|
| 1521 |
+
"loss": 1.4485,
|
| 1522 |
+
"step": 4320
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.8444538886527837,
|
| 1526 |
+
"grad_norm": 1.478449821472168,
|
| 1527 |
+
"learning_rate": 7.709307267318317e-05,
|
| 1528 |
+
"loss": 1.3998,
|
| 1529 |
+
"step": 4340
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.852953676158096,
|
| 1533 |
+
"grad_norm": 1.7076212167739868,
|
| 1534 |
+
"learning_rate": 7.652642017282902e-05,
|
| 1535 |
+
"loss": 1.4249,
|
| 1536 |
+
"step": 4360
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.8614534636634086,
|
| 1540 |
+
"grad_norm": 1.5418049097061157,
|
| 1541 |
+
"learning_rate": 7.595976767247486e-05,
|
| 1542 |
+
"loss": 1.3806,
|
| 1543 |
+
"step": 4380
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.8699532511687207,
|
| 1547 |
+
"grad_norm": 1.668404459953308,
|
| 1548 |
+
"learning_rate": 7.53931151721207e-05,
|
| 1549 |
+
"loss": 1.4088,
|
| 1550 |
+
"step": 4400
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.8784530386740332,
|
| 1554 |
+
"grad_norm": 2.0103743076324463,
|
| 1555 |
+
"learning_rate": 7.482646267176655e-05,
|
| 1556 |
+
"loss": 1.4432,
|
| 1557 |
+
"step": 4420
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.8869528261793456,
|
| 1561 |
+
"grad_norm": 1.8902521133422852,
|
| 1562 |
+
"learning_rate": 7.425981017141237e-05,
|
| 1563 |
+
"loss": 1.4262,
|
| 1564 |
+
"step": 4440
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.895452613684658,
|
| 1568 |
+
"grad_norm": 1.493699550628662,
|
| 1569 |
+
"learning_rate": 7.369315767105822e-05,
|
| 1570 |
+
"loss": 1.402,
|
| 1571 |
+
"step": 4460
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.9039524011899702,
|
| 1575 |
+
"grad_norm": 1.617872953414917,
|
| 1576 |
+
"learning_rate": 7.312650517070407e-05,
|
| 1577 |
+
"loss": 1.4409,
|
| 1578 |
+
"step": 4480
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.9124521886952826,
|
| 1582 |
+
"grad_norm": 1.5638338327407837,
|
| 1583 |
+
"learning_rate": 7.255985267034992e-05,
|
| 1584 |
+
"loss": 1.3933,
|
| 1585 |
+
"step": 4500
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.920951976200595,
|
| 1589 |
+
"grad_norm": 1.6773780584335327,
|
| 1590 |
+
"learning_rate": 7.199320016999576e-05,
|
| 1591 |
+
"loss": 1.4084,
|
| 1592 |
+
"step": 4520
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.9294517637059072,
|
| 1596 |
+
"grad_norm": 1.5437266826629639,
|
| 1597 |
+
"learning_rate": 7.14265476696416e-05,
|
| 1598 |
+
"loss": 1.4419,
|
| 1599 |
+
"step": 4540
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.9379515512112198,
|
| 1603 |
+
"grad_norm": 1.5624651908874512,
|
| 1604 |
+
"learning_rate": 7.085989516928744e-05,
|
| 1605 |
+
"loss": 1.3479,
|
| 1606 |
+
"step": 4560
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.946451338716532,
|
| 1610 |
+
"grad_norm": 1.594768762588501,
|
| 1611 |
+
"learning_rate": 7.029324266893327e-05,
|
| 1612 |
+
"loss": 1.4021,
|
| 1613 |
+
"step": 4580
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.9549511262218444,
|
| 1617 |
+
"grad_norm": 1.7385071516036987,
|
| 1618 |
+
"learning_rate": 6.972659016857912e-05,
|
| 1619 |
+
"loss": 1.3459,
|
| 1620 |
+
"step": 4600
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.963450913727157,
|
| 1624 |
+
"grad_norm": 1.835210919380188,
|
| 1625 |
+
"learning_rate": 6.915993766822496e-05,
|
| 1626 |
+
"loss": 1.4334,
|
| 1627 |
+
"step": 4620
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.971950701232469,
|
| 1631 |
+
"grad_norm": 1.3983690738677979,
|
| 1632 |
+
"learning_rate": 6.85932851678708e-05,
|
| 1633 |
+
"loss": 1.396,
|
| 1634 |
+
"step": 4640
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.9804504887377816,
|
| 1638 |
+
"grad_norm": 1.4692546129226685,
|
| 1639 |
+
"learning_rate": 6.802663266751664e-05,
|
| 1640 |
+
"loss": 1.4184,
|
| 1641 |
+
"step": 4660
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.988950276243094,
|
| 1645 |
+
"grad_norm": 2.199734926223755,
|
| 1646 |
+
"learning_rate": 6.74599801671625e-05,
|
| 1647 |
+
"loss": 1.3902,
|
| 1648 |
+
"step": 4680
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.9974500637484063,
|
| 1652 |
+
"grad_norm": 1.8094977140426636,
|
| 1653 |
+
"learning_rate": 6.689332766680833e-05,
|
| 1654 |
+
"loss": 1.3973,
|
| 1655 |
+
"step": 4700
|
| 1656 |
+
}
|
| 1657 |
+
],
|
| 1658 |
+
"logging_steps": 20,
|
| 1659 |
+
"max_steps": 7059,
|
| 1660 |
+
"num_input_tokens_seen": 0,
|
| 1661 |
+
"num_train_epochs": 3,
|
| 1662 |
+
"save_steps": 500,
|
| 1663 |
+
"stateful_callbacks": {
|
| 1664 |
+
"TrainerControl": {
|
| 1665 |
+
"args": {
|
| 1666 |
+
"should_epoch_stop": false,
|
| 1667 |
+
"should_evaluate": false,
|
| 1668 |
+
"should_log": false,
|
| 1669 |
+
"should_save": true,
|
| 1670 |
+
"should_training_stop": false
|
| 1671 |
+
},
|
| 1672 |
+
"attributes": {}
|
| 1673 |
+
}
|
| 1674 |
+
},
|
| 1675 |
+
"total_flos": 5.994699046885786e+16,
|
| 1676 |
+
"train_batch_size": 4,
|
| 1677 |
+
"trial_name": null,
|
| 1678 |
+
"trial_params": null
|
| 1679 |
+
}
|
tinyllama-lora-finetuned/checkpoint-4706/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15e87998291b092367622e9a01c7bf9c9073fbba3c3325c704524d294a28c0e8
|
| 3 |
+
size 5304
|
tinyllama-lora-finetuned/checkpoint-7059/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.15.2
|
tinyllama-lora-finetuned/checkpoint-7059/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.1,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 16,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"v_proj",
|
| 28 |
+
"q_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"trainable_token_indices": null,
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
tinyllama-lora-finetuned/checkpoint-7059/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30714917adf91c927617da51652825f423856d999278ab43a89ff8801a725527
|
| 3 |
+
size 9022864
|
tinyllama-lora-finetuned/checkpoint-7059/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66f13a3291aa3847a59743082fee3c2915e37b8fe0f282ce10a3a9799a89a819
|
| 3 |
+
size 18096570
|
tinyllama-lora-finetuned/checkpoint-7059/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b996b3ef9171dbe240918633947a37fa68cb6622b01fabf832fb70526c7cad1
|
| 3 |
+
size 14244
|
tinyllama-lora-finetuned/checkpoint-7059/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:476fa65f582625715ac485c74528d19b46570b69068eac5629dbb7e98bd6c520
|
| 3 |
+
size 988
|
tinyllama-lora-finetuned/checkpoint-7059/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a0ac6e7c83ab9a47bf0cb56003aa5c935cc7550b1e53b681393c66779198082
|
| 3 |
+
size 1064
|
tinyllama-lora-finetuned/checkpoint-7059/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tinyllama-lora-finetuned/checkpoint-7059/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tinyllama-lora-finetuned/checkpoint-7059/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tinyllama-lora-finetuned/checkpoint-7059/tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"extra_special_tokens": {},
|
| 36 |
+
"legacy": false,
|
| 37 |
+
"model_max_length": 2048,
|
| 38 |
+
"pad_token": "</s>",
|
| 39 |
+
"padding_side": "right",
|
| 40 |
+
"sp_model_kwargs": {},
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false
|
| 44 |
+
}
|
tinyllama-lora-finetuned/checkpoint-7059/trainer_state.json
ADDED
|
@@ -0,0 +1,2498 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 7059,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.008499787505312367,
|
| 14 |
+
"grad_norm": 1.8467686176300049,
|
| 15 |
+
"learning_rate": 0.00019946168012466354,
|
| 16 |
+
"loss": 2.1643,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.016999575010624733,
|
| 21 |
+
"grad_norm": 2.2261719703674316,
|
| 22 |
+
"learning_rate": 0.0001988950276243094,
|
| 23 |
+
"loss": 1.7448,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.025499362515937103,
|
| 28 |
+
"grad_norm": 1.9097844362258911,
|
| 29 |
+
"learning_rate": 0.00019832837512395523,
|
| 30 |
+
"loss": 1.702,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.033999150021249466,
|
| 35 |
+
"grad_norm": 1.676216721534729,
|
| 36 |
+
"learning_rate": 0.00019776172262360109,
|
| 37 |
+
"loss": 1.7414,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.042498937526561836,
|
| 42 |
+
"grad_norm": 1.7480692863464355,
|
| 43 |
+
"learning_rate": 0.00019719507012324694,
|
| 44 |
+
"loss": 1.6,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.050998725031874206,
|
| 49 |
+
"grad_norm": 1.603786826133728,
|
| 50 |
+
"learning_rate": 0.00019662841762289277,
|
| 51 |
+
"loss": 1.72,
|
| 52 |
+
"step": 120
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.05949851253718657,
|
| 56 |
+
"grad_norm": 1.577128529548645,
|
| 57 |
+
"learning_rate": 0.00019606176512253863,
|
| 58 |
+
"loss": 1.6804,
|
| 59 |
+
"step": 140
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06799830004249893,
|
| 63 |
+
"grad_norm": 1.5658762454986572,
|
| 64 |
+
"learning_rate": 0.00019549511262218446,
|
| 65 |
+
"loss": 1.6582,
|
| 66 |
+
"step": 160
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0764980875478113,
|
| 70 |
+
"grad_norm": 1.7549939155578613,
|
| 71 |
+
"learning_rate": 0.00019492846012183031,
|
| 72 |
+
"loss": 1.6238,
|
| 73 |
+
"step": 180
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.08499787505312367,
|
| 77 |
+
"grad_norm": 1.490046501159668,
|
| 78 |
+
"learning_rate": 0.00019436180762147614,
|
| 79 |
+
"loss": 1.6661,
|
| 80 |
+
"step": 200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.09349766255843604,
|
| 84 |
+
"grad_norm": 1.7966225147247314,
|
| 85 |
+
"learning_rate": 0.00019379515512112197,
|
| 86 |
+
"loss": 1.6258,
|
| 87 |
+
"step": 220
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.10199745006374841,
|
| 91 |
+
"grad_norm": 1.6181796789169312,
|
| 92 |
+
"learning_rate": 0.00019322850262076783,
|
| 93 |
+
"loss": 1.6042,
|
| 94 |
+
"step": 240
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.11049723756906077,
|
| 98 |
+
"grad_norm": 1.4492865800857544,
|
| 99 |
+
"learning_rate": 0.00019266185012041366,
|
| 100 |
+
"loss": 1.5649,
|
| 101 |
+
"step": 260
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.11899702507437314,
|
| 105 |
+
"grad_norm": 2.01737117767334,
|
| 106 |
+
"learning_rate": 0.0001920951976200595,
|
| 107 |
+
"loss": 1.6877,
|
| 108 |
+
"step": 280
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1274968125796855,
|
| 112 |
+
"grad_norm": 1.4284173250198364,
|
| 113 |
+
"learning_rate": 0.00019152854511970534,
|
| 114 |
+
"loss": 1.5727,
|
| 115 |
+
"step": 300
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.13599660008499787,
|
| 119 |
+
"grad_norm": 1.4602673053741455,
|
| 120 |
+
"learning_rate": 0.0001909618926193512,
|
| 121 |
+
"loss": 1.5837,
|
| 122 |
+
"step": 320
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14449638759031025,
|
| 126 |
+
"grad_norm": 1.6680593490600586,
|
| 127 |
+
"learning_rate": 0.00019039524011899703,
|
| 128 |
+
"loss": 1.6122,
|
| 129 |
+
"step": 340
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1529961750956226,
|
| 133 |
+
"grad_norm": 1.4604177474975586,
|
| 134 |
+
"learning_rate": 0.00018982858761864288,
|
| 135 |
+
"loss": 1.6064,
|
| 136 |
+
"step": 360
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.161495962600935,
|
| 140 |
+
"grad_norm": 1.4658399820327759,
|
| 141 |
+
"learning_rate": 0.00018926193511828871,
|
| 142 |
+
"loss": 1.5842,
|
| 143 |
+
"step": 380
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.16999575010624735,
|
| 147 |
+
"grad_norm": 1.2307661771774292,
|
| 148 |
+
"learning_rate": 0.00018869528261793457,
|
| 149 |
+
"loss": 1.6023,
|
| 150 |
+
"step": 400
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.1784955376115597,
|
| 154 |
+
"grad_norm": 1.4648102521896362,
|
| 155 |
+
"learning_rate": 0.0001881286301175804,
|
| 156 |
+
"loss": 1.5484,
|
| 157 |
+
"step": 420
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.18699532511687209,
|
| 161 |
+
"grad_norm": 1.4780811071395874,
|
| 162 |
+
"learning_rate": 0.00018756197761722626,
|
| 163 |
+
"loss": 1.5009,
|
| 164 |
+
"step": 440
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.19549511262218444,
|
| 168 |
+
"grad_norm": 1.4852784872055054,
|
| 169 |
+
"learning_rate": 0.00018699532511687208,
|
| 170 |
+
"loss": 1.6116,
|
| 171 |
+
"step": 460
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.20399490012749683,
|
| 175 |
+
"grad_norm": 1.4338926076889038,
|
| 176 |
+
"learning_rate": 0.00018642867261651794,
|
| 177 |
+
"loss": 1.6025,
|
| 178 |
+
"step": 480
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.21249468763280918,
|
| 182 |
+
"grad_norm": 1.5596784353256226,
|
| 183 |
+
"learning_rate": 0.00018586202011616377,
|
| 184 |
+
"loss": 1.6212,
|
| 185 |
+
"step": 500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.22099447513812154,
|
| 189 |
+
"grad_norm": 1.2840818166732788,
|
| 190 |
+
"learning_rate": 0.0001852953676158096,
|
| 191 |
+
"loss": 1.6135,
|
| 192 |
+
"step": 520
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.22949426264343392,
|
| 196 |
+
"grad_norm": 1.5443825721740723,
|
| 197 |
+
"learning_rate": 0.00018472871511545546,
|
| 198 |
+
"loss": 1.5785,
|
| 199 |
+
"step": 540
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.23799405014874628,
|
| 203 |
+
"grad_norm": 1.5090241432189941,
|
| 204 |
+
"learning_rate": 0.00018416206261510129,
|
| 205 |
+
"loss": 1.5871,
|
| 206 |
+
"step": 560
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.24649383765405866,
|
| 210 |
+
"grad_norm": 1.613731861114502,
|
| 211 |
+
"learning_rate": 0.00018359541011474714,
|
| 212 |
+
"loss": 1.604,
|
| 213 |
+
"step": 580
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.254993625159371,
|
| 217 |
+
"grad_norm": 1.354567289352417,
|
| 218 |
+
"learning_rate": 0.00018302875761439297,
|
| 219 |
+
"loss": 1.4996,
|
| 220 |
+
"step": 600
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.2634934126646834,
|
| 224 |
+
"grad_norm": 1.5025413036346436,
|
| 225 |
+
"learning_rate": 0.00018246210511403883,
|
| 226 |
+
"loss": 1.5923,
|
| 227 |
+
"step": 620
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.27199320016999573,
|
| 231 |
+
"grad_norm": 1.3449057340621948,
|
| 232 |
+
"learning_rate": 0.00018189545261368466,
|
| 233 |
+
"loss": 1.5435,
|
| 234 |
+
"step": 640
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2804929876753081,
|
| 238 |
+
"grad_norm": 1.2846812009811401,
|
| 239 |
+
"learning_rate": 0.0001813288001133305,
|
| 240 |
+
"loss": 1.536,
|
| 241 |
+
"step": 660
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2889927751806205,
|
| 245 |
+
"grad_norm": 1.3012146949768066,
|
| 246 |
+
"learning_rate": 0.00018076214761297634,
|
| 247 |
+
"loss": 1.539,
|
| 248 |
+
"step": 680
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.2974925626859328,
|
| 252 |
+
"grad_norm": 1.5017261505126953,
|
| 253 |
+
"learning_rate": 0.0001801954951126222,
|
| 254 |
+
"loss": 1.5727,
|
| 255 |
+
"step": 700
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3059923501912452,
|
| 259 |
+
"grad_norm": 1.3044496774673462,
|
| 260 |
+
"learning_rate": 0.00017962884261226805,
|
| 261 |
+
"loss": 1.6619,
|
| 262 |
+
"step": 720
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.3144921376965576,
|
| 266 |
+
"grad_norm": 1.6723718643188477,
|
| 267 |
+
"learning_rate": 0.00017906219011191388,
|
| 268 |
+
"loss": 1.5572,
|
| 269 |
+
"step": 740
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.32299192520187,
|
| 273 |
+
"grad_norm": 1.5928444862365723,
|
| 274 |
+
"learning_rate": 0.00017849553761155974,
|
| 275 |
+
"loss": 1.4755,
|
| 276 |
+
"step": 760
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.3314917127071823,
|
| 280 |
+
"grad_norm": 1.2782012224197388,
|
| 281 |
+
"learning_rate": 0.00017792888511120557,
|
| 282 |
+
"loss": 1.592,
|
| 283 |
+
"step": 780
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3399915002124947,
|
| 287 |
+
"grad_norm": 1.349767804145813,
|
| 288 |
+
"learning_rate": 0.0001773622326108514,
|
| 289 |
+
"loss": 1.5436,
|
| 290 |
+
"step": 800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.3484912877178071,
|
| 294 |
+
"grad_norm": 1.4979254007339478,
|
| 295 |
+
"learning_rate": 0.00017679558011049723,
|
| 296 |
+
"loss": 1.6191,
|
| 297 |
+
"step": 820
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3569910752231194,
|
| 301 |
+
"grad_norm": 1.5227205753326416,
|
| 302 |
+
"learning_rate": 0.00017622892761014308,
|
| 303 |
+
"loss": 1.6074,
|
| 304 |
+
"step": 840
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3654908627284318,
|
| 308 |
+
"grad_norm": 1.300671100616455,
|
| 309 |
+
"learning_rate": 0.0001756622751097889,
|
| 310 |
+
"loss": 1.5877,
|
| 311 |
+
"step": 860
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.37399065023374417,
|
| 315 |
+
"grad_norm": 1.1968013048171997,
|
| 316 |
+
"learning_rate": 0.00017509562260943477,
|
| 317 |
+
"loss": 1.5343,
|
| 318 |
+
"step": 880
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3824904377390565,
|
| 322 |
+
"grad_norm": 1.4233676195144653,
|
| 323 |
+
"learning_rate": 0.00017452897010908063,
|
| 324 |
+
"loss": 1.5093,
|
| 325 |
+
"step": 900
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.3909902252443689,
|
| 329 |
+
"grad_norm": 1.5608493089675903,
|
| 330 |
+
"learning_rate": 0.00017396231760872645,
|
| 331 |
+
"loss": 1.552,
|
| 332 |
+
"step": 920
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.39949001274968127,
|
| 336 |
+
"grad_norm": 1.6073567867279053,
|
| 337 |
+
"learning_rate": 0.0001733956651083723,
|
| 338 |
+
"loss": 1.551,
|
| 339 |
+
"step": 940
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.40798980025499365,
|
| 343 |
+
"grad_norm": 1.1513320207595825,
|
| 344 |
+
"learning_rate": 0.00017282901260801814,
|
| 345 |
+
"loss": 1.51,
|
| 346 |
+
"step": 960
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.416489587760306,
|
| 350 |
+
"grad_norm": 1.3810391426086426,
|
| 351 |
+
"learning_rate": 0.000172262360107664,
|
| 352 |
+
"loss": 1.5447,
|
| 353 |
+
"step": 980
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.42498937526561836,
|
| 357 |
+
"grad_norm": 1.4732245206832886,
|
| 358 |
+
"learning_rate": 0.00017169570760730983,
|
| 359 |
+
"loss": 1.5781,
|
| 360 |
+
"step": 1000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.43348916277093075,
|
| 364 |
+
"grad_norm": 1.1698389053344727,
|
| 365 |
+
"learning_rate": 0.00017112905510695568,
|
| 366 |
+
"loss": 1.5205,
|
| 367 |
+
"step": 1020
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.4419889502762431,
|
| 371 |
+
"grad_norm": 1.49894118309021,
|
| 372 |
+
"learning_rate": 0.0001705624026066015,
|
| 373 |
+
"loss": 1.6071,
|
| 374 |
+
"step": 1040
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.45048873778155546,
|
| 378 |
+
"grad_norm": 1.3100991249084473,
|
| 379 |
+
"learning_rate": 0.00016999575010624734,
|
| 380 |
+
"loss": 1.6148,
|
| 381 |
+
"step": 1060
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.45898852528686784,
|
| 385 |
+
"grad_norm": 1.5139139890670776,
|
| 386 |
+
"learning_rate": 0.0001694290976058932,
|
| 387 |
+
"loss": 1.5657,
|
| 388 |
+
"step": 1080
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.46748831279218017,
|
| 392 |
+
"grad_norm": 1.3952980041503906,
|
| 393 |
+
"learning_rate": 0.00016886244510553903,
|
| 394 |
+
"loss": 1.5596,
|
| 395 |
+
"step": 1100
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.47598810029749256,
|
| 399 |
+
"grad_norm": 1.2251731157302856,
|
| 400 |
+
"learning_rate": 0.00016829579260518488,
|
| 401 |
+
"loss": 1.5207,
|
| 402 |
+
"step": 1120
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.48448788780280494,
|
| 406 |
+
"grad_norm": 1.4944117069244385,
|
| 407 |
+
"learning_rate": 0.0001677291401048307,
|
| 408 |
+
"loss": 1.562,
|
| 409 |
+
"step": 1140
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.4929876753081173,
|
| 413 |
+
"grad_norm": 1.2576520442962646,
|
| 414 |
+
"learning_rate": 0.00016716248760447657,
|
| 415 |
+
"loss": 1.5362,
|
| 416 |
+
"step": 1160
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5014874628134297,
|
| 420 |
+
"grad_norm": 1.3012641668319702,
|
| 421 |
+
"learning_rate": 0.0001665958351041224,
|
| 422 |
+
"loss": 1.5384,
|
| 423 |
+
"step": 1180
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.509987250318742,
|
| 427 |
+
"grad_norm": 1.3370224237442017,
|
| 428 |
+
"learning_rate": 0.00016602918260376825,
|
| 429 |
+
"loss": 1.5406,
|
| 430 |
+
"step": 1200
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5184870378240544,
|
| 434 |
+
"grad_norm": 1.4711674451828003,
|
| 435 |
+
"learning_rate": 0.00016546253010341408,
|
| 436 |
+
"loss": 1.5489,
|
| 437 |
+
"step": 1220
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.5269868253293668,
|
| 441 |
+
"grad_norm": 1.3889433145523071,
|
| 442 |
+
"learning_rate": 0.00016489587760305994,
|
| 443 |
+
"loss": 1.5683,
|
| 444 |
+
"step": 1240
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5354866128346791,
|
| 448 |
+
"grad_norm": 1.181380271911621,
|
| 449 |
+
"learning_rate": 0.00016432922510270577,
|
| 450 |
+
"loss": 1.5282,
|
| 451 |
+
"step": 1260
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5439864003399915,
|
| 455 |
+
"grad_norm": 1.2874456644058228,
|
| 456 |
+
"learning_rate": 0.00016376257260235162,
|
| 457 |
+
"loss": 1.5642,
|
| 458 |
+
"step": 1280
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.5524861878453039,
|
| 462 |
+
"grad_norm": 1.2181987762451172,
|
| 463 |
+
"learning_rate": 0.00016319592010199748,
|
| 464 |
+
"loss": 1.5324,
|
| 465 |
+
"step": 1300
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.5609859753506162,
|
| 469 |
+
"grad_norm": 1.4149408340454102,
|
| 470 |
+
"learning_rate": 0.0001626292676016433,
|
| 471 |
+
"loss": 1.5366,
|
| 472 |
+
"step": 1320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5694857628559286,
|
| 476 |
+
"grad_norm": 1.1893357038497925,
|
| 477 |
+
"learning_rate": 0.00016206261510128914,
|
| 478 |
+
"loss": 1.5386,
|
| 479 |
+
"step": 1340
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.577985550361241,
|
| 483 |
+
"grad_norm": 1.4138270616531372,
|
| 484 |
+
"learning_rate": 0.00016149596260093497,
|
| 485 |
+
"loss": 1.4789,
|
| 486 |
+
"step": 1360
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.5864853378665533,
|
| 490 |
+
"grad_norm": 1.5200152397155762,
|
| 491 |
+
"learning_rate": 0.00016092931010058082,
|
| 492 |
+
"loss": 1.5012,
|
| 493 |
+
"step": 1380
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.5949851253718657,
|
| 497 |
+
"grad_norm": 1.2447080612182617,
|
| 498 |
+
"learning_rate": 0.00016036265760022665,
|
| 499 |
+
"loss": 1.498,
|
| 500 |
+
"step": 1400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6034849128771781,
|
| 504 |
+
"grad_norm": 1.4135057926177979,
|
| 505 |
+
"learning_rate": 0.0001597960050998725,
|
| 506 |
+
"loss": 1.4519,
|
| 507 |
+
"step": 1420
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.6119847003824904,
|
| 511 |
+
"grad_norm": 1.2652864456176758,
|
| 512 |
+
"learning_rate": 0.00015922935259951834,
|
| 513 |
+
"loss": 1.5595,
|
| 514 |
+
"step": 1440
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6204844878878029,
|
| 518 |
+
"grad_norm": 1.356728434562683,
|
| 519 |
+
"learning_rate": 0.0001586627000991642,
|
| 520 |
+
"loss": 1.4859,
|
| 521 |
+
"step": 1460
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.6289842753931152,
|
| 525 |
+
"grad_norm": 1.3269623517990112,
|
| 526 |
+
"learning_rate": 0.00015809604759881002,
|
| 527 |
+
"loss": 1.5002,
|
| 528 |
+
"step": 1480
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.6374840628984275,
|
| 532 |
+
"grad_norm": 1.5896166563034058,
|
| 533 |
+
"learning_rate": 0.00015752939509845588,
|
| 534 |
+
"loss": 1.4852,
|
| 535 |
+
"step": 1500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.64598385040374,
|
| 539 |
+
"grad_norm": 1.5948361158370972,
|
| 540 |
+
"learning_rate": 0.00015696274259810174,
|
| 541 |
+
"loss": 1.5728,
|
| 542 |
+
"step": 1520
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.6544836379090523,
|
| 546 |
+
"grad_norm": 1.3188483715057373,
|
| 547 |
+
"learning_rate": 0.00015639609009774757,
|
| 548 |
+
"loss": 1.5287,
|
| 549 |
+
"step": 1540
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6629834254143646,
|
| 553 |
+
"grad_norm": 1.2547403573989868,
|
| 554 |
+
"learning_rate": 0.00015582943759739342,
|
| 555 |
+
"loss": 1.4523,
|
| 556 |
+
"step": 1560
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.671483212919677,
|
| 560 |
+
"grad_norm": 1.3939685821533203,
|
| 561 |
+
"learning_rate": 0.00015526278509703925,
|
| 562 |
+
"loss": 1.4659,
|
| 563 |
+
"step": 1580
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6799830004249894,
|
| 567 |
+
"grad_norm": 1.1834455728530884,
|
| 568 |
+
"learning_rate": 0.0001546961325966851,
|
| 569 |
+
"loss": 1.4674,
|
| 570 |
+
"step": 1600
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6884827879303017,
|
| 574 |
+
"grad_norm": 1.5032856464385986,
|
| 575 |
+
"learning_rate": 0.00015412948009633094,
|
| 576 |
+
"loss": 1.6103,
|
| 577 |
+
"step": 1620
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6969825754356141,
|
| 581 |
+
"grad_norm": 1.4383857250213623,
|
| 582 |
+
"learning_rate": 0.00015356282759597677,
|
| 583 |
+
"loss": 1.5483,
|
| 584 |
+
"step": 1640
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.7054823629409265,
|
| 588 |
+
"grad_norm": 1.2931615114212036,
|
| 589 |
+
"learning_rate": 0.0001529961750956226,
|
| 590 |
+
"loss": 1.5219,
|
| 591 |
+
"step": 1660
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.7139821504462388,
|
| 595 |
+
"grad_norm": 1.3393011093139648,
|
| 596 |
+
"learning_rate": 0.00015242952259526845,
|
| 597 |
+
"loss": 1.4984,
|
| 598 |
+
"step": 1680
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.7224819379515512,
|
| 602 |
+
"grad_norm": 1.372475266456604,
|
| 603 |
+
"learning_rate": 0.0001518628700949143,
|
| 604 |
+
"loss": 1.4966,
|
| 605 |
+
"step": 1700
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.7309817254568636,
|
| 609 |
+
"grad_norm": 1.4294521808624268,
|
| 610 |
+
"learning_rate": 0.00015129621759456014,
|
| 611 |
+
"loss": 1.4844,
|
| 612 |
+
"step": 1720
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.7394815129621759,
|
| 616 |
+
"grad_norm": 1.5531823635101318,
|
| 617 |
+
"learning_rate": 0.000150729565094206,
|
| 618 |
+
"loss": 1.5581,
|
| 619 |
+
"step": 1740
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.7479813004674883,
|
| 623 |
+
"grad_norm": 1.5481995344161987,
|
| 624 |
+
"learning_rate": 0.00015016291259385182,
|
| 625 |
+
"loss": 1.5487,
|
| 626 |
+
"step": 1760
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.7564810879728007,
|
| 630 |
+
"grad_norm": 1.4445319175720215,
|
| 631 |
+
"learning_rate": 0.00014959626009349768,
|
| 632 |
+
"loss": 1.5389,
|
| 633 |
+
"step": 1780
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.764980875478113,
|
| 637 |
+
"grad_norm": 1.538258671760559,
|
| 638 |
+
"learning_rate": 0.0001490296075931435,
|
| 639 |
+
"loss": 1.5034,
|
| 640 |
+
"step": 1800
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.7734806629834254,
|
| 644 |
+
"grad_norm": 1.4794244766235352,
|
| 645 |
+
"learning_rate": 0.00014846295509278936,
|
| 646 |
+
"loss": 1.4403,
|
| 647 |
+
"step": 1820
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.7819804504887378,
|
| 651 |
+
"grad_norm": 1.3663828372955322,
|
| 652 |
+
"learning_rate": 0.0001478963025924352,
|
| 653 |
+
"loss": 1.5626,
|
| 654 |
+
"step": 1840
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7904802379940501,
|
| 658 |
+
"grad_norm": 1.6889076232910156,
|
| 659 |
+
"learning_rate": 0.00014732965009208105,
|
| 660 |
+
"loss": 1.4974,
|
| 661 |
+
"step": 1860
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.7989800254993625,
|
| 665 |
+
"grad_norm": 1.4024620056152344,
|
| 666 |
+
"learning_rate": 0.00014676299759172688,
|
| 667 |
+
"loss": 1.5809,
|
| 668 |
+
"step": 1880
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8074798130046749,
|
| 672 |
+
"grad_norm": 1.3137383460998535,
|
| 673 |
+
"learning_rate": 0.00014619634509137274,
|
| 674 |
+
"loss": 1.5202,
|
| 675 |
+
"step": 1900
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.8159796005099873,
|
| 679 |
+
"grad_norm": 1.5561782121658325,
|
| 680 |
+
"learning_rate": 0.00014562969259101856,
|
| 681 |
+
"loss": 1.4611,
|
| 682 |
+
"step": 1920
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.8244793880152996,
|
| 686 |
+
"grad_norm": 1.4386446475982666,
|
| 687 |
+
"learning_rate": 0.0001450630400906644,
|
| 688 |
+
"loss": 1.5364,
|
| 689 |
+
"step": 1940
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.832979175520612,
|
| 693 |
+
"grad_norm": 1.4223254919052124,
|
| 694 |
+
"learning_rate": 0.00014452472021532796,
|
| 695 |
+
"loss": 1.4866,
|
| 696 |
+
"step": 1960
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.8414789630259244,
|
| 700 |
+
"grad_norm": 1.290819525718689,
|
| 701 |
+
"learning_rate": 0.0001439580677149738,
|
| 702 |
+
"loss": 1.5182,
|
| 703 |
+
"step": 1980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.8499787505312367,
|
| 707 |
+
"grad_norm": 1.3473018407821655,
|
| 708 |
+
"learning_rate": 0.00014339141521461964,
|
| 709 |
+
"loss": 1.4962,
|
| 710 |
+
"step": 2000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.858478538036549,
|
| 714 |
+
"grad_norm": 1.480664849281311,
|
| 715 |
+
"learning_rate": 0.00014282476271426547,
|
| 716 |
+
"loss": 1.5277,
|
| 717 |
+
"step": 2020
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8669783255418615,
|
| 721 |
+
"grad_norm": 1.4417237043380737,
|
| 722 |
+
"learning_rate": 0.00014225811021391133,
|
| 723 |
+
"loss": 1.4646,
|
| 724 |
+
"step": 2040
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.8754781130471738,
|
| 728 |
+
"grad_norm": 1.3464792966842651,
|
| 729 |
+
"learning_rate": 0.00014169145771355716,
|
| 730 |
+
"loss": 1.5028,
|
| 731 |
+
"step": 2060
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.8839779005524862,
|
| 735 |
+
"grad_norm": 1.4068652391433716,
|
| 736 |
+
"learning_rate": 0.000141124805213203,
|
| 737 |
+
"loss": 1.5142,
|
| 738 |
+
"step": 2080
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.8924776880577986,
|
| 742 |
+
"grad_norm": 1.321798324584961,
|
| 743 |
+
"learning_rate": 0.00014055815271284884,
|
| 744 |
+
"loss": 1.5505,
|
| 745 |
+
"step": 2100
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.9009774755631109,
|
| 749 |
+
"grad_norm": 1.38119375705719,
|
| 750 |
+
"learning_rate": 0.0001399915002124947,
|
| 751 |
+
"loss": 1.5606,
|
| 752 |
+
"step": 2120
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.9094772630684232,
|
| 756 |
+
"grad_norm": 1.4736709594726562,
|
| 757 |
+
"learning_rate": 0.00013942484771214053,
|
| 758 |
+
"loss": 1.5104,
|
| 759 |
+
"step": 2140
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.9179770505737357,
|
| 763 |
+
"grad_norm": 1.5708409547805786,
|
| 764 |
+
"learning_rate": 0.00013885819521178638,
|
| 765 |
+
"loss": 1.5129,
|
| 766 |
+
"step": 2160
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.926476838079048,
|
| 770 |
+
"grad_norm": 1.2119626998901367,
|
| 771 |
+
"learning_rate": 0.00013829154271143224,
|
| 772 |
+
"loss": 1.5139,
|
| 773 |
+
"step": 2180
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.9349766255843603,
|
| 777 |
+
"grad_norm": 1.4460374116897583,
|
| 778 |
+
"learning_rate": 0.00013772489021107807,
|
| 779 |
+
"loss": 1.5176,
|
| 780 |
+
"step": 2200
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.9434764130896728,
|
| 784 |
+
"grad_norm": 1.377457618713379,
|
| 785 |
+
"learning_rate": 0.00013715823771072392,
|
| 786 |
+
"loss": 1.4846,
|
| 787 |
+
"step": 2220
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.9519762005949851,
|
| 791 |
+
"grad_norm": 1.5439783334732056,
|
| 792 |
+
"learning_rate": 0.00013659158521036975,
|
| 793 |
+
"loss": 1.4432,
|
| 794 |
+
"step": 2240
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.9604759881002974,
|
| 798 |
+
"grad_norm": 1.3697561025619507,
|
| 799 |
+
"learning_rate": 0.00013602493271001558,
|
| 800 |
+
"loss": 1.5054,
|
| 801 |
+
"step": 2260
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.9689757756056099,
|
| 805 |
+
"grad_norm": 1.6576790809631348,
|
| 806 |
+
"learning_rate": 0.0001354582802096614,
|
| 807 |
+
"loss": 1.5202,
|
| 808 |
+
"step": 2280
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.9774755631109222,
|
| 812 |
+
"grad_norm": 1.2522470951080322,
|
| 813 |
+
"learning_rate": 0.00013489162770930727,
|
| 814 |
+
"loss": 1.5237,
|
| 815 |
+
"step": 2300
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.9859753506162346,
|
| 819 |
+
"grad_norm": 1.316643476486206,
|
| 820 |
+
"learning_rate": 0.0001343249752089531,
|
| 821 |
+
"loss": 1.4693,
|
| 822 |
+
"step": 2320
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.994475138121547,
|
| 826 |
+
"grad_norm": 1.415403127670288,
|
| 827 |
+
"learning_rate": 0.00013375832270859895,
|
| 828 |
+
"loss": 1.5064,
|
| 829 |
+
"step": 2340
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0029749256268594,
|
| 833 |
+
"grad_norm": 1.2021781206130981,
|
| 834 |
+
"learning_rate": 0.00013319167020824478,
|
| 835 |
+
"loss": 1.4576,
|
| 836 |
+
"step": 2360
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.0114747131321717,
|
| 840 |
+
"grad_norm": 1.391981840133667,
|
| 841 |
+
"learning_rate": 0.00013262501770789064,
|
| 842 |
+
"loss": 1.4672,
|
| 843 |
+
"step": 2380
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.019974500637484,
|
| 847 |
+
"grad_norm": 1.6223762035369873,
|
| 848 |
+
"learning_rate": 0.0001320583652075365,
|
| 849 |
+
"loss": 1.4746,
|
| 850 |
+
"step": 2400
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.0284742881427964,
|
| 854 |
+
"grad_norm": 1.584978699684143,
|
| 855 |
+
"learning_rate": 0.00013149171270718233,
|
| 856 |
+
"loss": 1.446,
|
| 857 |
+
"step": 2420
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.0369740756481087,
|
| 861 |
+
"grad_norm": 1.3905613422393799,
|
| 862 |
+
"learning_rate": 0.00013092506020682818,
|
| 863 |
+
"loss": 1.4673,
|
| 864 |
+
"step": 2440
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.045473863153421,
|
| 868 |
+
"grad_norm": 1.3543156385421753,
|
| 869 |
+
"learning_rate": 0.000130358407706474,
|
| 870 |
+
"loss": 1.4774,
|
| 871 |
+
"step": 2460
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.0539736506587336,
|
| 875 |
+
"grad_norm": 1.4284417629241943,
|
| 876 |
+
"learning_rate": 0.00012979175520611987,
|
| 877 |
+
"loss": 1.4828,
|
| 878 |
+
"step": 2480
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.062473438164046,
|
| 882 |
+
"grad_norm": 1.2880805730819702,
|
| 883 |
+
"learning_rate": 0.0001292251027057657,
|
| 884 |
+
"loss": 1.4688,
|
| 885 |
+
"step": 2500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.0709732256693583,
|
| 889 |
+
"grad_norm": 1.4029446840286255,
|
| 890 |
+
"learning_rate": 0.00012865845020541155,
|
| 891 |
+
"loss": 1.4667,
|
| 892 |
+
"step": 2520
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.0794730131746706,
|
| 896 |
+
"grad_norm": 1.4345691204071045,
|
| 897 |
+
"learning_rate": 0.00012809179770505738,
|
| 898 |
+
"loss": 1.4268,
|
| 899 |
+
"step": 2540
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.087972800679983,
|
| 903 |
+
"grad_norm": 1.5828334093093872,
|
| 904 |
+
"learning_rate": 0.0001275251452047032,
|
| 905 |
+
"loss": 1.3897,
|
| 906 |
+
"step": 2560
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.0964725881852955,
|
| 910 |
+
"grad_norm": 1.8496978282928467,
|
| 911 |
+
"learning_rate": 0.00012695849270434907,
|
| 912 |
+
"loss": 1.4783,
|
| 913 |
+
"step": 2580
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.1049723756906078,
|
| 917 |
+
"grad_norm": 1.756039023399353,
|
| 918 |
+
"learning_rate": 0.0001263918402039949,
|
| 919 |
+
"loss": 1.4611,
|
| 920 |
+
"step": 2600
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.1134721631959201,
|
| 924 |
+
"grad_norm": 1.3964674472808838,
|
| 925 |
+
"learning_rate": 0.00012582518770364075,
|
| 926 |
+
"loss": 1.4139,
|
| 927 |
+
"step": 2620
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.1219719507012325,
|
| 931 |
+
"grad_norm": 1.7207622528076172,
|
| 932 |
+
"learning_rate": 0.00012525853520328658,
|
| 933 |
+
"loss": 1.4206,
|
| 934 |
+
"step": 2640
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.1304717382065448,
|
| 938 |
+
"grad_norm": 1.4870052337646484,
|
| 939 |
+
"learning_rate": 0.00012469188270293244,
|
| 940 |
+
"loss": 1.3631,
|
| 941 |
+
"step": 2660
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.1389715257118571,
|
| 945 |
+
"grad_norm": 1.4430071115493774,
|
| 946 |
+
"learning_rate": 0.00012412523020257827,
|
| 947 |
+
"loss": 1.4766,
|
| 948 |
+
"step": 2680
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.1474713132171697,
|
| 952 |
+
"grad_norm": 1.5112409591674805,
|
| 953 |
+
"learning_rate": 0.00012355857770222412,
|
| 954 |
+
"loss": 1.461,
|
| 955 |
+
"step": 2700
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.155971100722482,
|
| 959 |
+
"grad_norm": 1.4189656972885132,
|
| 960 |
+
"learning_rate": 0.00012299192520186995,
|
| 961 |
+
"loss": 1.389,
|
| 962 |
+
"step": 2720
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.1644708882277943,
|
| 966 |
+
"grad_norm": 1.543331265449524,
|
| 967 |
+
"learning_rate": 0.0001224252727015158,
|
| 968 |
+
"loss": 1.4474,
|
| 969 |
+
"step": 2740
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.1729706757331066,
|
| 973 |
+
"grad_norm": 1.398582100868225,
|
| 974 |
+
"learning_rate": 0.00012185862020116164,
|
| 975 |
+
"loss": 1.4047,
|
| 976 |
+
"step": 2760
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.181470463238419,
|
| 980 |
+
"grad_norm": 1.3756153583526611,
|
| 981 |
+
"learning_rate": 0.00012129196770080748,
|
| 982 |
+
"loss": 1.4086,
|
| 983 |
+
"step": 2780
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.1899702507437313,
|
| 987 |
+
"grad_norm": 1.5835983753204346,
|
| 988 |
+
"learning_rate": 0.00012072531520045334,
|
| 989 |
+
"loss": 1.4855,
|
| 990 |
+
"step": 2800
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.1984700382490439,
|
| 994 |
+
"grad_norm": 1.516381025314331,
|
| 995 |
+
"learning_rate": 0.00012015866270009917,
|
| 996 |
+
"loss": 1.455,
|
| 997 |
+
"step": 2820
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.2069698257543562,
|
| 1001 |
+
"grad_norm": 1.2615922689437866,
|
| 1002 |
+
"learning_rate": 0.00011959201019974502,
|
| 1003 |
+
"loss": 1.4531,
|
| 1004 |
+
"step": 2840
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.2154696132596685,
|
| 1008 |
+
"grad_norm": 1.5319349765777588,
|
| 1009 |
+
"learning_rate": 0.00011902535769939085,
|
| 1010 |
+
"loss": 1.4098,
|
| 1011 |
+
"step": 2860
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.2239694007649808,
|
| 1015 |
+
"grad_norm": 1.384494423866272,
|
| 1016 |
+
"learning_rate": 0.0001184587051990367,
|
| 1017 |
+
"loss": 1.424,
|
| 1018 |
+
"step": 2880
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.2324691882702932,
|
| 1022 |
+
"grad_norm": 1.4936223030090332,
|
| 1023 |
+
"learning_rate": 0.00011789205269868254,
|
| 1024 |
+
"loss": 1.4409,
|
| 1025 |
+
"step": 2900
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.2409689757756057,
|
| 1029 |
+
"grad_norm": 1.8717914819717407,
|
| 1030 |
+
"learning_rate": 0.00011732540019832838,
|
| 1031 |
+
"loss": 1.4478,
|
| 1032 |
+
"step": 2920
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.249468763280918,
|
| 1036 |
+
"grad_norm": 1.5673747062683105,
|
| 1037 |
+
"learning_rate": 0.00011675874769797421,
|
| 1038 |
+
"loss": 1.4076,
|
| 1039 |
+
"step": 2940
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.2579685507862304,
|
| 1043 |
+
"grad_norm": 1.5353143215179443,
|
| 1044 |
+
"learning_rate": 0.00011619209519762007,
|
| 1045 |
+
"loss": 1.4527,
|
| 1046 |
+
"step": 2960
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.2664683382915427,
|
| 1050 |
+
"grad_norm": 1.5840922594070435,
|
| 1051 |
+
"learning_rate": 0.00011562544269726592,
|
| 1052 |
+
"loss": 1.4547,
|
| 1053 |
+
"step": 2980
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.274968125796855,
|
| 1057 |
+
"grad_norm": 1.432485580444336,
|
| 1058 |
+
"learning_rate": 0.00011505879019691175,
|
| 1059 |
+
"loss": 1.3915,
|
| 1060 |
+
"step": 3000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.2834679133021676,
|
| 1064 |
+
"grad_norm": 1.6025019884109497,
|
| 1065 |
+
"learning_rate": 0.0001144921376965576,
|
| 1066 |
+
"loss": 1.4778,
|
| 1067 |
+
"step": 3020
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.2919677008074797,
|
| 1071 |
+
"grad_norm": 1.446283221244812,
|
| 1072 |
+
"learning_rate": 0.00011392548519620342,
|
| 1073 |
+
"loss": 1.4232,
|
| 1074 |
+
"step": 3040
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.3004674883127922,
|
| 1078 |
+
"grad_norm": 1.770347237586975,
|
| 1079 |
+
"learning_rate": 0.00011335883269584928,
|
| 1080 |
+
"loss": 1.4471,
|
| 1081 |
+
"step": 3060
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.3089672758181046,
|
| 1085 |
+
"grad_norm": 1.6366223096847534,
|
| 1086 |
+
"learning_rate": 0.00011279218019549511,
|
| 1087 |
+
"loss": 1.3898,
|
| 1088 |
+
"step": 3080
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.317467063323417,
|
| 1092 |
+
"grad_norm": 1.6164251565933228,
|
| 1093 |
+
"learning_rate": 0.00011222552769514096,
|
| 1094 |
+
"loss": 1.4911,
|
| 1095 |
+
"step": 3100
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.3259668508287292,
|
| 1099 |
+
"grad_norm": 1.72907292842865,
|
| 1100 |
+
"learning_rate": 0.0001116588751947868,
|
| 1101 |
+
"loss": 1.4324,
|
| 1102 |
+
"step": 3120
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.3344666383340416,
|
| 1106 |
+
"grad_norm": 1.5645689964294434,
|
| 1107 |
+
"learning_rate": 0.00011109222269443265,
|
| 1108 |
+
"loss": 1.4571,
|
| 1109 |
+
"step": 3140
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.342966425839354,
|
| 1113 |
+
"grad_norm": 1.6170058250427246,
|
| 1114 |
+
"learning_rate": 0.00011052557019407848,
|
| 1115 |
+
"loss": 1.4016,
|
| 1116 |
+
"step": 3160
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.3514662133446664,
|
| 1120 |
+
"grad_norm": 1.806199312210083,
|
| 1121 |
+
"learning_rate": 0.00010995891769372432,
|
| 1122 |
+
"loss": 1.3691,
|
| 1123 |
+
"step": 3180
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.3599660008499788,
|
| 1127 |
+
"grad_norm": 1.3674649000167847,
|
| 1128 |
+
"learning_rate": 0.00010939226519337018,
|
| 1129 |
+
"loss": 1.3924,
|
| 1130 |
+
"step": 3200
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.368465788355291,
|
| 1134 |
+
"grad_norm": 1.7301322221755981,
|
| 1135 |
+
"learning_rate": 0.00010882561269301601,
|
| 1136 |
+
"loss": 1.4296,
|
| 1137 |
+
"step": 3220
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.3769655758606034,
|
| 1141 |
+
"grad_norm": 1.4442013502120972,
|
| 1142 |
+
"learning_rate": 0.00010825896019266186,
|
| 1143 |
+
"loss": 1.4403,
|
| 1144 |
+
"step": 3240
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.385465363365916,
|
| 1148 |
+
"grad_norm": 1.838722586631775,
|
| 1149 |
+
"learning_rate": 0.0001076923076923077,
|
| 1150 |
+
"loss": 1.4345,
|
| 1151 |
+
"step": 3260
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.3939651508712283,
|
| 1155 |
+
"grad_norm": 1.4899051189422607,
|
| 1156 |
+
"learning_rate": 0.00010712565519195355,
|
| 1157 |
+
"loss": 1.4075,
|
| 1158 |
+
"step": 3280
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.4024649383765406,
|
| 1162 |
+
"grad_norm": 1.5684807300567627,
|
| 1163 |
+
"learning_rate": 0.00010655900269159938,
|
| 1164 |
+
"loss": 1.3676,
|
| 1165 |
+
"step": 3300
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.410964725881853,
|
| 1169 |
+
"grad_norm": 1.5851366519927979,
|
| 1170 |
+
"learning_rate": 0.00010599235019124522,
|
| 1171 |
+
"loss": 1.4093,
|
| 1172 |
+
"step": 3320
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.4194645133871653,
|
| 1176 |
+
"grad_norm": 1.5306929349899292,
|
| 1177 |
+
"learning_rate": 0.00010542569769089105,
|
| 1178 |
+
"loss": 1.4281,
|
| 1179 |
+
"step": 3340
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.4279643008924776,
|
| 1183 |
+
"grad_norm": 1.798202633857727,
|
| 1184 |
+
"learning_rate": 0.00010485904519053691,
|
| 1185 |
+
"loss": 1.405,
|
| 1186 |
+
"step": 3360
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.43646408839779,
|
| 1190 |
+
"grad_norm": 1.725794792175293,
|
| 1191 |
+
"learning_rate": 0.00010429239269018276,
|
| 1192 |
+
"loss": 1.4055,
|
| 1193 |
+
"step": 3380
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.4449638759031025,
|
| 1197 |
+
"grad_norm": 1.4544621706008911,
|
| 1198 |
+
"learning_rate": 0.00010372574018982859,
|
| 1199 |
+
"loss": 1.4608,
|
| 1200 |
+
"step": 3400
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.4534636634084148,
|
| 1204 |
+
"grad_norm": 1.6607258319854736,
|
| 1205 |
+
"learning_rate": 0.00010315908768947445,
|
| 1206 |
+
"loss": 1.3565,
|
| 1207 |
+
"step": 3420
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.4619634509137271,
|
| 1211 |
+
"grad_norm": 1.3560140132904053,
|
| 1212 |
+
"learning_rate": 0.00010259243518912028,
|
| 1213 |
+
"loss": 1.4086,
|
| 1214 |
+
"step": 3440
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.4704632384190395,
|
| 1218 |
+
"grad_norm": 1.5847728252410889,
|
| 1219 |
+
"learning_rate": 0.00010202578268876612,
|
| 1220 |
+
"loss": 1.4006,
|
| 1221 |
+
"step": 3460
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.4789630259243518,
|
| 1225 |
+
"grad_norm": 1.555255651473999,
|
| 1226 |
+
"learning_rate": 0.00010145913018841195,
|
| 1227 |
+
"loss": 1.4639,
|
| 1228 |
+
"step": 3480
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.4874628134296644,
|
| 1232 |
+
"grad_norm": 1.389131784439087,
|
| 1233 |
+
"learning_rate": 0.0001008924776880578,
|
| 1234 |
+
"loss": 1.4167,
|
| 1235 |
+
"step": 3500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.4959626009349767,
|
| 1239 |
+
"grad_norm": 1.435861349105835,
|
| 1240 |
+
"learning_rate": 0.00010032582518770364,
|
| 1241 |
+
"loss": 1.4018,
|
| 1242 |
+
"step": 3520
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.504462388440289,
|
| 1246 |
+
"grad_norm": 2.1325809955596924,
|
| 1247 |
+
"learning_rate": 9.975917268734949e-05,
|
| 1248 |
+
"loss": 1.4261,
|
| 1249 |
+
"step": 3540
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.5129621759456013,
|
| 1253 |
+
"grad_norm": 1.6307079792022705,
|
| 1254 |
+
"learning_rate": 9.919252018699533e-05,
|
| 1255 |
+
"loss": 1.4596,
|
| 1256 |
+
"step": 3560
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.5214619634509137,
|
| 1260 |
+
"grad_norm": 1.5455667972564697,
|
| 1261 |
+
"learning_rate": 9.862586768664118e-05,
|
| 1262 |
+
"loss": 1.4111,
|
| 1263 |
+
"step": 3580
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.5299617509562262,
|
| 1267 |
+
"grad_norm": 1.3528661727905273,
|
| 1268 |
+
"learning_rate": 9.8059215186287e-05,
|
| 1269 |
+
"loss": 1.4634,
|
| 1270 |
+
"step": 3600
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.5384615384615383,
|
| 1274 |
+
"grad_norm": 1.477866768836975,
|
| 1275 |
+
"learning_rate": 9.749256268593285e-05,
|
| 1276 |
+
"loss": 1.503,
|
| 1277 |
+
"step": 3620
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.5469613259668509,
|
| 1281 |
+
"grad_norm": 1.5204942226409912,
|
| 1282 |
+
"learning_rate": 9.692591018557869e-05,
|
| 1283 |
+
"loss": 1.4811,
|
| 1284 |
+
"step": 3640
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.5554611134721632,
|
| 1288 |
+
"grad_norm": 1.5966800451278687,
|
| 1289 |
+
"learning_rate": 9.635925768522453e-05,
|
| 1290 |
+
"loss": 1.4768,
|
| 1291 |
+
"step": 3660
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.5639609009774755,
|
| 1295 |
+
"grad_norm": 1.538609504699707,
|
| 1296 |
+
"learning_rate": 9.579260518487039e-05,
|
| 1297 |
+
"loss": 1.4379,
|
| 1298 |
+
"step": 3680
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.572460688482788,
|
| 1302 |
+
"grad_norm": 1.6952332258224487,
|
| 1303 |
+
"learning_rate": 9.522595268451623e-05,
|
| 1304 |
+
"loss": 1.4503,
|
| 1305 |
+
"step": 3700
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.5809604759881002,
|
| 1309 |
+
"grad_norm": 1.4433083534240723,
|
| 1310 |
+
"learning_rate": 9.465930018416208e-05,
|
| 1311 |
+
"loss": 1.4461,
|
| 1312 |
+
"step": 3720
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.5894602634934127,
|
| 1316 |
+
"grad_norm": 1.6331605911254883,
|
| 1317 |
+
"learning_rate": 9.40926476838079e-05,
|
| 1318 |
+
"loss": 1.4212,
|
| 1319 |
+
"step": 3740
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.597960050998725,
|
| 1323 |
+
"grad_norm": 2.1244919300079346,
|
| 1324 |
+
"learning_rate": 9.352599518345375e-05,
|
| 1325 |
+
"loss": 1.3775,
|
| 1326 |
+
"step": 3760
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.6064598385040374,
|
| 1330 |
+
"grad_norm": 1.6804299354553223,
|
| 1331 |
+
"learning_rate": 9.295934268309959e-05,
|
| 1332 |
+
"loss": 1.4365,
|
| 1333 |
+
"step": 3780
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.6149596260093497,
|
| 1337 |
+
"grad_norm": 1.5793712139129639,
|
| 1338 |
+
"learning_rate": 9.239269018274543e-05,
|
| 1339 |
+
"loss": 1.3996,
|
| 1340 |
+
"step": 3800
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.623459413514662,
|
| 1344 |
+
"grad_norm": 1.646560788154602,
|
| 1345 |
+
"learning_rate": 9.182603768239128e-05,
|
| 1346 |
+
"loss": 1.4735,
|
| 1347 |
+
"step": 3820
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.6319592010199746,
|
| 1351 |
+
"grad_norm": 1.6244877576828003,
|
| 1352 |
+
"learning_rate": 9.125938518203712e-05,
|
| 1353 |
+
"loss": 1.4646,
|
| 1354 |
+
"step": 3840
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.6404589885252867,
|
| 1358 |
+
"grad_norm": 1.4168405532836914,
|
| 1359 |
+
"learning_rate": 9.069273268168296e-05,
|
| 1360 |
+
"loss": 1.3962,
|
| 1361 |
+
"step": 3860
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.6489587760305993,
|
| 1365 |
+
"grad_norm": 1.4018287658691406,
|
| 1366 |
+
"learning_rate": 9.01260801813288e-05,
|
| 1367 |
+
"loss": 1.3747,
|
| 1368 |
+
"step": 3880
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.6574585635359116,
|
| 1372 |
+
"grad_norm": 1.3393577337265015,
|
| 1373 |
+
"learning_rate": 8.955942768097465e-05,
|
| 1374 |
+
"loss": 1.3644,
|
| 1375 |
+
"step": 3900
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.665958351041224,
|
| 1379 |
+
"grad_norm": 1.5588535070419312,
|
| 1380 |
+
"learning_rate": 8.899277518062049e-05,
|
| 1381 |
+
"loss": 1.417,
|
| 1382 |
+
"step": 3920
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.6744581385465365,
|
| 1386 |
+
"grad_norm": 1.4518215656280518,
|
| 1387 |
+
"learning_rate": 8.842612268026633e-05,
|
| 1388 |
+
"loss": 1.4177,
|
| 1389 |
+
"step": 3940
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.6829579260518486,
|
| 1393 |
+
"grad_norm": 1.593959093093872,
|
| 1394 |
+
"learning_rate": 8.785947017991218e-05,
|
| 1395 |
+
"loss": 1.4692,
|
| 1396 |
+
"step": 3960
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.6914577135571611,
|
| 1400 |
+
"grad_norm": 1.61430025100708,
|
| 1401 |
+
"learning_rate": 8.729281767955802e-05,
|
| 1402 |
+
"loss": 1.4231,
|
| 1403 |
+
"step": 3980
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.6999575010624735,
|
| 1407 |
+
"grad_norm": 1.5006210803985596,
|
| 1408 |
+
"learning_rate": 8.672616517920386e-05,
|
| 1409 |
+
"loss": 1.4632,
|
| 1410 |
+
"step": 4000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.7084572885677858,
|
| 1414 |
+
"grad_norm": 1.5484602451324463,
|
| 1415 |
+
"learning_rate": 8.615951267884969e-05,
|
| 1416 |
+
"loss": 1.4282,
|
| 1417 |
+
"step": 4020
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.7169570760730983,
|
| 1421 |
+
"grad_norm": 1.667822003364563,
|
| 1422 |
+
"learning_rate": 8.559286017849553e-05,
|
| 1423 |
+
"loss": 1.3641,
|
| 1424 |
+
"step": 4040
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.7254568635784104,
|
| 1428 |
+
"grad_norm": 1.6226531267166138,
|
| 1429 |
+
"learning_rate": 8.502620767814138e-05,
|
| 1430 |
+
"loss": 1.4197,
|
| 1431 |
+
"step": 4060
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.733956651083723,
|
| 1435 |
+
"grad_norm": 2.0089526176452637,
|
| 1436 |
+
"learning_rate": 8.445955517778723e-05,
|
| 1437 |
+
"loss": 1.4129,
|
| 1438 |
+
"step": 4080
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.7424564385890353,
|
| 1442 |
+
"grad_norm": 1.3930327892303467,
|
| 1443 |
+
"learning_rate": 8.389290267743307e-05,
|
| 1444 |
+
"loss": 1.3614,
|
| 1445 |
+
"step": 4100
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.7509562260943476,
|
| 1449 |
+
"grad_norm": 1.890655755996704,
|
| 1450 |
+
"learning_rate": 8.332625017707892e-05,
|
| 1451 |
+
"loss": 1.4578,
|
| 1452 |
+
"step": 4120
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.75945601359966,
|
| 1456 |
+
"grad_norm": 1.7144534587860107,
|
| 1457 |
+
"learning_rate": 8.275959767672476e-05,
|
| 1458 |
+
"loss": 1.4148,
|
| 1459 |
+
"step": 4140
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.7679558011049723,
|
| 1463 |
+
"grad_norm": 1.5091826915740967,
|
| 1464 |
+
"learning_rate": 8.219294517637059e-05,
|
| 1465 |
+
"loss": 1.4203,
|
| 1466 |
+
"step": 4160
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.7764555886102849,
|
| 1470 |
+
"grad_norm": 1.7839044332504272,
|
| 1471 |
+
"learning_rate": 8.162629267601643e-05,
|
| 1472 |
+
"loss": 1.3824,
|
| 1473 |
+
"step": 4180
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.784955376115597,
|
| 1477 |
+
"grad_norm": 1.661871075630188,
|
| 1478 |
+
"learning_rate": 8.105964017566228e-05,
|
| 1479 |
+
"loss": 1.4356,
|
| 1480 |
+
"step": 4200
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.7934551636209095,
|
| 1484 |
+
"grad_norm": 1.4366284608840942,
|
| 1485 |
+
"learning_rate": 8.049298767530812e-05,
|
| 1486 |
+
"loss": 1.3839,
|
| 1487 |
+
"step": 4220
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.8019549511262218,
|
| 1491 |
+
"grad_norm": 1.5518572330474854,
|
| 1492 |
+
"learning_rate": 7.992633517495396e-05,
|
| 1493 |
+
"loss": 1.4134,
|
| 1494 |
+
"step": 4240
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.8104547386315342,
|
| 1498 |
+
"grad_norm": 1.652972936630249,
|
| 1499 |
+
"learning_rate": 7.93596826745998e-05,
|
| 1500 |
+
"loss": 1.4234,
|
| 1501 |
+
"step": 4260
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.8189545261368467,
|
| 1505 |
+
"grad_norm": 1.4948612451553345,
|
| 1506 |
+
"learning_rate": 7.879303017424565e-05,
|
| 1507 |
+
"loss": 1.3798,
|
| 1508 |
+
"step": 4280
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.8274543136421588,
|
| 1512 |
+
"grad_norm": 1.6756293773651123,
|
| 1513 |
+
"learning_rate": 7.822637767389149e-05,
|
| 1514 |
+
"loss": 1.4239,
|
| 1515 |
+
"step": 4300
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.8359541011474714,
|
| 1519 |
+
"grad_norm": 1.7066694498062134,
|
| 1520 |
+
"learning_rate": 7.765972517353733e-05,
|
| 1521 |
+
"loss": 1.4485,
|
| 1522 |
+
"step": 4320
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.8444538886527837,
|
| 1526 |
+
"grad_norm": 1.478449821472168,
|
| 1527 |
+
"learning_rate": 7.709307267318317e-05,
|
| 1528 |
+
"loss": 1.3998,
|
| 1529 |
+
"step": 4340
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.852953676158096,
|
| 1533 |
+
"grad_norm": 1.7076212167739868,
|
| 1534 |
+
"learning_rate": 7.652642017282902e-05,
|
| 1535 |
+
"loss": 1.4249,
|
| 1536 |
+
"step": 4360
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.8614534636634086,
|
| 1540 |
+
"grad_norm": 1.5418049097061157,
|
| 1541 |
+
"learning_rate": 7.595976767247486e-05,
|
| 1542 |
+
"loss": 1.3806,
|
| 1543 |
+
"step": 4380
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.8699532511687207,
|
| 1547 |
+
"grad_norm": 1.668404459953308,
|
| 1548 |
+
"learning_rate": 7.53931151721207e-05,
|
| 1549 |
+
"loss": 1.4088,
|
| 1550 |
+
"step": 4400
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.8784530386740332,
|
| 1554 |
+
"grad_norm": 2.0103743076324463,
|
| 1555 |
+
"learning_rate": 7.482646267176655e-05,
|
| 1556 |
+
"loss": 1.4432,
|
| 1557 |
+
"step": 4420
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.8869528261793456,
|
| 1561 |
+
"grad_norm": 1.8902521133422852,
|
| 1562 |
+
"learning_rate": 7.425981017141237e-05,
|
| 1563 |
+
"loss": 1.4262,
|
| 1564 |
+
"step": 4440
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.895452613684658,
|
| 1568 |
+
"grad_norm": 1.493699550628662,
|
| 1569 |
+
"learning_rate": 7.369315767105822e-05,
|
| 1570 |
+
"loss": 1.402,
|
| 1571 |
+
"step": 4460
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.9039524011899702,
|
| 1575 |
+
"grad_norm": 1.617872953414917,
|
| 1576 |
+
"learning_rate": 7.312650517070407e-05,
|
| 1577 |
+
"loss": 1.4409,
|
| 1578 |
+
"step": 4480
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.9124521886952826,
|
| 1582 |
+
"grad_norm": 1.5638338327407837,
|
| 1583 |
+
"learning_rate": 7.255985267034992e-05,
|
| 1584 |
+
"loss": 1.3933,
|
| 1585 |
+
"step": 4500
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.920951976200595,
|
| 1589 |
+
"grad_norm": 1.6773780584335327,
|
| 1590 |
+
"learning_rate": 7.199320016999576e-05,
|
| 1591 |
+
"loss": 1.4084,
|
| 1592 |
+
"step": 4520
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.9294517637059072,
|
| 1596 |
+
"grad_norm": 1.5437266826629639,
|
| 1597 |
+
"learning_rate": 7.14265476696416e-05,
|
| 1598 |
+
"loss": 1.4419,
|
| 1599 |
+
"step": 4540
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.9379515512112198,
|
| 1603 |
+
"grad_norm": 1.5624651908874512,
|
| 1604 |
+
"learning_rate": 7.085989516928744e-05,
|
| 1605 |
+
"loss": 1.3479,
|
| 1606 |
+
"step": 4560
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.946451338716532,
|
| 1610 |
+
"grad_norm": 1.594768762588501,
|
| 1611 |
+
"learning_rate": 7.029324266893327e-05,
|
| 1612 |
+
"loss": 1.4021,
|
| 1613 |
+
"step": 4580
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.9549511262218444,
|
| 1617 |
+
"grad_norm": 1.7385071516036987,
|
| 1618 |
+
"learning_rate": 6.972659016857912e-05,
|
| 1619 |
+
"loss": 1.3459,
|
| 1620 |
+
"step": 4600
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.963450913727157,
|
| 1624 |
+
"grad_norm": 1.835210919380188,
|
| 1625 |
+
"learning_rate": 6.915993766822496e-05,
|
| 1626 |
+
"loss": 1.4334,
|
| 1627 |
+
"step": 4620
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.971950701232469,
|
| 1631 |
+
"grad_norm": 1.3983690738677979,
|
| 1632 |
+
"learning_rate": 6.85932851678708e-05,
|
| 1633 |
+
"loss": 1.396,
|
| 1634 |
+
"step": 4640
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.9804504887377816,
|
| 1638 |
+
"grad_norm": 1.4692546129226685,
|
| 1639 |
+
"learning_rate": 6.802663266751664e-05,
|
| 1640 |
+
"loss": 1.4184,
|
| 1641 |
+
"step": 4660
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.988950276243094,
|
| 1645 |
+
"grad_norm": 2.199734926223755,
|
| 1646 |
+
"learning_rate": 6.74599801671625e-05,
|
| 1647 |
+
"loss": 1.3902,
|
| 1648 |
+
"step": 4680
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.9974500637484063,
|
| 1652 |
+
"grad_norm": 1.8094977140426636,
|
| 1653 |
+
"learning_rate": 6.689332766680833e-05,
|
| 1654 |
+
"loss": 1.3973,
|
| 1655 |
+
"step": 4700
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.005949851253719,
|
| 1659 |
+
"grad_norm": 1.4437006711959839,
|
| 1660 |
+
"learning_rate": 6.632667516645417e-05,
|
| 1661 |
+
"loss": 1.3595,
|
| 1662 |
+
"step": 4720
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.014449638759031,
|
| 1666 |
+
"grad_norm": 1.6683040857315063,
|
| 1667 |
+
"learning_rate": 6.576002266610002e-05,
|
| 1668 |
+
"loss": 1.3589,
|
| 1669 |
+
"step": 4740
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.0229494262643435,
|
| 1673 |
+
"grad_norm": 1.5770437717437744,
|
| 1674 |
+
"learning_rate": 6.519337016574586e-05,
|
| 1675 |
+
"loss": 1.3924,
|
| 1676 |
+
"step": 4760
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.0314492137696556,
|
| 1680 |
+
"grad_norm": 1.6709238290786743,
|
| 1681 |
+
"learning_rate": 6.465505029040941e-05,
|
| 1682 |
+
"loss": 1.385,
|
| 1683 |
+
"step": 4780
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.039949001274968,
|
| 1687 |
+
"grad_norm": 1.4806042909622192,
|
| 1688 |
+
"learning_rate": 6.408839779005525e-05,
|
| 1689 |
+
"loss": 1.3821,
|
| 1690 |
+
"step": 4800
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.0484487887802807,
|
| 1694 |
+
"grad_norm": 1.9815375804901123,
|
| 1695 |
+
"learning_rate": 6.352174528970109e-05,
|
| 1696 |
+
"loss": 1.3698,
|
| 1697 |
+
"step": 4820
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.056948576285593,
|
| 1701 |
+
"grad_norm": 1.5569688081741333,
|
| 1702 |
+
"learning_rate": 6.295509278934694e-05,
|
| 1703 |
+
"loss": 1.2949,
|
| 1704 |
+
"step": 4840
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.0654483637909054,
|
| 1708 |
+
"grad_norm": 1.7990926504135132,
|
| 1709 |
+
"learning_rate": 6.238844028899278e-05,
|
| 1710 |
+
"loss": 1.3434,
|
| 1711 |
+
"step": 4860
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.0739481512962175,
|
| 1715 |
+
"grad_norm": 1.6309067010879517,
|
| 1716 |
+
"learning_rate": 6.182178778863862e-05,
|
| 1717 |
+
"loss": 1.3536,
|
| 1718 |
+
"step": 4880
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.08244793880153,
|
| 1722 |
+
"grad_norm": 1.7287702560424805,
|
| 1723 |
+
"learning_rate": 6.125513528828446e-05,
|
| 1724 |
+
"loss": 1.3648,
|
| 1725 |
+
"step": 4900
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.090947726306842,
|
| 1729 |
+
"grad_norm": 1.6067641973495483,
|
| 1730 |
+
"learning_rate": 6.06884827879303e-05,
|
| 1731 |
+
"loss": 1.3003,
|
| 1732 |
+
"step": 4920
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.0994475138121547,
|
| 1736 |
+
"grad_norm": 2.101600408554077,
|
| 1737 |
+
"learning_rate": 6.012183028757614e-05,
|
| 1738 |
+
"loss": 1.3172,
|
| 1739 |
+
"step": 4940
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.107947301317467,
|
| 1743 |
+
"grad_norm": 1.7530735731124878,
|
| 1744 |
+
"learning_rate": 5.955517778722199e-05,
|
| 1745 |
+
"loss": 1.3195,
|
| 1746 |
+
"step": 4960
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.1164470888227793,
|
| 1750 |
+
"grad_norm": 1.5520099401474,
|
| 1751 |
+
"learning_rate": 5.8988525286867834e-05,
|
| 1752 |
+
"loss": 1.2941,
|
| 1753 |
+
"step": 4980
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.124946876328092,
|
| 1757 |
+
"grad_norm": 1.8086482286453247,
|
| 1758 |
+
"learning_rate": 5.842187278651368e-05,
|
| 1759 |
+
"loss": 1.3591,
|
| 1760 |
+
"step": 5000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.133446663833404,
|
| 1764 |
+
"grad_norm": 1.7753677368164062,
|
| 1765 |
+
"learning_rate": 5.785522028615952e-05,
|
| 1766 |
+
"loss": 1.335,
|
| 1767 |
+
"step": 5020
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.1419464513387165,
|
| 1771 |
+
"grad_norm": 1.9112579822540283,
|
| 1772 |
+
"learning_rate": 5.7288567785805356e-05,
|
| 1773 |
+
"loss": 1.3363,
|
| 1774 |
+
"step": 5040
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.150446238844029,
|
| 1778 |
+
"grad_norm": 2.093616247177124,
|
| 1779 |
+
"learning_rate": 5.67219152854512e-05,
|
| 1780 |
+
"loss": 1.3008,
|
| 1781 |
+
"step": 5060
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.158946026349341,
|
| 1785 |
+
"grad_norm": 1.6216552257537842,
|
| 1786 |
+
"learning_rate": 5.615526278509704e-05,
|
| 1787 |
+
"loss": 1.3529,
|
| 1788 |
+
"step": 5080
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.1674458138546537,
|
| 1792 |
+
"grad_norm": 1.714783787727356,
|
| 1793 |
+
"learning_rate": 5.5588610284742884e-05,
|
| 1794 |
+
"loss": 1.3847,
|
| 1795 |
+
"step": 5100
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.175945601359966,
|
| 1799 |
+
"grad_norm": 2.0024187564849854,
|
| 1800 |
+
"learning_rate": 5.502195778438872e-05,
|
| 1801 |
+
"loss": 1.3623,
|
| 1802 |
+
"step": 5120
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.1844453888652784,
|
| 1806 |
+
"grad_norm": 1.5948599576950073,
|
| 1807 |
+
"learning_rate": 5.445530528403456e-05,
|
| 1808 |
+
"loss": 1.3499,
|
| 1809 |
+
"step": 5140
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.192945176370591,
|
| 1813 |
+
"grad_norm": 1.862939715385437,
|
| 1814 |
+
"learning_rate": 5.388865278368042e-05,
|
| 1815 |
+
"loss": 1.3231,
|
| 1816 |
+
"step": 5160
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.201444963875903,
|
| 1820 |
+
"grad_norm": 1.623194932937622,
|
| 1821 |
+
"learning_rate": 5.3322000283326255e-05,
|
| 1822 |
+
"loss": 1.3635,
|
| 1823 |
+
"step": 5180
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.2099447513812156,
|
| 1827 |
+
"grad_norm": 1.5168296098709106,
|
| 1828 |
+
"learning_rate": 5.27553477829721e-05,
|
| 1829 |
+
"loss": 1.2642,
|
| 1830 |
+
"step": 5200
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.2184445388865277,
|
| 1834 |
+
"grad_norm": 1.7383768558502197,
|
| 1835 |
+
"learning_rate": 5.218869528261794e-05,
|
| 1836 |
+
"loss": 1.3172,
|
| 1837 |
+
"step": 5220
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.2269443263918403,
|
| 1841 |
+
"grad_norm": 1.637037754058838,
|
| 1842 |
+
"learning_rate": 5.162204278226378e-05,
|
| 1843 |
+
"loss": 1.4083,
|
| 1844 |
+
"step": 5240
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.2354441138971524,
|
| 1848 |
+
"grad_norm": 2.1732664108276367,
|
| 1849 |
+
"learning_rate": 5.105539028190962e-05,
|
| 1850 |
+
"loss": 1.3312,
|
| 1851 |
+
"step": 5260
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.243943901402465,
|
| 1855 |
+
"grad_norm": 1.9546133279800415,
|
| 1856 |
+
"learning_rate": 5.048873778155546e-05,
|
| 1857 |
+
"loss": 1.4041,
|
| 1858 |
+
"step": 5280
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.2524436889077775,
|
| 1862 |
+
"grad_norm": 1.623448133468628,
|
| 1863 |
+
"learning_rate": 4.992208528120131e-05,
|
| 1864 |
+
"loss": 1.3266,
|
| 1865 |
+
"step": 5300
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.2609434764130896,
|
| 1869 |
+
"grad_norm": 1.6076593399047852,
|
| 1870 |
+
"learning_rate": 4.935543278084715e-05,
|
| 1871 |
+
"loss": 1.34,
|
| 1872 |
+
"step": 5320
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.269443263918402,
|
| 1876 |
+
"grad_norm": 1.7159696817398071,
|
| 1877 |
+
"learning_rate": 4.878878028049299e-05,
|
| 1878 |
+
"loss": 1.3483,
|
| 1879 |
+
"step": 5340
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.2779430514237142,
|
| 1883 |
+
"grad_norm": 2.0286951065063477,
|
| 1884 |
+
"learning_rate": 4.822212778013883e-05,
|
| 1885 |
+
"loss": 1.3935,
|
| 1886 |
+
"step": 5360
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.2864428389290268,
|
| 1890 |
+
"grad_norm": 1.7484012842178345,
|
| 1891 |
+
"learning_rate": 4.7655475279784676e-05,
|
| 1892 |
+
"loss": 1.2851,
|
| 1893 |
+
"step": 5380
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.2949426264343393,
|
| 1897 |
+
"grad_norm": 1.913295030593872,
|
| 1898 |
+
"learning_rate": 4.708882277943052e-05,
|
| 1899 |
+
"loss": 1.3141,
|
| 1900 |
+
"step": 5400
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.3034424139396514,
|
| 1904 |
+
"grad_norm": 1.3480751514434814,
|
| 1905 |
+
"learning_rate": 4.652217027907636e-05,
|
| 1906 |
+
"loss": 1.418,
|
| 1907 |
+
"step": 5420
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.311942201444964,
|
| 1911 |
+
"grad_norm": 1.6764460802078247,
|
| 1912 |
+
"learning_rate": 4.5955517778722204e-05,
|
| 1913 |
+
"loss": 1.3528,
|
| 1914 |
+
"step": 5440
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.320441988950276,
|
| 1918 |
+
"grad_norm": 2.255345106124878,
|
| 1919 |
+
"learning_rate": 4.538886527836804e-05,
|
| 1920 |
+
"loss": 1.3452,
|
| 1921 |
+
"step": 5460
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.3289417764555886,
|
| 1925 |
+
"grad_norm": 1.7120798826217651,
|
| 1926 |
+
"learning_rate": 4.482221277801388e-05,
|
| 1927 |
+
"loss": 1.416,
|
| 1928 |
+
"step": 5480
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.337441563960901,
|
| 1932 |
+
"grad_norm": 1.5951834917068481,
|
| 1933 |
+
"learning_rate": 4.425556027765973e-05,
|
| 1934 |
+
"loss": 1.4115,
|
| 1935 |
+
"step": 5500
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.3459413514662133,
|
| 1939 |
+
"grad_norm": 1.9381834268569946,
|
| 1940 |
+
"learning_rate": 4.368890777730557e-05,
|
| 1941 |
+
"loss": 1.338,
|
| 1942 |
+
"step": 5520
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.354441138971526,
|
| 1946 |
+
"grad_norm": 1.6465120315551758,
|
| 1947 |
+
"learning_rate": 4.312225527695141e-05,
|
| 1948 |
+
"loss": 1.3652,
|
| 1949 |
+
"step": 5540
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.362940926476838,
|
| 1953 |
+
"grad_norm": 1.5020956993103027,
|
| 1954 |
+
"learning_rate": 4.2555602776597253e-05,
|
| 1955 |
+
"loss": 1.3526,
|
| 1956 |
+
"step": 5560
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.3714407139821505,
|
| 1960 |
+
"grad_norm": 1.6624023914337158,
|
| 1961 |
+
"learning_rate": 4.1988950276243096e-05,
|
| 1962 |
+
"loss": 1.3685,
|
| 1963 |
+
"step": 5580
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.3799405014874626,
|
| 1967 |
+
"grad_norm": 1.9438233375549316,
|
| 1968 |
+
"learning_rate": 4.142229777588894e-05,
|
| 1969 |
+
"loss": 1.3812,
|
| 1970 |
+
"step": 5600
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.388440288992775,
|
| 1974 |
+
"grad_norm": 1.6776275634765625,
|
| 1975 |
+
"learning_rate": 4.085564527553478e-05,
|
| 1976 |
+
"loss": 1.3558,
|
| 1977 |
+
"step": 5620
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.3969400764980877,
|
| 1981 |
+
"grad_norm": 1.7344412803649902,
|
| 1982 |
+
"learning_rate": 4.0288992775180624e-05,
|
| 1983 |
+
"loss": 1.3472,
|
| 1984 |
+
"step": 5640
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.4054398640034,
|
| 1988 |
+
"grad_norm": 1.5919348001480103,
|
| 1989 |
+
"learning_rate": 3.972234027482647e-05,
|
| 1990 |
+
"loss": 1.3805,
|
| 1991 |
+
"step": 5660
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.4139396515087124,
|
| 1995 |
+
"grad_norm": 1.8995840549468994,
|
| 1996 |
+
"learning_rate": 3.91556877744723e-05,
|
| 1997 |
+
"loss": 1.3703,
|
| 1998 |
+
"step": 5680
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.4224394390140245,
|
| 2002 |
+
"grad_norm": 1.4829695224761963,
|
| 2003 |
+
"learning_rate": 3.858903527411815e-05,
|
| 2004 |
+
"loss": 1.4167,
|
| 2005 |
+
"step": 5700
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.430939226519337,
|
| 2009 |
+
"grad_norm": 1.818079948425293,
|
| 2010 |
+
"learning_rate": 3.8022382773763995e-05,
|
| 2011 |
+
"loss": 1.3363,
|
| 2012 |
+
"step": 5720
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.4394390140246496,
|
| 2016 |
+
"grad_norm": 1.7308282852172852,
|
| 2017 |
+
"learning_rate": 3.745573027340983e-05,
|
| 2018 |
+
"loss": 1.3286,
|
| 2019 |
+
"step": 5740
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.4479388015299617,
|
| 2023 |
+
"grad_norm": 1.7932735681533813,
|
| 2024 |
+
"learning_rate": 3.6889077773055674e-05,
|
| 2025 |
+
"loss": 1.389,
|
| 2026 |
+
"step": 5760
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.4564385890352742,
|
| 2030 |
+
"grad_norm": 2.104896068572998,
|
| 2031 |
+
"learning_rate": 3.632242527270152e-05,
|
| 2032 |
+
"loss": 1.33,
|
| 2033 |
+
"step": 5780
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.4649383765405863,
|
| 2037 |
+
"grad_norm": 1.7119940519332886,
|
| 2038 |
+
"learning_rate": 3.575577277234736e-05,
|
| 2039 |
+
"loss": 1.3614,
|
| 2040 |
+
"step": 5800
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.473438164045899,
|
| 2044 |
+
"grad_norm": 1.7597520351409912,
|
| 2045 |
+
"learning_rate": 3.51891202719932e-05,
|
| 2046 |
+
"loss": 1.3376,
|
| 2047 |
+
"step": 5820
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.4819379515512114,
|
| 2051 |
+
"grad_norm": 1.5762982368469238,
|
| 2052 |
+
"learning_rate": 3.4622467771639045e-05,
|
| 2053 |
+
"loss": 1.3829,
|
| 2054 |
+
"step": 5840
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.4904377390565235,
|
| 2058 |
+
"grad_norm": 1.8265308141708374,
|
| 2059 |
+
"learning_rate": 3.405581527128489e-05,
|
| 2060 |
+
"loss": 1.3436,
|
| 2061 |
+
"step": 5860
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.498937526561836,
|
| 2065 |
+
"grad_norm": 1.70365571975708,
|
| 2066 |
+
"learning_rate": 3.3489162770930724e-05,
|
| 2067 |
+
"loss": 1.3255,
|
| 2068 |
+
"step": 5880
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.507437314067148,
|
| 2072 |
+
"grad_norm": 2.1082663536071777,
|
| 2073 |
+
"learning_rate": 3.292251027057657e-05,
|
| 2074 |
+
"loss": 1.3892,
|
| 2075 |
+
"step": 5900
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.5159371015724608,
|
| 2079 |
+
"grad_norm": 1.9773534536361694,
|
| 2080 |
+
"learning_rate": 3.2355857770222416e-05,
|
| 2081 |
+
"loss": 1.3376,
|
| 2082 |
+
"step": 5920
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.524436889077773,
|
| 2086 |
+
"grad_norm": 1.7395081520080566,
|
| 2087 |
+
"learning_rate": 3.178920526986825e-05,
|
| 2088 |
+
"loss": 1.4138,
|
| 2089 |
+
"step": 5940
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.5329366765830854,
|
| 2093 |
+
"grad_norm": 1.7831342220306396,
|
| 2094 |
+
"learning_rate": 3.1222552769514095e-05,
|
| 2095 |
+
"loss": 1.3325,
|
| 2096 |
+
"step": 5960
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.541436464088398,
|
| 2100 |
+
"grad_norm": 1.4583061933517456,
|
| 2101 |
+
"learning_rate": 3.065590026915994e-05,
|
| 2102 |
+
"loss": 1.3131,
|
| 2103 |
+
"step": 5980
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.54993625159371,
|
| 2107 |
+
"grad_norm": 1.854566216468811,
|
| 2108 |
+
"learning_rate": 3.0089247768805784e-05,
|
| 2109 |
+
"loss": 1.3243,
|
| 2110 |
+
"step": 6000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.5584360390990226,
|
| 2114 |
+
"grad_norm": 1.6933608055114746,
|
| 2115 |
+
"learning_rate": 2.9522595268451626e-05,
|
| 2116 |
+
"loss": 1.3649,
|
| 2117 |
+
"step": 6020
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.566935826604335,
|
| 2121 |
+
"grad_norm": 1.571779727935791,
|
| 2122 |
+
"learning_rate": 2.8955942768097466e-05,
|
| 2123 |
+
"loss": 1.3198,
|
| 2124 |
+
"step": 6040
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.5754356141096473,
|
| 2128 |
+
"grad_norm": 1.7845191955566406,
|
| 2129 |
+
"learning_rate": 2.838929026774331e-05,
|
| 2130 |
+
"loss": 1.3612,
|
| 2131 |
+
"step": 6060
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.5839354016149594,
|
| 2135 |
+
"grad_norm": 1.586799144744873,
|
| 2136 |
+
"learning_rate": 2.7822637767389148e-05,
|
| 2137 |
+
"loss": 1.3779,
|
| 2138 |
+
"step": 6080
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.592435189120272,
|
| 2142 |
+
"grad_norm": 1.7283703088760376,
|
| 2143 |
+
"learning_rate": 2.7255985267034994e-05,
|
| 2144 |
+
"loss": 1.4086,
|
| 2145 |
+
"step": 6100
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.6009349766255845,
|
| 2149 |
+
"grad_norm": 1.6855144500732422,
|
| 2150 |
+
"learning_rate": 2.6689332766680837e-05,
|
| 2151 |
+
"loss": 1.332,
|
| 2152 |
+
"step": 6120
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.6094347641308966,
|
| 2156 |
+
"grad_norm": 1.6331347227096558,
|
| 2157 |
+
"learning_rate": 2.6122680266326676e-05,
|
| 2158 |
+
"loss": 1.3825,
|
| 2159 |
+
"step": 6140
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.617934551636209,
|
| 2163 |
+
"grad_norm": 1.776105523109436,
|
| 2164 |
+
"learning_rate": 2.555602776597252e-05,
|
| 2165 |
+
"loss": 1.3828,
|
| 2166 |
+
"step": 6160
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.6264343391415217,
|
| 2170 |
+
"grad_norm": 1.9031463861465454,
|
| 2171 |
+
"learning_rate": 2.498937526561836e-05,
|
| 2172 |
+
"loss": 1.3507,
|
| 2173 |
+
"step": 6180
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.634934126646834,
|
| 2177 |
+
"grad_norm": 1.746543526649475,
|
| 2178 |
+
"learning_rate": 2.4422722765264204e-05,
|
| 2179 |
+
"loss": 1.3965,
|
| 2180 |
+
"step": 6200
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.6434339141521463,
|
| 2184 |
+
"grad_norm": 1.577978491783142,
|
| 2185 |
+
"learning_rate": 2.3856070264910044e-05,
|
| 2186 |
+
"loss": 1.3613,
|
| 2187 |
+
"step": 6220
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 2.6519337016574585,
|
| 2191 |
+
"grad_norm": 2.0596683025360107,
|
| 2192 |
+
"learning_rate": 2.3289417764555886e-05,
|
| 2193 |
+
"loss": 1.3259,
|
| 2194 |
+
"step": 6240
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.660433489162771,
|
| 2198 |
+
"grad_norm": 1.6416441202163696,
|
| 2199 |
+
"learning_rate": 2.272276526420173e-05,
|
| 2200 |
+
"loss": 1.3975,
|
| 2201 |
+
"step": 6260
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 2.668933276668083,
|
| 2205 |
+
"grad_norm": 1.653041958808899,
|
| 2206 |
+
"learning_rate": 2.2156112763847572e-05,
|
| 2207 |
+
"loss": 1.3281,
|
| 2208 |
+
"step": 6280
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.6774330641733957,
|
| 2212 |
+
"grad_norm": 1.6398296356201172,
|
| 2213 |
+
"learning_rate": 2.1589460263493415e-05,
|
| 2214 |
+
"loss": 1.3857,
|
| 2215 |
+
"step": 6300
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 2.685932851678708,
|
| 2219 |
+
"grad_norm": 1.722346305847168,
|
| 2220 |
+
"learning_rate": 2.1022807763139254e-05,
|
| 2221 |
+
"loss": 1.3459,
|
| 2222 |
+
"step": 6320
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.6944326391840203,
|
| 2226 |
+
"grad_norm": 1.6148895025253296,
|
| 2227 |
+
"learning_rate": 2.0456155262785097e-05,
|
| 2228 |
+
"loss": 1.4212,
|
| 2229 |
+
"step": 6340
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 2.702932426689333,
|
| 2233 |
+
"grad_norm": 1.6951065063476562,
|
| 2234 |
+
"learning_rate": 1.988950276243094e-05,
|
| 2235 |
+
"loss": 1.3228,
|
| 2236 |
+
"step": 6360
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 2.711432214194645,
|
| 2240 |
+
"grad_norm": 1.6303852796554565,
|
| 2241 |
+
"learning_rate": 1.9322850262076782e-05,
|
| 2242 |
+
"loss": 1.3422,
|
| 2243 |
+
"step": 6380
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 2.7199320016999575,
|
| 2247 |
+
"grad_norm": 1.540625810623169,
|
| 2248 |
+
"learning_rate": 1.8756197761722625e-05,
|
| 2249 |
+
"loss": 1.33,
|
| 2250 |
+
"step": 6400
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.7284317892052696,
|
| 2254 |
+
"grad_norm": 1.9898580312728882,
|
| 2255 |
+
"learning_rate": 1.8189545261368468e-05,
|
| 2256 |
+
"loss": 1.4018,
|
| 2257 |
+
"step": 6420
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.736931576710582,
|
| 2261 |
+
"grad_norm": 1.809574007987976,
|
| 2262 |
+
"learning_rate": 1.762289276101431e-05,
|
| 2263 |
+
"loss": 1.3645,
|
| 2264 |
+
"step": 6440
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.7454313642158947,
|
| 2268 |
+
"grad_norm": 1.7633795738220215,
|
| 2269 |
+
"learning_rate": 1.705624026066015e-05,
|
| 2270 |
+
"loss": 1.2959,
|
| 2271 |
+
"step": 6460
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.753931151721207,
|
| 2275 |
+
"grad_norm": 1.8831983804702759,
|
| 2276 |
+
"learning_rate": 1.6489587760305992e-05,
|
| 2277 |
+
"loss": 1.3563,
|
| 2278 |
+
"step": 6480
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.7624309392265194,
|
| 2282 |
+
"grad_norm": 1.7189044952392578,
|
| 2283 |
+
"learning_rate": 1.5922935259951835e-05,
|
| 2284 |
+
"loss": 1.3696,
|
| 2285 |
+
"step": 6500
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.770930726731832,
|
| 2289 |
+
"grad_norm": 2.021745204925537,
|
| 2290 |
+
"learning_rate": 1.5356282759597678e-05,
|
| 2291 |
+
"loss": 1.3032,
|
| 2292 |
+
"step": 6520
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.779430514237144,
|
| 2296 |
+
"grad_norm": 1.7517627477645874,
|
| 2297 |
+
"learning_rate": 1.478963025924352e-05,
|
| 2298 |
+
"loss": 1.3437,
|
| 2299 |
+
"step": 6540
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.7879303017424566,
|
| 2303 |
+
"grad_norm": 1.7145280838012695,
|
| 2304 |
+
"learning_rate": 1.4222977758889362e-05,
|
| 2305 |
+
"loss": 1.3514,
|
| 2306 |
+
"step": 6560
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.7964300892477687,
|
| 2310 |
+
"grad_norm": 1.6447581052780151,
|
| 2311 |
+
"learning_rate": 1.3656325258535204e-05,
|
| 2312 |
+
"loss": 1.3583,
|
| 2313 |
+
"step": 6580
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.8049298767530813,
|
| 2317 |
+
"grad_norm": 2.2724671363830566,
|
| 2318 |
+
"learning_rate": 1.3089672758181046e-05,
|
| 2319 |
+
"loss": 1.4376,
|
| 2320 |
+
"step": 6600
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.8134296642583934,
|
| 2324 |
+
"grad_norm": 1.8688862323760986,
|
| 2325 |
+
"learning_rate": 1.252302025782689e-05,
|
| 2326 |
+
"loss": 1.3107,
|
| 2327 |
+
"step": 6620
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 2.821929451763706,
|
| 2331 |
+
"grad_norm": 1.6515421867370605,
|
| 2332 |
+
"learning_rate": 1.1956367757472731e-05,
|
| 2333 |
+
"loss": 1.314,
|
| 2334 |
+
"step": 6640
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 2.8304292392690185,
|
| 2338 |
+
"grad_norm": 1.6967641115188599,
|
| 2339 |
+
"learning_rate": 1.1389715257118574e-05,
|
| 2340 |
+
"loss": 1.3865,
|
| 2341 |
+
"step": 6660
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.8389290267743306,
|
| 2345 |
+
"grad_norm": 2.137071371078491,
|
| 2346 |
+
"learning_rate": 1.0823062756764415e-05,
|
| 2347 |
+
"loss": 1.3028,
|
| 2348 |
+
"step": 6680
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.847428814279643,
|
| 2352 |
+
"grad_norm": 2.1401865482330322,
|
| 2353 |
+
"learning_rate": 1.0256410256410256e-05,
|
| 2354 |
+
"loss": 1.3872,
|
| 2355 |
+
"step": 6700
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 2.8559286017849552,
|
| 2359 |
+
"grad_norm": 1.701802134513855,
|
| 2360 |
+
"learning_rate": 9.689757756056099e-06,
|
| 2361 |
+
"loss": 1.3266,
|
| 2362 |
+
"step": 6720
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 2.8644283892902678,
|
| 2366 |
+
"grad_norm": 1.8868361711502075,
|
| 2367 |
+
"learning_rate": 9.123105255701941e-06,
|
| 2368 |
+
"loss": 1.3023,
|
| 2369 |
+
"step": 6740
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 2.87292817679558,
|
| 2373 |
+
"grad_norm": 1.4570691585540771,
|
| 2374 |
+
"learning_rate": 8.556452755347784e-06,
|
| 2375 |
+
"loss": 1.2953,
|
| 2376 |
+
"step": 6760
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 2.8814279643008924,
|
| 2380 |
+
"grad_norm": 1.551537275314331,
|
| 2381 |
+
"learning_rate": 7.989800254993625e-06,
|
| 2382 |
+
"loss": 1.3777,
|
| 2383 |
+
"step": 6780
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 2.889927751806205,
|
| 2387 |
+
"grad_norm": 1.9063984155654907,
|
| 2388 |
+
"learning_rate": 7.423147754639467e-06,
|
| 2389 |
+
"loss": 1.3874,
|
| 2390 |
+
"step": 6800
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 2.898427539311517,
|
| 2394 |
+
"grad_norm": 1.859644889831543,
|
| 2395 |
+
"learning_rate": 6.85649525428531e-06,
|
| 2396 |
+
"loss": 1.3712,
|
| 2397 |
+
"step": 6820
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 2.9069273268168296,
|
| 2401 |
+
"grad_norm": 1.7726514339447021,
|
| 2402 |
+
"learning_rate": 6.2898427539311525e-06,
|
| 2403 |
+
"loss": 1.3823,
|
| 2404 |
+
"step": 6840
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 2.915427114322142,
|
| 2408 |
+
"grad_norm": 1.552988886833191,
|
| 2409 |
+
"learning_rate": 5.7231902535769936e-06,
|
| 2410 |
+
"loss": 1.3455,
|
| 2411 |
+
"step": 6860
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 2.9239269018274543,
|
| 2415 |
+
"grad_norm": 1.5305794477462769,
|
| 2416 |
+
"learning_rate": 5.156537753222836e-06,
|
| 2417 |
+
"loss": 1.3412,
|
| 2418 |
+
"step": 6880
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 2.932426689332767,
|
| 2422 |
+
"grad_norm": 1.8889455795288086,
|
| 2423 |
+
"learning_rate": 4.589885252868679e-06,
|
| 2424 |
+
"loss": 1.3576,
|
| 2425 |
+
"step": 6900
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 2.940926476838079,
|
| 2429 |
+
"grad_norm": 1.7747056484222412,
|
| 2430 |
+
"learning_rate": 4.023232752514521e-06,
|
| 2431 |
+
"loss": 1.346,
|
| 2432 |
+
"step": 6920
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 2.9494262643433915,
|
| 2436 |
+
"grad_norm": 1.5252270698547363,
|
| 2437 |
+
"learning_rate": 3.456580252160363e-06,
|
| 2438 |
+
"loss": 1.3317,
|
| 2439 |
+
"step": 6940
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 2.9579260518487036,
|
| 2443 |
+
"grad_norm": 1.7793165445327759,
|
| 2444 |
+
"learning_rate": 2.889927751806205e-06,
|
| 2445 |
+
"loss": 1.3725,
|
| 2446 |
+
"step": 6960
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 2.966425839354016,
|
| 2450 |
+
"grad_norm": 1.6094822883605957,
|
| 2451 |
+
"learning_rate": 2.323275251452047e-06,
|
| 2452 |
+
"loss": 1.3647,
|
| 2453 |
+
"step": 6980
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 2.9749256268593287,
|
| 2457 |
+
"grad_norm": 1.7421776056289673,
|
| 2458 |
+
"learning_rate": 1.7566227510978892e-06,
|
| 2459 |
+
"loss": 1.4039,
|
| 2460 |
+
"step": 7000
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 2.983425414364641,
|
| 2464 |
+
"grad_norm": 1.8629122972488403,
|
| 2465 |
+
"learning_rate": 1.1899702507437315e-06,
|
| 2466 |
+
"loss": 1.3356,
|
| 2467 |
+
"step": 7020
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 2.9919252018699534,
|
| 2471 |
+
"grad_norm": 1.6828492879867554,
|
| 2472 |
+
"learning_rate": 6.233177503895737e-07,
|
| 2473 |
+
"loss": 1.3754,
|
| 2474 |
+
"step": 7040
|
| 2475 |
+
}
|
| 2476 |
+
],
|
| 2477 |
+
"logging_steps": 20,
|
| 2478 |
+
"max_steps": 7059,
|
| 2479 |
+
"num_input_tokens_seen": 0,
|
| 2480 |
+
"num_train_epochs": 3,
|
| 2481 |
+
"save_steps": 500,
|
| 2482 |
+
"stateful_callbacks": {
|
| 2483 |
+
"TrainerControl": {
|
| 2484 |
+
"args": {
|
| 2485 |
+
"should_epoch_stop": false,
|
| 2486 |
+
"should_evaluate": false,
|
| 2487 |
+
"should_log": false,
|
| 2488 |
+
"should_save": true,
|
| 2489 |
+
"should_training_stop": true
|
| 2490 |
+
},
|
| 2491 |
+
"attributes": {}
|
| 2492 |
+
}
|
| 2493 |
+
},
|
| 2494 |
+
"total_flos": 8.992048570328678e+16,
|
| 2495 |
+
"train_batch_size": 4,
|
| 2496 |
+
"trial_name": null,
|
| 2497 |
+
"trial_params": null
|
| 2498 |
+
}
|
tinyllama-lora-finetuned/checkpoint-7059/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15e87998291b092367622e9a01c7bf9c9073fbba3c3325c704524d294a28c0e8
|
| 3 |
+
size 5304
|