Task: SequenceClassification
Browse files- README.md +202 -0
- adapter_config.json +36 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
- trainer_state-llama2-bnb8-QLORA-super_glue-boolq-sequence_classification.json +2014 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: meta-llama/Llama-2-7b-hf
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": [
|
| 18 |
+
"score"
|
| 19 |
+
],
|
| 20 |
+
"peft_type": "LORA",
|
| 21 |
+
"r": 8,
|
| 22 |
+
"rank_pattern": {},
|
| 23 |
+
"revision": null,
|
| 24 |
+
"target_modules": [
|
| 25 |
+
"k_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"up_proj"
|
| 32 |
+
],
|
| 33 |
+
"task_type": "SEQ_CLS",
|
| 34 |
+
"use_dora": false,
|
| 35 |
+
"use_rslora": false
|
| 36 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70f771a17994d83fcf017d2331c0b59891c4620129028b9f69aec57a4768e8fc
|
| 3 |
+
size 80045992
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": "</s>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
+
"unk_token": "<unk>",
|
| 40 |
+
"use_default_system_prompt": false
|
| 41 |
+
}
|
trainer_state-llama2-bnb8-QLORA-super_glue-boolq-sequence_classification.json
ADDED
|
@@ -0,0 +1,2014 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.984,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 124,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016,
|
| 13 |
+
"grad_norm": NaN,
|
| 14 |
+
"learning_rate": 0.0,
|
| 15 |
+
"loss": 1.1733,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.016,
|
| 20 |
+
"eval_accuracy": 0.364,
|
| 21 |
+
"eval_loss": 1.2354755401611328,
|
| 22 |
+
"eval_runtime": 11.4949,
|
| 23 |
+
"eval_samples_per_second": 21.749,
|
| 24 |
+
"eval_steps_per_second": 2.784,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.032,
|
| 29 |
+
"grad_norm": NaN,
|
| 30 |
+
"learning_rate": 0.0,
|
| 31 |
+
"loss": 1.1385,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.032,
|
| 36 |
+
"eval_accuracy": 0.364,
|
| 37 |
+
"eval_loss": 1.2354755401611328,
|
| 38 |
+
"eval_runtime": 11.3512,
|
| 39 |
+
"eval_samples_per_second": 22.024,
|
| 40 |
+
"eval_steps_per_second": 2.819,
|
| 41 |
+
"step": 2
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.048,
|
| 45 |
+
"grad_norm": NaN,
|
| 46 |
+
"learning_rate": 0.0,
|
| 47 |
+
"loss": 1.1504,
|
| 48 |
+
"step": 3
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.048,
|
| 52 |
+
"eval_accuracy": 0.364,
|
| 53 |
+
"eval_loss": 1.2354755401611328,
|
| 54 |
+
"eval_runtime": 11.554,
|
| 55 |
+
"eval_samples_per_second": 21.638,
|
| 56 |
+
"eval_steps_per_second": 2.77,
|
| 57 |
+
"step": 3
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.064,
|
| 61 |
+
"grad_norm": NaN,
|
| 62 |
+
"learning_rate": 0.0,
|
| 63 |
+
"loss": 1.4467,
|
| 64 |
+
"step": 4
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.064,
|
| 68 |
+
"eval_accuracy": 0.364,
|
| 69 |
+
"eval_loss": 1.2354755401611328,
|
| 70 |
+
"eval_runtime": 11.2846,
|
| 71 |
+
"eval_samples_per_second": 22.154,
|
| 72 |
+
"eval_steps_per_second": 2.836,
|
| 73 |
+
"step": 4
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.08,
|
| 77 |
+
"grad_norm": Infinity,
|
| 78 |
+
"learning_rate": 0.0,
|
| 79 |
+
"loss": 1.0915,
|
| 80 |
+
"step": 5
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08,
|
| 84 |
+
"eval_accuracy": 0.364,
|
| 85 |
+
"eval_loss": 1.2354755401611328,
|
| 86 |
+
"eval_runtime": 11.2925,
|
| 87 |
+
"eval_samples_per_second": 22.138,
|
| 88 |
+
"eval_steps_per_second": 2.834,
|
| 89 |
+
"step": 5
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.096,
|
| 93 |
+
"grad_norm": 87.5323715209961,
|
| 94 |
+
"learning_rate": 2.5e-05,
|
| 95 |
+
"loss": 1.3424,
|
| 96 |
+
"step": 6
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.096,
|
| 100 |
+
"eval_accuracy": 0.364,
|
| 101 |
+
"eval_loss": 1.2354755401611328,
|
| 102 |
+
"eval_runtime": 11.311,
|
| 103 |
+
"eval_samples_per_second": 22.102,
|
| 104 |
+
"eval_steps_per_second": 2.829,
|
| 105 |
+
"step": 6
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.112,
|
| 109 |
+
"grad_norm": 50.48843765258789,
|
| 110 |
+
"learning_rate": 5e-05,
|
| 111 |
+
"loss": 1.1041,
|
| 112 |
+
"step": 7
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.112,
|
| 116 |
+
"eval_accuracy": 0.432,
|
| 117 |
+
"eval_loss": 1.0213314294815063,
|
| 118 |
+
"eval_runtime": 11.2832,
|
| 119 |
+
"eval_samples_per_second": 22.157,
|
| 120 |
+
"eval_steps_per_second": 2.836,
|
| 121 |
+
"step": 7
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.128,
|
| 125 |
+
"grad_norm": 12.972390174865723,
|
| 126 |
+
"learning_rate": 4.959016393442623e-05,
|
| 127 |
+
"loss": 0.751,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.128,
|
| 132 |
+
"eval_accuracy": 0.456,
|
| 133 |
+
"eval_loss": 0.9333825707435608,
|
| 134 |
+
"eval_runtime": 11.3015,
|
| 135 |
+
"eval_samples_per_second": 22.121,
|
| 136 |
+
"eval_steps_per_second": 2.831,
|
| 137 |
+
"step": 8
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.144,
|
| 141 |
+
"grad_norm": 38.46497344970703,
|
| 142 |
+
"learning_rate": 4.918032786885246e-05,
|
| 143 |
+
"loss": 0.9293,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.144,
|
| 148 |
+
"eval_accuracy": 0.536,
|
| 149 |
+
"eval_loss": 0.9040337800979614,
|
| 150 |
+
"eval_runtime": 11.3267,
|
| 151 |
+
"eval_samples_per_second": 22.072,
|
| 152 |
+
"eval_steps_per_second": 2.825,
|
| 153 |
+
"step": 9
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.16,
|
| 157 |
+
"grad_norm": 9.813628196716309,
|
| 158 |
+
"learning_rate": 4.8770491803278687e-05,
|
| 159 |
+
"loss": 0.6036,
|
| 160 |
+
"step": 10
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.16,
|
| 164 |
+
"eval_accuracy": 0.58,
|
| 165 |
+
"eval_loss": 1.0835610628128052,
|
| 166 |
+
"eval_runtime": 11.3275,
|
| 167 |
+
"eval_samples_per_second": 22.07,
|
| 168 |
+
"eval_steps_per_second": 2.825,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.176,
|
| 173 |
+
"grad_norm": 11.096491813659668,
|
| 174 |
+
"learning_rate": 4.836065573770492e-05,
|
| 175 |
+
"loss": 0.9184,
|
| 176 |
+
"step": 11
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.176,
|
| 180 |
+
"eval_accuracy": 0.596,
|
| 181 |
+
"eval_loss": 1.2577338218688965,
|
| 182 |
+
"eval_runtime": 11.2856,
|
| 183 |
+
"eval_samples_per_second": 22.152,
|
| 184 |
+
"eval_steps_per_second": 2.835,
|
| 185 |
+
"step": 11
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.192,
|
| 189 |
+
"grad_norm": 45.111083984375,
|
| 190 |
+
"learning_rate": 4.795081967213115e-05,
|
| 191 |
+
"loss": 0.8972,
|
| 192 |
+
"step": 12
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.192,
|
| 196 |
+
"eval_accuracy": 0.612,
|
| 197 |
+
"eval_loss": 1.280572533607483,
|
| 198 |
+
"eval_runtime": 11.296,
|
| 199 |
+
"eval_samples_per_second": 22.132,
|
| 200 |
+
"eval_steps_per_second": 2.833,
|
| 201 |
+
"step": 12
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.208,
|
| 205 |
+
"grad_norm": 54.95970153808594,
|
| 206 |
+
"learning_rate": 4.754098360655738e-05,
|
| 207 |
+
"loss": 1.1253,
|
| 208 |
+
"step": 13
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.208,
|
| 212 |
+
"eval_accuracy": 0.612,
|
| 213 |
+
"eval_loss": 1.1115046739578247,
|
| 214 |
+
"eval_runtime": 11.3216,
|
| 215 |
+
"eval_samples_per_second": 22.082,
|
| 216 |
+
"eval_steps_per_second": 2.826,
|
| 217 |
+
"step": 13
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.224,
|
| 221 |
+
"grad_norm": 19.976964950561523,
|
| 222 |
+
"learning_rate": 4.713114754098361e-05,
|
| 223 |
+
"loss": 0.9591,
|
| 224 |
+
"step": 14
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.224,
|
| 228 |
+
"eval_accuracy": 0.584,
|
| 229 |
+
"eval_loss": 0.9410788416862488,
|
| 230 |
+
"eval_runtime": 11.3197,
|
| 231 |
+
"eval_samples_per_second": 22.085,
|
| 232 |
+
"eval_steps_per_second": 2.827,
|
| 233 |
+
"step": 14
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.24,
|
| 237 |
+
"grad_norm": 21.54231834411621,
|
| 238 |
+
"learning_rate": 4.672131147540984e-05,
|
| 239 |
+
"loss": 0.4318,
|
| 240 |
+
"step": 15
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.24,
|
| 244 |
+
"eval_accuracy": 0.504,
|
| 245 |
+
"eval_loss": 0.8608736395835876,
|
| 246 |
+
"eval_runtime": 11.2959,
|
| 247 |
+
"eval_samples_per_second": 22.132,
|
| 248 |
+
"eval_steps_per_second": 2.833,
|
| 249 |
+
"step": 15
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.256,
|
| 253 |
+
"grad_norm": 31.807493209838867,
|
| 254 |
+
"learning_rate": 4.631147540983607e-05,
|
| 255 |
+
"loss": 0.7278,
|
| 256 |
+
"step": 16
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.256,
|
| 260 |
+
"eval_accuracy": 0.52,
|
| 261 |
+
"eval_loss": 0.8945115804672241,
|
| 262 |
+
"eval_runtime": 11.3237,
|
| 263 |
+
"eval_samples_per_second": 22.078,
|
| 264 |
+
"eval_steps_per_second": 2.826,
|
| 265 |
+
"step": 16
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.272,
|
| 269 |
+
"grad_norm": 27.370149612426758,
|
| 270 |
+
"learning_rate": 4.59016393442623e-05,
|
| 271 |
+
"loss": 0.8711,
|
| 272 |
+
"step": 17
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.272,
|
| 276 |
+
"eval_accuracy": 0.524,
|
| 277 |
+
"eval_loss": 0.8897060751914978,
|
| 278 |
+
"eval_runtime": 11.3355,
|
| 279 |
+
"eval_samples_per_second": 22.055,
|
| 280 |
+
"eval_steps_per_second": 2.823,
|
| 281 |
+
"step": 17
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.288,
|
| 285 |
+
"grad_norm": 40.707698822021484,
|
| 286 |
+
"learning_rate": 4.549180327868853e-05,
|
| 287 |
+
"loss": 0.9991,
|
| 288 |
+
"step": 18
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.288,
|
| 292 |
+
"eval_accuracy": 0.548,
|
| 293 |
+
"eval_loss": 0.8214626312255859,
|
| 294 |
+
"eval_runtime": 11.3233,
|
| 295 |
+
"eval_samples_per_second": 22.078,
|
| 296 |
+
"eval_steps_per_second": 2.826,
|
| 297 |
+
"step": 18
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.304,
|
| 301 |
+
"grad_norm": 13.598702430725098,
|
| 302 |
+
"learning_rate": 4.508196721311476e-05,
|
| 303 |
+
"loss": 0.807,
|
| 304 |
+
"step": 19
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.304,
|
| 308 |
+
"eval_accuracy": 0.556,
|
| 309 |
+
"eval_loss": 0.7961764931678772,
|
| 310 |
+
"eval_runtime": 11.3396,
|
| 311 |
+
"eval_samples_per_second": 22.047,
|
| 312 |
+
"eval_steps_per_second": 2.822,
|
| 313 |
+
"step": 19
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.32,
|
| 317 |
+
"grad_norm": 18.774343490600586,
|
| 318 |
+
"learning_rate": 4.467213114754098e-05,
|
| 319 |
+
"loss": 0.617,
|
| 320 |
+
"step": 20
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.32,
|
| 324 |
+
"eval_accuracy": 0.516,
|
| 325 |
+
"eval_loss": 0.807204008102417,
|
| 326 |
+
"eval_runtime": 11.3337,
|
| 327 |
+
"eval_samples_per_second": 22.058,
|
| 328 |
+
"eval_steps_per_second": 2.823,
|
| 329 |
+
"step": 20
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.336,
|
| 333 |
+
"grad_norm": 24.550052642822266,
|
| 334 |
+
"learning_rate": 4.426229508196721e-05,
|
| 335 |
+
"loss": 0.6701,
|
| 336 |
+
"step": 21
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.336,
|
| 340 |
+
"eval_accuracy": 0.552,
|
| 341 |
+
"eval_loss": 0.7810255289077759,
|
| 342 |
+
"eval_runtime": 11.3902,
|
| 343 |
+
"eval_samples_per_second": 21.949,
|
| 344 |
+
"eval_steps_per_second": 2.809,
|
| 345 |
+
"step": 21
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.352,
|
| 349 |
+
"grad_norm": 28.407976150512695,
|
| 350 |
+
"learning_rate": 4.3852459016393444e-05,
|
| 351 |
+
"loss": 0.823,
|
| 352 |
+
"step": 22
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.352,
|
| 356 |
+
"eval_accuracy": 0.552,
|
| 357 |
+
"eval_loss": 0.764638364315033,
|
| 358 |
+
"eval_runtime": 11.3671,
|
| 359 |
+
"eval_samples_per_second": 21.993,
|
| 360 |
+
"eval_steps_per_second": 2.815,
|
| 361 |
+
"step": 22
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.368,
|
| 365 |
+
"grad_norm": 31.69023895263672,
|
| 366 |
+
"learning_rate": 4.3442622950819674e-05,
|
| 367 |
+
"loss": 0.7332,
|
| 368 |
+
"step": 23
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.368,
|
| 372 |
+
"eval_accuracy": 0.6,
|
| 373 |
+
"eval_loss": 0.7719610333442688,
|
| 374 |
+
"eval_runtime": 11.3313,
|
| 375 |
+
"eval_samples_per_second": 22.063,
|
| 376 |
+
"eval_steps_per_second": 2.824,
|
| 377 |
+
"step": 23
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.384,
|
| 381 |
+
"grad_norm": 51.598724365234375,
|
| 382 |
+
"learning_rate": 4.3032786885245904e-05,
|
| 383 |
+
"loss": 1.0789,
|
| 384 |
+
"step": 24
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.384,
|
| 388 |
+
"eval_accuracy": 0.604,
|
| 389 |
+
"eval_loss": 0.792045533657074,
|
| 390 |
+
"eval_runtime": 11.3212,
|
| 391 |
+
"eval_samples_per_second": 22.082,
|
| 392 |
+
"eval_steps_per_second": 2.827,
|
| 393 |
+
"step": 24
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.4,
|
| 397 |
+
"grad_norm": 8.370189666748047,
|
| 398 |
+
"learning_rate": 4.262295081967213e-05,
|
| 399 |
+
"loss": 0.5899,
|
| 400 |
+
"step": 25
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.4,
|
| 404 |
+
"eval_accuracy": 0.588,
|
| 405 |
+
"eval_loss": 0.8152350187301636,
|
| 406 |
+
"eval_runtime": 11.2787,
|
| 407 |
+
"eval_samples_per_second": 22.166,
|
| 408 |
+
"eval_steps_per_second": 2.837,
|
| 409 |
+
"step": 25
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.416,
|
| 413 |
+
"grad_norm": 8.866107940673828,
|
| 414 |
+
"learning_rate": 4.2213114754098365e-05,
|
| 415 |
+
"loss": 0.6057,
|
| 416 |
+
"step": 26
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.416,
|
| 420 |
+
"eval_accuracy": 0.604,
|
| 421 |
+
"eval_loss": 0.8338910937309265,
|
| 422 |
+
"eval_runtime": 11.3283,
|
| 423 |
+
"eval_samples_per_second": 22.069,
|
| 424 |
+
"eval_steps_per_second": 2.825,
|
| 425 |
+
"step": 26
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.432,
|
| 429 |
+
"grad_norm": 32.09278106689453,
|
| 430 |
+
"learning_rate": 4.1803278688524595e-05,
|
| 431 |
+
"loss": 0.7418,
|
| 432 |
+
"step": 27
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.432,
|
| 436 |
+
"eval_accuracy": 0.616,
|
| 437 |
+
"eval_loss": 0.8316658735275269,
|
| 438 |
+
"eval_runtime": 11.3272,
|
| 439 |
+
"eval_samples_per_second": 22.071,
|
| 440 |
+
"eval_steps_per_second": 2.825,
|
| 441 |
+
"step": 27
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.448,
|
| 445 |
+
"grad_norm": 22.857614517211914,
|
| 446 |
+
"learning_rate": 4.1393442622950826e-05,
|
| 447 |
+
"loss": 0.8383,
|
| 448 |
+
"step": 28
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.448,
|
| 452 |
+
"eval_accuracy": 0.616,
|
| 453 |
+
"eval_loss": 0.7918907999992371,
|
| 454 |
+
"eval_runtime": 11.3212,
|
| 455 |
+
"eval_samples_per_second": 22.082,
|
| 456 |
+
"eval_steps_per_second": 2.827,
|
| 457 |
+
"step": 28
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.464,
|
| 461 |
+
"grad_norm": 22.1180362701416,
|
| 462 |
+
"learning_rate": 4.098360655737705e-05,
|
| 463 |
+
"loss": 0.8923,
|
| 464 |
+
"step": 29
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.464,
|
| 468 |
+
"eval_accuracy": 0.62,
|
| 469 |
+
"eval_loss": 0.7275803685188293,
|
| 470 |
+
"eval_runtime": 11.3478,
|
| 471 |
+
"eval_samples_per_second": 22.031,
|
| 472 |
+
"eval_steps_per_second": 2.82,
|
| 473 |
+
"step": 29
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.48,
|
| 477 |
+
"grad_norm": 43.09483337402344,
|
| 478 |
+
"learning_rate": 4.057377049180328e-05,
|
| 479 |
+
"loss": 0.9467,
|
| 480 |
+
"step": 30
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.48,
|
| 484 |
+
"eval_accuracy": 0.616,
|
| 485 |
+
"eval_loss": 0.6892617344856262,
|
| 486 |
+
"eval_runtime": 11.348,
|
| 487 |
+
"eval_samples_per_second": 22.03,
|
| 488 |
+
"eval_steps_per_second": 2.82,
|
| 489 |
+
"step": 30
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.496,
|
| 493 |
+
"grad_norm": 8.46947956085205,
|
| 494 |
+
"learning_rate": 4.016393442622951e-05,
|
| 495 |
+
"loss": 0.7778,
|
| 496 |
+
"step": 31
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.496,
|
| 500 |
+
"eval_accuracy": 0.612,
|
| 501 |
+
"eval_loss": 0.6953690052032471,
|
| 502 |
+
"eval_runtime": 11.3372,
|
| 503 |
+
"eval_samples_per_second": 22.051,
|
| 504 |
+
"eval_steps_per_second": 2.823,
|
| 505 |
+
"step": 31
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.512,
|
| 509 |
+
"grad_norm": 33.367454528808594,
|
| 510 |
+
"learning_rate": 3.975409836065574e-05,
|
| 511 |
+
"loss": 0.6468,
|
| 512 |
+
"step": 32
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.512,
|
| 516 |
+
"eval_accuracy": 0.564,
|
| 517 |
+
"eval_loss": 0.6975896954536438,
|
| 518 |
+
"eval_runtime": 11.3103,
|
| 519 |
+
"eval_samples_per_second": 22.104,
|
| 520 |
+
"eval_steps_per_second": 2.829,
|
| 521 |
+
"step": 32
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.528,
|
| 525 |
+
"grad_norm": 14.80160903930664,
|
| 526 |
+
"learning_rate": 3.934426229508197e-05,
|
| 527 |
+
"loss": 0.7333,
|
| 528 |
+
"step": 33
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.528,
|
| 532 |
+
"eval_accuracy": 0.58,
|
| 533 |
+
"eval_loss": 0.6965731978416443,
|
| 534 |
+
"eval_runtime": 11.3519,
|
| 535 |
+
"eval_samples_per_second": 22.023,
|
| 536 |
+
"eval_steps_per_second": 2.819,
|
| 537 |
+
"step": 33
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.544,
|
| 541 |
+
"grad_norm": 38.160823822021484,
|
| 542 |
+
"learning_rate": 3.89344262295082e-05,
|
| 543 |
+
"loss": 0.6591,
|
| 544 |
+
"step": 34
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.544,
|
| 548 |
+
"eval_accuracy": 0.588,
|
| 549 |
+
"eval_loss": 0.6874374747276306,
|
| 550 |
+
"eval_runtime": 11.3235,
|
| 551 |
+
"eval_samples_per_second": 22.078,
|
| 552 |
+
"eval_steps_per_second": 2.826,
|
| 553 |
+
"step": 34
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.56,
|
| 557 |
+
"grad_norm": 33.589561462402344,
|
| 558 |
+
"learning_rate": 3.8524590163934424e-05,
|
| 559 |
+
"loss": 0.7186,
|
| 560 |
+
"step": 35
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.56,
|
| 564 |
+
"eval_accuracy": 0.608,
|
| 565 |
+
"eval_loss": 0.6751595139503479,
|
| 566 |
+
"eval_runtime": 11.3159,
|
| 567 |
+
"eval_samples_per_second": 22.093,
|
| 568 |
+
"eval_steps_per_second": 2.828,
|
| 569 |
+
"step": 35
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.576,
|
| 573 |
+
"grad_norm": 12.282697677612305,
|
| 574 |
+
"learning_rate": 3.8114754098360655e-05,
|
| 575 |
+
"loss": 0.4988,
|
| 576 |
+
"step": 36
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.576,
|
| 580 |
+
"eval_accuracy": 0.616,
|
| 581 |
+
"eval_loss": 0.6890735030174255,
|
| 582 |
+
"eval_runtime": 11.3573,
|
| 583 |
+
"eval_samples_per_second": 22.012,
|
| 584 |
+
"eval_steps_per_second": 2.818,
|
| 585 |
+
"step": 36
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.592,
|
| 589 |
+
"grad_norm": 15.36685562133789,
|
| 590 |
+
"learning_rate": 3.7704918032786885e-05,
|
| 591 |
+
"loss": 0.8962,
|
| 592 |
+
"step": 37
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.592,
|
| 596 |
+
"eval_accuracy": 0.576,
|
| 597 |
+
"eval_loss": 0.7174173593521118,
|
| 598 |
+
"eval_runtime": 11.3449,
|
| 599 |
+
"eval_samples_per_second": 22.036,
|
| 600 |
+
"eval_steps_per_second": 2.821,
|
| 601 |
+
"step": 37
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.608,
|
| 605 |
+
"grad_norm": 37.992069244384766,
|
| 606 |
+
"learning_rate": 3.729508196721312e-05,
|
| 607 |
+
"loss": 0.7407,
|
| 608 |
+
"step": 38
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.608,
|
| 612 |
+
"eval_accuracy": 0.528,
|
| 613 |
+
"eval_loss": 0.7468773126602173,
|
| 614 |
+
"eval_runtime": 11.3013,
|
| 615 |
+
"eval_samples_per_second": 22.121,
|
| 616 |
+
"eval_steps_per_second": 2.832,
|
| 617 |
+
"step": 38
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.624,
|
| 621 |
+
"grad_norm": 43.514469146728516,
|
| 622 |
+
"learning_rate": 3.6885245901639346e-05,
|
| 623 |
+
"loss": 0.7984,
|
| 624 |
+
"step": 39
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.624,
|
| 628 |
+
"eval_accuracy": 0.536,
|
| 629 |
+
"eval_loss": 0.7447397708892822,
|
| 630 |
+
"eval_runtime": 11.3203,
|
| 631 |
+
"eval_samples_per_second": 22.084,
|
| 632 |
+
"eval_steps_per_second": 2.827,
|
| 633 |
+
"step": 39
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.64,
|
| 637 |
+
"grad_norm": 43.61343765258789,
|
| 638 |
+
"learning_rate": 3.6475409836065576e-05,
|
| 639 |
+
"loss": 0.6023,
|
| 640 |
+
"step": 40
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.64,
|
| 644 |
+
"eval_accuracy": 0.564,
|
| 645 |
+
"eval_loss": 0.7195525765419006,
|
| 646 |
+
"eval_runtime": 11.3049,
|
| 647 |
+
"eval_samples_per_second": 22.114,
|
| 648 |
+
"eval_steps_per_second": 2.831,
|
| 649 |
+
"step": 40
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.656,
|
| 653 |
+
"grad_norm": 59.5920295715332,
|
| 654 |
+
"learning_rate": 3.6065573770491806e-05,
|
| 655 |
+
"loss": 0.7771,
|
| 656 |
+
"step": 41
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.656,
|
| 660 |
+
"eval_accuracy": 0.604,
|
| 661 |
+
"eval_loss": 0.686376690864563,
|
| 662 |
+
"eval_runtime": 11.276,
|
| 663 |
+
"eval_samples_per_second": 22.171,
|
| 664 |
+
"eval_steps_per_second": 2.838,
|
| 665 |
+
"step": 41
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.672,
|
| 669 |
+
"grad_norm": 32.0897216796875,
|
| 670 |
+
"learning_rate": 3.5655737704918037e-05,
|
| 671 |
+
"loss": 0.6586,
|
| 672 |
+
"step": 42
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.672,
|
| 676 |
+
"eval_accuracy": 0.62,
|
| 677 |
+
"eval_loss": 0.6858681440353394,
|
| 678 |
+
"eval_runtime": 11.2967,
|
| 679 |
+
"eval_samples_per_second": 22.13,
|
| 680 |
+
"eval_steps_per_second": 2.833,
|
| 681 |
+
"step": 42
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.688,
|
| 685 |
+
"grad_norm": 7.754942893981934,
|
| 686 |
+
"learning_rate": 3.524590163934427e-05,
|
| 687 |
+
"loss": 0.5622,
|
| 688 |
+
"step": 43
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.688,
|
| 692 |
+
"eval_accuracy": 0.616,
|
| 693 |
+
"eval_loss": 0.7191852331161499,
|
| 694 |
+
"eval_runtime": 11.3359,
|
| 695 |
+
"eval_samples_per_second": 22.054,
|
| 696 |
+
"eval_steps_per_second": 2.823,
|
| 697 |
+
"step": 43
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.704,
|
| 701 |
+
"grad_norm": 13.65731143951416,
|
| 702 |
+
"learning_rate": 3.483606557377049e-05,
|
| 703 |
+
"loss": 0.6567,
|
| 704 |
+
"step": 44
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.704,
|
| 708 |
+
"eval_accuracy": 0.604,
|
| 709 |
+
"eval_loss": 0.7964421510696411,
|
| 710 |
+
"eval_runtime": 11.3043,
|
| 711 |
+
"eval_samples_per_second": 22.116,
|
| 712 |
+
"eval_steps_per_second": 2.831,
|
| 713 |
+
"step": 44
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.72,
|
| 717 |
+
"grad_norm": 13.19625473022461,
|
| 718 |
+
"learning_rate": 3.442622950819672e-05,
|
| 719 |
+
"loss": 0.637,
|
| 720 |
+
"step": 45
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.72,
|
| 724 |
+
"eval_accuracy": 0.612,
|
| 725 |
+
"eval_loss": 0.8056248426437378,
|
| 726 |
+
"eval_runtime": 11.331,
|
| 727 |
+
"eval_samples_per_second": 22.063,
|
| 728 |
+
"eval_steps_per_second": 2.824,
|
| 729 |
+
"step": 45
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.736,
|
| 733 |
+
"grad_norm": 10.382162094116211,
|
| 734 |
+
"learning_rate": 3.401639344262295e-05,
|
| 735 |
+
"loss": 0.5964,
|
| 736 |
+
"step": 46
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.736,
|
| 740 |
+
"eval_accuracy": 0.62,
|
| 741 |
+
"eval_loss": 0.8342519402503967,
|
| 742 |
+
"eval_runtime": 11.3384,
|
| 743 |
+
"eval_samples_per_second": 22.049,
|
| 744 |
+
"eval_steps_per_second": 2.822,
|
| 745 |
+
"step": 46
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.752,
|
| 749 |
+
"grad_norm": 31.208406448364258,
|
| 750 |
+
"learning_rate": 3.360655737704918e-05,
|
| 751 |
+
"loss": 0.9646,
|
| 752 |
+
"step": 47
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.752,
|
| 756 |
+
"eval_accuracy": 0.612,
|
| 757 |
+
"eval_loss": 0.7941861748695374,
|
| 758 |
+
"eval_runtime": 11.3217,
|
| 759 |
+
"eval_samples_per_second": 22.081,
|
| 760 |
+
"eval_steps_per_second": 2.826,
|
| 761 |
+
"step": 47
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.768,
|
| 765 |
+
"grad_norm": 28.09980583190918,
|
| 766 |
+
"learning_rate": 3.319672131147541e-05,
|
| 767 |
+
"loss": 0.778,
|
| 768 |
+
"step": 48
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.768,
|
| 772 |
+
"eval_accuracy": 0.62,
|
| 773 |
+
"eval_loss": 0.727009117603302,
|
| 774 |
+
"eval_runtime": 11.3124,
|
| 775 |
+
"eval_samples_per_second": 22.1,
|
| 776 |
+
"eval_steps_per_second": 2.829,
|
| 777 |
+
"step": 48
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.784,
|
| 781 |
+
"grad_norm": 26.889928817749023,
|
| 782 |
+
"learning_rate": 3.2786885245901635e-05,
|
| 783 |
+
"loss": 0.8173,
|
| 784 |
+
"step": 49
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.784,
|
| 788 |
+
"eval_accuracy": 0.62,
|
| 789 |
+
"eval_loss": 0.6923478841781616,
|
| 790 |
+
"eval_runtime": 11.3715,
|
| 791 |
+
"eval_samples_per_second": 21.985,
|
| 792 |
+
"eval_steps_per_second": 2.814,
|
| 793 |
+
"step": 49
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.8,
|
| 797 |
+
"grad_norm": 12.534849166870117,
|
| 798 |
+
"learning_rate": 3.237704918032787e-05,
|
| 799 |
+
"loss": 0.6164,
|
| 800 |
+
"step": 50
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.8,
|
| 804 |
+
"eval_accuracy": 0.66,
|
| 805 |
+
"eval_loss": 0.6402404308319092,
|
| 806 |
+
"eval_runtime": 11.6238,
|
| 807 |
+
"eval_samples_per_second": 21.508,
|
| 808 |
+
"eval_steps_per_second": 2.753,
|
| 809 |
+
"step": 50
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.816,
|
| 813 |
+
"grad_norm": 14.15957260131836,
|
| 814 |
+
"learning_rate": 3.19672131147541e-05,
|
| 815 |
+
"loss": 0.6124,
|
| 816 |
+
"step": 51
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.816,
|
| 820 |
+
"eval_accuracy": 0.648,
|
| 821 |
+
"eval_loss": 0.6378893852233887,
|
| 822 |
+
"eval_runtime": 11.4856,
|
| 823 |
+
"eval_samples_per_second": 21.766,
|
| 824 |
+
"eval_steps_per_second": 2.786,
|
| 825 |
+
"step": 51
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.832,
|
| 829 |
+
"grad_norm": 19.737197875976562,
|
| 830 |
+
"learning_rate": 3.155737704918033e-05,
|
| 831 |
+
"loss": 0.6773,
|
| 832 |
+
"step": 52
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.832,
|
| 836 |
+
"eval_accuracy": 0.584,
|
| 837 |
+
"eval_loss": 0.6686127781867981,
|
| 838 |
+
"eval_runtime": 11.4137,
|
| 839 |
+
"eval_samples_per_second": 21.903,
|
| 840 |
+
"eval_steps_per_second": 2.804,
|
| 841 |
+
"step": 52
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.848,
|
| 845 |
+
"grad_norm": 19.23349952697754,
|
| 846 |
+
"learning_rate": 3.114754098360656e-05,
|
| 847 |
+
"loss": 0.6336,
|
| 848 |
+
"step": 53
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.848,
|
| 852 |
+
"eval_accuracy": 0.608,
|
| 853 |
+
"eval_loss": 0.6502300500869751,
|
| 854 |
+
"eval_runtime": 11.6377,
|
| 855 |
+
"eval_samples_per_second": 21.482,
|
| 856 |
+
"eval_steps_per_second": 2.75,
|
| 857 |
+
"step": 53
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.864,
|
| 861 |
+
"grad_norm": 40.20008087158203,
|
| 862 |
+
"learning_rate": 3.073770491803279e-05,
|
| 863 |
+
"loss": 0.7077,
|
| 864 |
+
"step": 54
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.864,
|
| 868 |
+
"eval_accuracy": 0.62,
|
| 869 |
+
"eval_loss": 0.6335379481315613,
|
| 870 |
+
"eval_runtime": 11.4293,
|
| 871 |
+
"eval_samples_per_second": 21.874,
|
| 872 |
+
"eval_steps_per_second": 2.8,
|
| 873 |
+
"step": 54
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.88,
|
| 877 |
+
"grad_norm": 9.706358909606934,
|
| 878 |
+
"learning_rate": 3.0327868852459017e-05,
|
| 879 |
+
"loss": 0.4935,
|
| 880 |
+
"step": 55
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.88,
|
| 884 |
+
"eval_accuracy": 0.616,
|
| 885 |
+
"eval_loss": 0.640767514705658,
|
| 886 |
+
"eval_runtime": 11.367,
|
| 887 |
+
"eval_samples_per_second": 21.993,
|
| 888 |
+
"eval_steps_per_second": 2.815,
|
| 889 |
+
"step": 55
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.896,
|
| 893 |
+
"grad_norm": 7.35679817199707,
|
| 894 |
+
"learning_rate": 2.9918032786885248e-05,
|
| 895 |
+
"loss": 0.4311,
|
| 896 |
+
"step": 56
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.896,
|
| 900 |
+
"eval_accuracy": 0.604,
|
| 901 |
+
"eval_loss": 0.6300995349884033,
|
| 902 |
+
"eval_runtime": 11.4719,
|
| 903 |
+
"eval_samples_per_second": 21.792,
|
| 904 |
+
"eval_steps_per_second": 2.789,
|
| 905 |
+
"step": 56
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.912,
|
| 909 |
+
"grad_norm": 9.2598876953125,
|
| 910 |
+
"learning_rate": 2.9508196721311478e-05,
|
| 911 |
+
"loss": 0.4558,
|
| 912 |
+
"step": 57
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.912,
|
| 916 |
+
"eval_accuracy": 0.664,
|
| 917 |
+
"eval_loss": 0.630566418170929,
|
| 918 |
+
"eval_runtime": 11.5188,
|
| 919 |
+
"eval_samples_per_second": 21.704,
|
| 920 |
+
"eval_steps_per_second": 2.778,
|
| 921 |
+
"step": 57
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.928,
|
| 925 |
+
"grad_norm": 31.75694465637207,
|
| 926 |
+
"learning_rate": 2.9098360655737705e-05,
|
| 927 |
+
"loss": 0.6486,
|
| 928 |
+
"step": 58
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.928,
|
| 932 |
+
"eval_accuracy": 0.64,
|
| 933 |
+
"eval_loss": 0.614264726638794,
|
| 934 |
+
"eval_runtime": 11.6451,
|
| 935 |
+
"eval_samples_per_second": 21.468,
|
| 936 |
+
"eval_steps_per_second": 2.748,
|
| 937 |
+
"step": 58
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.944,
|
| 941 |
+
"grad_norm": 39.16770553588867,
|
| 942 |
+
"learning_rate": 2.8688524590163935e-05,
|
| 943 |
+
"loss": 0.6755,
|
| 944 |
+
"step": 59
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.944,
|
| 948 |
+
"eval_accuracy": 0.668,
|
| 949 |
+
"eval_loss": 0.5880586504936218,
|
| 950 |
+
"eval_runtime": 11.5144,
|
| 951 |
+
"eval_samples_per_second": 21.712,
|
| 952 |
+
"eval_steps_per_second": 2.779,
|
| 953 |
+
"step": 59
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.96,
|
| 957 |
+
"grad_norm": 17.8769474029541,
|
| 958 |
+
"learning_rate": 2.8278688524590162e-05,
|
| 959 |
+
"loss": 0.6925,
|
| 960 |
+
"step": 60
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.96,
|
| 964 |
+
"eval_accuracy": 0.636,
|
| 965 |
+
"eval_loss": 0.5895799398422241,
|
| 966 |
+
"eval_runtime": 11.4443,
|
| 967 |
+
"eval_samples_per_second": 21.845,
|
| 968 |
+
"eval_steps_per_second": 2.796,
|
| 969 |
+
"step": 60
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.976,
|
| 973 |
+
"grad_norm": 16.898263931274414,
|
| 974 |
+
"learning_rate": 2.7868852459016392e-05,
|
| 975 |
+
"loss": 0.3927,
|
| 976 |
+
"step": 61
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.976,
|
| 980 |
+
"eval_accuracy": 0.672,
|
| 981 |
+
"eval_loss": 0.6116553544998169,
|
| 982 |
+
"eval_runtime": 11.4294,
|
| 983 |
+
"eval_samples_per_second": 21.873,
|
| 984 |
+
"eval_steps_per_second": 2.8,
|
| 985 |
+
"step": 61
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.992,
|
| 989 |
+
"grad_norm": 11.950173377990723,
|
| 990 |
+
"learning_rate": 2.7459016393442626e-05,
|
| 991 |
+
"loss": 0.6678,
|
| 992 |
+
"step": 62
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.992,
|
| 996 |
+
"eval_accuracy": 0.676,
|
| 997 |
+
"eval_loss": 0.629517138004303,
|
| 998 |
+
"eval_runtime": 11.2631,
|
| 999 |
+
"eval_samples_per_second": 22.196,
|
| 1000 |
+
"eval_steps_per_second": 2.841,
|
| 1001 |
+
"step": 62
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.008,
|
| 1005 |
+
"grad_norm": 14.72547435760498,
|
| 1006 |
+
"learning_rate": 2.7049180327868856e-05,
|
| 1007 |
+
"loss": 0.4718,
|
| 1008 |
+
"step": 63
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 1.008,
|
| 1012 |
+
"eval_accuracy": 0.676,
|
| 1013 |
+
"eval_loss": 0.6391622424125671,
|
| 1014 |
+
"eval_runtime": 11.4024,
|
| 1015 |
+
"eval_samples_per_second": 21.925,
|
| 1016 |
+
"eval_steps_per_second": 2.806,
|
| 1017 |
+
"step": 63
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.024,
|
| 1021 |
+
"grad_norm": 21.045801162719727,
|
| 1022 |
+
"learning_rate": 2.6639344262295087e-05,
|
| 1023 |
+
"loss": 0.4525,
|
| 1024 |
+
"step": 64
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.024,
|
| 1028 |
+
"eval_accuracy": 0.676,
|
| 1029 |
+
"eval_loss": 0.6506518721580505,
|
| 1030 |
+
"eval_runtime": 11.4065,
|
| 1031 |
+
"eval_samples_per_second": 21.917,
|
| 1032 |
+
"eval_steps_per_second": 2.805,
|
| 1033 |
+
"step": 64
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.04,
|
| 1037 |
+
"grad_norm": NaN,
|
| 1038 |
+
"learning_rate": 2.6639344262295087e-05,
|
| 1039 |
+
"loss": 0.5411,
|
| 1040 |
+
"step": 65
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.04,
|
| 1044 |
+
"eval_accuracy": 0.676,
|
| 1045 |
+
"eval_loss": 0.6506518721580505,
|
| 1046 |
+
"eval_runtime": 11.483,
|
| 1047 |
+
"eval_samples_per_second": 21.771,
|
| 1048 |
+
"eval_steps_per_second": 2.787,
|
| 1049 |
+
"step": 65
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.056,
|
| 1053 |
+
"grad_norm": 35.55463409423828,
|
| 1054 |
+
"learning_rate": 2.6229508196721314e-05,
|
| 1055 |
+
"loss": 0.5345,
|
| 1056 |
+
"step": 66
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 1.056,
|
| 1060 |
+
"eval_accuracy": 0.68,
|
| 1061 |
+
"eval_loss": 0.64942467212677,
|
| 1062 |
+
"eval_runtime": 11.2992,
|
| 1063 |
+
"eval_samples_per_second": 22.125,
|
| 1064 |
+
"eval_steps_per_second": 2.832,
|
| 1065 |
+
"step": 66
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.072,
|
| 1069 |
+
"grad_norm": 36.09001922607422,
|
| 1070 |
+
"learning_rate": 2.5819672131147544e-05,
|
| 1071 |
+
"loss": 0.5968,
|
| 1072 |
+
"step": 67
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.072,
|
| 1076 |
+
"eval_accuracy": 0.696,
|
| 1077 |
+
"eval_loss": 0.6280552744865417,
|
| 1078 |
+
"eval_runtime": 11.47,
|
| 1079 |
+
"eval_samples_per_second": 21.796,
|
| 1080 |
+
"eval_steps_per_second": 2.79,
|
| 1081 |
+
"step": 67
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.088,
|
| 1085 |
+
"grad_norm": 42.95037078857422,
|
| 1086 |
+
"learning_rate": 2.540983606557377e-05,
|
| 1087 |
+
"loss": 0.7288,
|
| 1088 |
+
"step": 68
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.088,
|
| 1092 |
+
"eval_accuracy": 0.684,
|
| 1093 |
+
"eval_loss": 0.6100922226905823,
|
| 1094 |
+
"eval_runtime": 11.395,
|
| 1095 |
+
"eval_samples_per_second": 21.939,
|
| 1096 |
+
"eval_steps_per_second": 2.808,
|
| 1097 |
+
"step": 68
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 1.104,
|
| 1101 |
+
"grad_norm": 18.122161865234375,
|
| 1102 |
+
"learning_rate": 2.5e-05,
|
| 1103 |
+
"loss": 0.3666,
|
| 1104 |
+
"step": 69
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 1.104,
|
| 1108 |
+
"eval_accuracy": 0.708,
|
| 1109 |
+
"eval_loss": 0.5811479687690735,
|
| 1110 |
+
"eval_runtime": 11.467,
|
| 1111 |
+
"eval_samples_per_second": 21.802,
|
| 1112 |
+
"eval_steps_per_second": 2.791,
|
| 1113 |
+
"step": 69
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 1.12,
|
| 1117 |
+
"grad_norm": 17.941131591796875,
|
| 1118 |
+
"learning_rate": 2.459016393442623e-05,
|
| 1119 |
+
"loss": 0.5333,
|
| 1120 |
+
"step": 70
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 1.12,
|
| 1124 |
+
"eval_accuracy": 0.684,
|
| 1125 |
+
"eval_loss": 0.5954810976982117,
|
| 1126 |
+
"eval_runtime": 11.4815,
|
| 1127 |
+
"eval_samples_per_second": 21.774,
|
| 1128 |
+
"eval_steps_per_second": 2.787,
|
| 1129 |
+
"step": 70
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.1360000000000001,
|
| 1133 |
+
"grad_norm": 10.752734184265137,
|
| 1134 |
+
"learning_rate": 2.418032786885246e-05,
|
| 1135 |
+
"loss": 0.4274,
|
| 1136 |
+
"step": 71
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.1360000000000001,
|
| 1140 |
+
"eval_accuracy": 0.672,
|
| 1141 |
+
"eval_loss": 0.5998041033744812,
|
| 1142 |
+
"eval_runtime": 11.5172,
|
| 1143 |
+
"eval_samples_per_second": 21.707,
|
| 1144 |
+
"eval_steps_per_second": 2.778,
|
| 1145 |
+
"step": 71
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.152,
|
| 1149 |
+
"grad_norm": 21.44332504272461,
|
| 1150 |
+
"learning_rate": 2.377049180327869e-05,
|
| 1151 |
+
"loss": 0.4109,
|
| 1152 |
+
"step": 72
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 1.152,
|
| 1156 |
+
"eval_accuracy": 0.668,
|
| 1157 |
+
"eval_loss": 0.6016911864280701,
|
| 1158 |
+
"eval_runtime": 11.4217,
|
| 1159 |
+
"eval_samples_per_second": 21.888,
|
| 1160 |
+
"eval_steps_per_second": 2.802,
|
| 1161 |
+
"step": 72
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.168,
|
| 1165 |
+
"grad_norm": 40.88154220581055,
|
| 1166 |
+
"learning_rate": 2.336065573770492e-05,
|
| 1167 |
+
"loss": 0.576,
|
| 1168 |
+
"step": 73
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.168,
|
| 1172 |
+
"eval_accuracy": 0.672,
|
| 1173 |
+
"eval_loss": 0.6131250262260437,
|
| 1174 |
+
"eval_runtime": 11.4732,
|
| 1175 |
+
"eval_samples_per_second": 21.79,
|
| 1176 |
+
"eval_steps_per_second": 2.789,
|
| 1177 |
+
"step": 73
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.184,
|
| 1181 |
+
"grad_norm": 21.387557983398438,
|
| 1182 |
+
"learning_rate": 2.295081967213115e-05,
|
| 1183 |
+
"loss": 0.598,
|
| 1184 |
+
"step": 74
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.184,
|
| 1188 |
+
"eval_accuracy": 0.688,
|
| 1189 |
+
"eval_loss": 0.5768781900405884,
|
| 1190 |
+
"eval_runtime": 11.3223,
|
| 1191 |
+
"eval_samples_per_second": 22.08,
|
| 1192 |
+
"eval_steps_per_second": 2.826,
|
| 1193 |
+
"step": 74
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.2,
|
| 1197 |
+
"grad_norm": 22.257291793823242,
|
| 1198 |
+
"learning_rate": 2.254098360655738e-05,
|
| 1199 |
+
"loss": 0.4916,
|
| 1200 |
+
"step": 75
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.2,
|
| 1204 |
+
"eval_accuracy": 0.704,
|
| 1205 |
+
"eval_loss": 0.5493154525756836,
|
| 1206 |
+
"eval_runtime": 11.4048,
|
| 1207 |
+
"eval_samples_per_second": 21.921,
|
| 1208 |
+
"eval_steps_per_second": 2.806,
|
| 1209 |
+
"step": 75
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 1.216,
|
| 1213 |
+
"grad_norm": 8.411641120910645,
|
| 1214 |
+
"learning_rate": 2.2131147540983607e-05,
|
| 1215 |
+
"loss": 0.3723,
|
| 1216 |
+
"step": 76
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 1.216,
|
| 1220 |
+
"eval_accuracy": 0.716,
|
| 1221 |
+
"eval_loss": 0.5425886511802673,
|
| 1222 |
+
"eval_runtime": 11.4678,
|
| 1223 |
+
"eval_samples_per_second": 21.8,
|
| 1224 |
+
"eval_steps_per_second": 2.79,
|
| 1225 |
+
"step": 76
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.232,
|
| 1229 |
+
"grad_norm": 10.33214282989502,
|
| 1230 |
+
"learning_rate": 2.1721311475409837e-05,
|
| 1231 |
+
"loss": 0.5423,
|
| 1232 |
+
"step": 77
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.232,
|
| 1236 |
+
"eval_accuracy": 0.704,
|
| 1237 |
+
"eval_loss": 0.5367762446403503,
|
| 1238 |
+
"eval_runtime": 11.5849,
|
| 1239 |
+
"eval_samples_per_second": 21.58,
|
| 1240 |
+
"eval_steps_per_second": 2.762,
|
| 1241 |
+
"step": 77
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.248,
|
| 1245 |
+
"grad_norm": 8.413525581359863,
|
| 1246 |
+
"learning_rate": 2.1311475409836064e-05,
|
| 1247 |
+
"loss": 0.5154,
|
| 1248 |
+
"step": 78
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.248,
|
| 1252 |
+
"eval_accuracy": 0.728,
|
| 1253 |
+
"eval_loss": 0.5338938236236572,
|
| 1254 |
+
"eval_runtime": 11.3935,
|
| 1255 |
+
"eval_samples_per_second": 21.942,
|
| 1256 |
+
"eval_steps_per_second": 2.809,
|
| 1257 |
+
"step": 78
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.264,
|
| 1261 |
+
"grad_norm": 29.967487335205078,
|
| 1262 |
+
"learning_rate": 2.0901639344262298e-05,
|
| 1263 |
+
"loss": 0.5072,
|
| 1264 |
+
"step": 79
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 1.264,
|
| 1268 |
+
"eval_accuracy": 0.716,
|
| 1269 |
+
"eval_loss": 0.5389543175697327,
|
| 1270 |
+
"eval_runtime": 11.5734,
|
| 1271 |
+
"eval_samples_per_second": 21.601,
|
| 1272 |
+
"eval_steps_per_second": 2.765,
|
| 1273 |
+
"step": 79
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.28,
|
| 1277 |
+
"grad_norm": 15.605040550231934,
|
| 1278 |
+
"learning_rate": 2.0491803278688525e-05,
|
| 1279 |
+
"loss": 0.38,
|
| 1280 |
+
"step": 80
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.28,
|
| 1284 |
+
"eval_accuracy": 0.728,
|
| 1285 |
+
"eval_loss": 0.5024056434631348,
|
| 1286 |
+
"eval_runtime": 11.3479,
|
| 1287 |
+
"eval_samples_per_second": 22.031,
|
| 1288 |
+
"eval_steps_per_second": 2.82,
|
| 1289 |
+
"step": 80
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 1.296,
|
| 1293 |
+
"grad_norm": 35.906517028808594,
|
| 1294 |
+
"learning_rate": 2.0081967213114755e-05,
|
| 1295 |
+
"loss": 0.6005,
|
| 1296 |
+
"step": 81
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 1.296,
|
| 1300 |
+
"eval_accuracy": 0.744,
|
| 1301 |
+
"eval_loss": 0.49823418259620667,
|
| 1302 |
+
"eval_runtime": 11.4956,
|
| 1303 |
+
"eval_samples_per_second": 21.747,
|
| 1304 |
+
"eval_steps_per_second": 2.784,
|
| 1305 |
+
"step": 81
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.312,
|
| 1309 |
+
"grad_norm": 7.512831211090088,
|
| 1310 |
+
"learning_rate": 1.9672131147540985e-05,
|
| 1311 |
+
"loss": 0.5016,
|
| 1312 |
+
"step": 82
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.312,
|
| 1316 |
+
"eval_accuracy": 0.728,
|
| 1317 |
+
"eval_loss": 0.4885072708129883,
|
| 1318 |
+
"eval_runtime": 11.4788,
|
| 1319 |
+
"eval_samples_per_second": 21.779,
|
| 1320 |
+
"eval_steps_per_second": 2.788,
|
| 1321 |
+
"step": 82
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 1.328,
|
| 1325 |
+
"grad_norm": 16.890913009643555,
|
| 1326 |
+
"learning_rate": 1.9262295081967212e-05,
|
| 1327 |
+
"loss": 0.4624,
|
| 1328 |
+
"step": 83
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 1.328,
|
| 1332 |
+
"eval_accuracy": 0.736,
|
| 1333 |
+
"eval_loss": 0.5011359453201294,
|
| 1334 |
+
"eval_runtime": 11.451,
|
| 1335 |
+
"eval_samples_per_second": 21.832,
|
| 1336 |
+
"eval_steps_per_second": 2.795,
|
| 1337 |
+
"step": 83
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.3439999999999999,
|
| 1341 |
+
"grad_norm": 8.635043144226074,
|
| 1342 |
+
"learning_rate": 1.8852459016393442e-05,
|
| 1343 |
+
"loss": 0.3138,
|
| 1344 |
+
"step": 84
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 1.3439999999999999,
|
| 1348 |
+
"eval_accuracy": 0.748,
|
| 1349 |
+
"eval_loss": 0.5005082488059998,
|
| 1350 |
+
"eval_runtime": 11.5278,
|
| 1351 |
+
"eval_samples_per_second": 21.687,
|
| 1352 |
+
"eval_steps_per_second": 2.776,
|
| 1353 |
+
"step": 84
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.3599999999999999,
|
| 1357 |
+
"grad_norm": 28.464235305786133,
|
| 1358 |
+
"learning_rate": 1.8442622950819673e-05,
|
| 1359 |
+
"loss": 0.3379,
|
| 1360 |
+
"step": 85
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.3599999999999999,
|
| 1364 |
+
"eval_accuracy": 0.784,
|
| 1365 |
+
"eval_loss": 0.49115338921546936,
|
| 1366 |
+
"eval_runtime": 11.4489,
|
| 1367 |
+
"eval_samples_per_second": 21.836,
|
| 1368 |
+
"eval_steps_per_second": 2.795,
|
| 1369 |
+
"step": 85
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 1.376,
|
| 1373 |
+
"grad_norm": 6.288327217102051,
|
| 1374 |
+
"learning_rate": 1.8032786885245903e-05,
|
| 1375 |
+
"loss": 0.2329,
|
| 1376 |
+
"step": 86
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 1.376,
|
| 1380 |
+
"eval_accuracy": 0.76,
|
| 1381 |
+
"eval_loss": 0.486227810382843,
|
| 1382 |
+
"eval_runtime": 11.4903,
|
| 1383 |
+
"eval_samples_per_second": 21.757,
|
| 1384 |
+
"eval_steps_per_second": 2.785,
|
| 1385 |
+
"step": 86
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.392,
|
| 1389 |
+
"grad_norm": 9.165458679199219,
|
| 1390 |
+
"learning_rate": 1.7622950819672133e-05,
|
| 1391 |
+
"loss": 0.4698,
|
| 1392 |
+
"step": 87
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.392,
|
| 1396 |
+
"eval_accuracy": 0.764,
|
| 1397 |
+
"eval_loss": 0.49401524662971497,
|
| 1398 |
+
"eval_runtime": 11.6,
|
| 1399 |
+
"eval_samples_per_second": 21.552,
|
| 1400 |
+
"eval_steps_per_second": 2.759,
|
| 1401 |
+
"step": 87
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 1.408,
|
| 1405 |
+
"grad_norm": 30.95488166809082,
|
| 1406 |
+
"learning_rate": 1.721311475409836e-05,
|
| 1407 |
+
"loss": 0.386,
|
| 1408 |
+
"step": 88
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 1.408,
|
| 1412 |
+
"eval_accuracy": 0.788,
|
| 1413 |
+
"eval_loss": 0.4993850588798523,
|
| 1414 |
+
"eval_runtime": 11.4082,
|
| 1415 |
+
"eval_samples_per_second": 21.914,
|
| 1416 |
+
"eval_steps_per_second": 2.805,
|
| 1417 |
+
"step": 88
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.424,
|
| 1421 |
+
"grad_norm": 37.84017562866211,
|
| 1422 |
+
"learning_rate": 1.680327868852459e-05,
|
| 1423 |
+
"loss": 0.7592,
|
| 1424 |
+
"step": 89
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.424,
|
| 1428 |
+
"eval_accuracy": 0.768,
|
| 1429 |
+
"eval_loss": 0.4701511263847351,
|
| 1430 |
+
"eval_runtime": 11.4269,
|
| 1431 |
+
"eval_samples_per_second": 21.878,
|
| 1432 |
+
"eval_steps_per_second": 2.8,
|
| 1433 |
+
"step": 89
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 1.44,
|
| 1437 |
+
"grad_norm": 41.4830436706543,
|
| 1438 |
+
"learning_rate": 1.6393442622950818e-05,
|
| 1439 |
+
"loss": 0.5635,
|
| 1440 |
+
"step": 90
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 1.44,
|
| 1444 |
+
"eval_accuracy": 0.776,
|
| 1445 |
+
"eval_loss": 0.4597744047641754,
|
| 1446 |
+
"eval_runtime": 11.3414,
|
| 1447 |
+
"eval_samples_per_second": 22.043,
|
| 1448 |
+
"eval_steps_per_second": 2.822,
|
| 1449 |
+
"step": 90
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.456,
|
| 1453 |
+
"grad_norm": 8.639835357666016,
|
| 1454 |
+
"learning_rate": 1.598360655737705e-05,
|
| 1455 |
+
"loss": 0.4412,
|
| 1456 |
+
"step": 91
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.456,
|
| 1460 |
+
"eval_accuracy": 0.76,
|
| 1461 |
+
"eval_loss": 0.44887205958366394,
|
| 1462 |
+
"eval_runtime": 11.3759,
|
| 1463 |
+
"eval_samples_per_second": 21.976,
|
| 1464 |
+
"eval_steps_per_second": 2.813,
|
| 1465 |
+
"step": 91
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.472,
|
| 1469 |
+
"grad_norm": 13.933167457580566,
|
| 1470 |
+
"learning_rate": 1.557377049180328e-05,
|
| 1471 |
+
"loss": 0.4016,
|
| 1472 |
+
"step": 92
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.472,
|
| 1476 |
+
"eval_accuracy": 0.764,
|
| 1477 |
+
"eval_loss": 0.4409584403038025,
|
| 1478 |
+
"eval_runtime": 11.4154,
|
| 1479 |
+
"eval_samples_per_second": 21.9,
|
| 1480 |
+
"eval_steps_per_second": 2.803,
|
| 1481 |
+
"step": 92
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.488,
|
| 1485 |
+
"grad_norm": 25.79916000366211,
|
| 1486 |
+
"learning_rate": 1.5163934426229509e-05,
|
| 1487 |
+
"loss": 0.3462,
|
| 1488 |
+
"step": 93
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 1.488,
|
| 1492 |
+
"eval_accuracy": 0.76,
|
| 1493 |
+
"eval_loss": 0.4534677267074585,
|
| 1494 |
+
"eval_runtime": 11.4913,
|
| 1495 |
+
"eval_samples_per_second": 21.756,
|
| 1496 |
+
"eval_steps_per_second": 2.785,
|
| 1497 |
+
"step": 93
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.504,
|
| 1501 |
+
"grad_norm": 8.152263641357422,
|
| 1502 |
+
"learning_rate": 1.4754098360655739e-05,
|
| 1503 |
+
"loss": 0.2376,
|
| 1504 |
+
"step": 94
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 1.504,
|
| 1508 |
+
"eval_accuracy": 0.78,
|
| 1509 |
+
"eval_loss": 0.4606277644634247,
|
| 1510 |
+
"eval_runtime": 11.3366,
|
| 1511 |
+
"eval_samples_per_second": 22.053,
|
| 1512 |
+
"eval_steps_per_second": 2.823,
|
| 1513 |
+
"step": 94
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 1.52,
|
| 1517 |
+
"grad_norm": 50.013893127441406,
|
| 1518 |
+
"learning_rate": 1.4344262295081968e-05,
|
| 1519 |
+
"loss": 0.8243,
|
| 1520 |
+
"step": 95
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 1.52,
|
| 1524 |
+
"eval_accuracy": 0.76,
|
| 1525 |
+
"eval_loss": 0.4745258092880249,
|
| 1526 |
+
"eval_runtime": 11.4641,
|
| 1527 |
+
"eval_samples_per_second": 21.807,
|
| 1528 |
+
"eval_steps_per_second": 2.791,
|
| 1529 |
+
"step": 95
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.536,
|
| 1533 |
+
"grad_norm": 7.844508647918701,
|
| 1534 |
+
"learning_rate": 1.3934426229508196e-05,
|
| 1535 |
+
"loss": 0.2607,
|
| 1536 |
+
"step": 96
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.536,
|
| 1540 |
+
"eval_accuracy": 0.768,
|
| 1541 |
+
"eval_loss": 0.46744146943092346,
|
| 1542 |
+
"eval_runtime": 11.4558,
|
| 1543 |
+
"eval_samples_per_second": 21.823,
|
| 1544 |
+
"eval_steps_per_second": 2.793,
|
| 1545 |
+
"step": 96
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 1.552,
|
| 1549 |
+
"grad_norm": 36.814781188964844,
|
| 1550 |
+
"learning_rate": 1.3524590163934428e-05,
|
| 1551 |
+
"loss": 0.6977,
|
| 1552 |
+
"step": 97
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 1.552,
|
| 1556 |
+
"eval_accuracy": 0.768,
|
| 1557 |
+
"eval_loss": 0.46450626850128174,
|
| 1558 |
+
"eval_runtime": 11.6232,
|
| 1559 |
+
"eval_samples_per_second": 21.509,
|
| 1560 |
+
"eval_steps_per_second": 2.753,
|
| 1561 |
+
"step": 97
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 1.568,
|
| 1565 |
+
"grad_norm": 12.111028671264648,
|
| 1566 |
+
"learning_rate": 1.3114754098360657e-05,
|
| 1567 |
+
"loss": 0.9507,
|
| 1568 |
+
"step": 98
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 1.568,
|
| 1572 |
+
"eval_accuracy": 0.78,
|
| 1573 |
+
"eval_loss": 0.45364972949028015,
|
| 1574 |
+
"eval_runtime": 11.495,
|
| 1575 |
+
"eval_samples_per_second": 21.749,
|
| 1576 |
+
"eval_steps_per_second": 2.784,
|
| 1577 |
+
"step": 98
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.584,
|
| 1581 |
+
"grad_norm": 8.090563774108887,
|
| 1582 |
+
"learning_rate": 1.2704918032786885e-05,
|
| 1583 |
+
"loss": 0.376,
|
| 1584 |
+
"step": 99
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.584,
|
| 1588 |
+
"eval_accuracy": 0.78,
|
| 1589 |
+
"eval_loss": 0.45443812012672424,
|
| 1590 |
+
"eval_runtime": 11.4699,
|
| 1591 |
+
"eval_samples_per_second": 21.796,
|
| 1592 |
+
"eval_steps_per_second": 2.79,
|
| 1593 |
+
"step": 99
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.6,
|
| 1597 |
+
"grad_norm": 27.078815460205078,
|
| 1598 |
+
"learning_rate": 1.2295081967213116e-05,
|
| 1599 |
+
"loss": 0.4708,
|
| 1600 |
+
"step": 100
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.6,
|
| 1604 |
+
"eval_accuracy": 0.792,
|
| 1605 |
+
"eval_loss": 0.43265777826309204,
|
| 1606 |
+
"eval_runtime": 11.434,
|
| 1607 |
+
"eval_samples_per_second": 21.865,
|
| 1608 |
+
"eval_steps_per_second": 2.799,
|
| 1609 |
+
"step": 100
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 1.616,
|
| 1613 |
+
"grad_norm": 31.743221282958984,
|
| 1614 |
+
"learning_rate": 1.1885245901639344e-05,
|
| 1615 |
+
"loss": 0.4244,
|
| 1616 |
+
"step": 101
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 1.616,
|
| 1620 |
+
"eval_accuracy": 0.8,
|
| 1621 |
+
"eval_loss": 0.4210461378097534,
|
| 1622 |
+
"eval_runtime": 11.605,
|
| 1623 |
+
"eval_samples_per_second": 21.543,
|
| 1624 |
+
"eval_steps_per_second": 2.757,
|
| 1625 |
+
"step": 101
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.6320000000000001,
|
| 1629 |
+
"grad_norm": 5.887348175048828,
|
| 1630 |
+
"learning_rate": 1.1475409836065575e-05,
|
| 1631 |
+
"loss": 0.2502,
|
| 1632 |
+
"step": 102
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 1.6320000000000001,
|
| 1636 |
+
"eval_accuracy": 0.816,
|
| 1637 |
+
"eval_loss": 0.40375572443008423,
|
| 1638 |
+
"eval_runtime": 11.4278,
|
| 1639 |
+
"eval_samples_per_second": 21.876,
|
| 1640 |
+
"eval_steps_per_second": 2.8,
|
| 1641 |
+
"step": 102
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.6480000000000001,
|
| 1645 |
+
"grad_norm": 13.274320602416992,
|
| 1646 |
+
"learning_rate": 1.1065573770491803e-05,
|
| 1647 |
+
"loss": 0.8468,
|
| 1648 |
+
"step": 103
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.6480000000000001,
|
| 1652 |
+
"eval_accuracy": 0.816,
|
| 1653 |
+
"eval_loss": 0.39257147908210754,
|
| 1654 |
+
"eval_runtime": 11.4088,
|
| 1655 |
+
"eval_samples_per_second": 21.913,
|
| 1656 |
+
"eval_steps_per_second": 2.805,
|
| 1657 |
+
"step": 103
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 1.6640000000000001,
|
| 1661 |
+
"grad_norm": 22.40627098083496,
|
| 1662 |
+
"learning_rate": 1.0655737704918032e-05,
|
| 1663 |
+
"loss": 0.5753,
|
| 1664 |
+
"step": 104
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.6640000000000001,
|
| 1668 |
+
"eval_accuracy": 0.816,
|
| 1669 |
+
"eval_loss": 0.39645299315452576,
|
| 1670 |
+
"eval_runtime": 11.469,
|
| 1671 |
+
"eval_samples_per_second": 21.798,
|
| 1672 |
+
"eval_steps_per_second": 2.79,
|
| 1673 |
+
"step": 104
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 1.6800000000000002,
|
| 1677 |
+
"grad_norm": 7.59094762802124,
|
| 1678 |
+
"learning_rate": 1.0245901639344262e-05,
|
| 1679 |
+
"loss": 0.2518,
|
| 1680 |
+
"step": 105
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 1.6800000000000002,
|
| 1684 |
+
"eval_accuracy": 0.812,
|
| 1685 |
+
"eval_loss": 0.3954884707927704,
|
| 1686 |
+
"eval_runtime": 11.452,
|
| 1687 |
+
"eval_samples_per_second": 21.83,
|
| 1688 |
+
"eval_steps_per_second": 2.794,
|
| 1689 |
+
"step": 105
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.696,
|
| 1693 |
+
"grad_norm": 10.119157791137695,
|
| 1694 |
+
"learning_rate": 9.836065573770493e-06,
|
| 1695 |
+
"loss": 0.4945,
|
| 1696 |
+
"step": 106
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.696,
|
| 1700 |
+
"eval_accuracy": 0.796,
|
| 1701 |
+
"eval_loss": 0.39326009154319763,
|
| 1702 |
+
"eval_runtime": 11.4475,
|
| 1703 |
+
"eval_samples_per_second": 21.839,
|
| 1704 |
+
"eval_steps_per_second": 2.795,
|
| 1705 |
+
"step": 106
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 1.712,
|
| 1709 |
+
"grad_norm": 12.016386032104492,
|
| 1710 |
+
"learning_rate": 9.426229508196721e-06,
|
| 1711 |
+
"loss": 0.2257,
|
| 1712 |
+
"step": 107
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 1.712,
|
| 1716 |
+
"eval_accuracy": 0.82,
|
| 1717 |
+
"eval_loss": 0.38625067472457886,
|
| 1718 |
+
"eval_runtime": 11.4441,
|
| 1719 |
+
"eval_samples_per_second": 21.845,
|
| 1720 |
+
"eval_steps_per_second": 2.796,
|
| 1721 |
+
"step": 107
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 1.728,
|
| 1725 |
+
"grad_norm": 37.06383514404297,
|
| 1726 |
+
"learning_rate": 9.016393442622952e-06,
|
| 1727 |
+
"loss": 0.8669,
|
| 1728 |
+
"step": 108
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 1.728,
|
| 1732 |
+
"eval_accuracy": 0.804,
|
| 1733 |
+
"eval_loss": 0.388757586479187,
|
| 1734 |
+
"eval_runtime": 11.59,
|
| 1735 |
+
"eval_samples_per_second": 21.57,
|
| 1736 |
+
"eval_steps_per_second": 2.761,
|
| 1737 |
+
"step": 108
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.744,
|
| 1741 |
+
"grad_norm": 19.463485717773438,
|
| 1742 |
+
"learning_rate": 8.60655737704918e-06,
|
| 1743 |
+
"loss": 0.4496,
|
| 1744 |
+
"step": 109
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 1.744,
|
| 1748 |
+
"eval_accuracy": 0.82,
|
| 1749 |
+
"eval_loss": 0.3835999667644501,
|
| 1750 |
+
"eval_runtime": 11.3837,
|
| 1751 |
+
"eval_samples_per_second": 21.961,
|
| 1752 |
+
"eval_steps_per_second": 2.811,
|
| 1753 |
+
"step": 109
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.76,
|
| 1757 |
+
"grad_norm": 9.631560325622559,
|
| 1758 |
+
"learning_rate": 8.196721311475409e-06,
|
| 1759 |
+
"loss": 0.3514,
|
| 1760 |
+
"step": 110
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.76,
|
| 1764 |
+
"eval_accuracy": 0.804,
|
| 1765 |
+
"eval_loss": 0.3807854652404785,
|
| 1766 |
+
"eval_runtime": 11.3909,
|
| 1767 |
+
"eval_samples_per_second": 21.947,
|
| 1768 |
+
"eval_steps_per_second": 2.809,
|
| 1769 |
+
"step": 110
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 1.776,
|
| 1773 |
+
"grad_norm": 15.87090015411377,
|
| 1774 |
+
"learning_rate": 7.78688524590164e-06,
|
| 1775 |
+
"loss": 0.2494,
|
| 1776 |
+
"step": 111
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 1.776,
|
| 1780 |
+
"eval_accuracy": 0.784,
|
| 1781 |
+
"eval_loss": 0.39890381693840027,
|
| 1782 |
+
"eval_runtime": 11.3662,
|
| 1783 |
+
"eval_samples_per_second": 21.995,
|
| 1784 |
+
"eval_steps_per_second": 2.815,
|
| 1785 |
+
"step": 111
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 1.792,
|
| 1789 |
+
"grad_norm": 13.411320686340332,
|
| 1790 |
+
"learning_rate": 7.3770491803278695e-06,
|
| 1791 |
+
"loss": 0.5852,
|
| 1792 |
+
"step": 112
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 1.792,
|
| 1796 |
+
"eval_accuracy": 0.812,
|
| 1797 |
+
"eval_loss": 0.37704914808273315,
|
| 1798 |
+
"eval_runtime": 11.496,
|
| 1799 |
+
"eval_samples_per_second": 21.747,
|
| 1800 |
+
"eval_steps_per_second": 2.784,
|
| 1801 |
+
"step": 112
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.808,
|
| 1805 |
+
"grad_norm": 10.2308931350708,
|
| 1806 |
+
"learning_rate": 6.967213114754098e-06,
|
| 1807 |
+
"loss": 0.2353,
|
| 1808 |
+
"step": 113
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.808,
|
| 1812 |
+
"eval_accuracy": 0.804,
|
| 1813 |
+
"eval_loss": 0.3881246745586395,
|
| 1814 |
+
"eval_runtime": 11.6252,
|
| 1815 |
+
"eval_samples_per_second": 21.505,
|
| 1816 |
+
"eval_steps_per_second": 2.753,
|
| 1817 |
+
"step": 113
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 1.8239999999999998,
|
| 1821 |
+
"grad_norm": 35.862152099609375,
|
| 1822 |
+
"learning_rate": 6.557377049180328e-06,
|
| 1823 |
+
"loss": 0.347,
|
| 1824 |
+
"step": 114
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 1.8239999999999998,
|
| 1828 |
+
"eval_accuracy": 0.82,
|
| 1829 |
+
"eval_loss": 0.38348227739334106,
|
| 1830 |
+
"eval_runtime": 11.3665,
|
| 1831 |
+
"eval_samples_per_second": 21.995,
|
| 1832 |
+
"eval_steps_per_second": 2.815,
|
| 1833 |
+
"step": 114
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 1.8399999999999999,
|
| 1837 |
+
"grad_norm": 16.910600662231445,
|
| 1838 |
+
"learning_rate": 6.147540983606558e-06,
|
| 1839 |
+
"loss": 0.5338,
|
| 1840 |
+
"step": 115
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 1.8399999999999999,
|
| 1844 |
+
"eval_accuracy": 0.788,
|
| 1845 |
+
"eval_loss": 0.39259979128837585,
|
| 1846 |
+
"eval_runtime": 11.3572,
|
| 1847 |
+
"eval_samples_per_second": 22.013,
|
| 1848 |
+
"eval_steps_per_second": 2.818,
|
| 1849 |
+
"step": 115
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.8559999999999999,
|
| 1853 |
+
"grad_norm": 14.902595520019531,
|
| 1854 |
+
"learning_rate": 5.737704918032787e-06,
|
| 1855 |
+
"loss": 0.3718,
|
| 1856 |
+
"step": 116
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 1.8559999999999999,
|
| 1860 |
+
"eval_accuracy": 0.812,
|
| 1861 |
+
"eval_loss": 0.37997427582740784,
|
| 1862 |
+
"eval_runtime": 11.3538,
|
| 1863 |
+
"eval_samples_per_second": 22.019,
|
| 1864 |
+
"eval_steps_per_second": 2.818,
|
| 1865 |
+
"step": 116
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.8719999999999999,
|
| 1869 |
+
"grad_norm": 13.893790245056152,
|
| 1870 |
+
"learning_rate": 5.327868852459016e-06,
|
| 1871 |
+
"loss": 0.1954,
|
| 1872 |
+
"step": 117
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.8719999999999999,
|
| 1876 |
+
"eval_accuracy": 0.82,
|
| 1877 |
+
"eval_loss": 0.3953521251678467,
|
| 1878 |
+
"eval_runtime": 11.6285,
|
| 1879 |
+
"eval_samples_per_second": 21.499,
|
| 1880 |
+
"eval_steps_per_second": 2.752,
|
| 1881 |
+
"step": 117
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 1.888,
|
| 1885 |
+
"grad_norm": 20.8792667388916,
|
| 1886 |
+
"learning_rate": 4.918032786885246e-06,
|
| 1887 |
+
"loss": 0.3679,
|
| 1888 |
+
"step": 118
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 1.888,
|
| 1892 |
+
"eval_accuracy": 0.788,
|
| 1893 |
+
"eval_loss": 0.4041662812232971,
|
| 1894 |
+
"eval_runtime": 11.7007,
|
| 1895 |
+
"eval_samples_per_second": 21.366,
|
| 1896 |
+
"eval_steps_per_second": 2.735,
|
| 1897 |
+
"step": 118
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 1.904,
|
| 1901 |
+
"grad_norm": 10.44711685180664,
|
| 1902 |
+
"learning_rate": 4.508196721311476e-06,
|
| 1903 |
+
"loss": 0.2971,
|
| 1904 |
+
"step": 119
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 1.904,
|
| 1908 |
+
"eval_accuracy": 0.796,
|
| 1909 |
+
"eval_loss": 0.39307668805122375,
|
| 1910 |
+
"eval_runtime": 11.5223,
|
| 1911 |
+
"eval_samples_per_second": 21.697,
|
| 1912 |
+
"eval_steps_per_second": 2.777,
|
| 1913 |
+
"step": 119
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.92,
|
| 1917 |
+
"grad_norm": 17.487539291381836,
|
| 1918 |
+
"learning_rate": 4.098360655737704e-06,
|
| 1919 |
+
"loss": 0.2742,
|
| 1920 |
+
"step": 120
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.92,
|
| 1924 |
+
"eval_accuracy": 0.804,
|
| 1925 |
+
"eval_loss": 0.38854384422302246,
|
| 1926 |
+
"eval_runtime": 11.3276,
|
| 1927 |
+
"eval_samples_per_second": 22.07,
|
| 1928 |
+
"eval_steps_per_second": 2.825,
|
| 1929 |
+
"step": 120
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 1.936,
|
| 1933 |
+
"grad_norm": 33.492523193359375,
|
| 1934 |
+
"learning_rate": 3.6885245901639347e-06,
|
| 1935 |
+
"loss": 0.5166,
|
| 1936 |
+
"step": 121
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 1.936,
|
| 1940 |
+
"eval_accuracy": 0.776,
|
| 1941 |
+
"eval_loss": 0.39685389399528503,
|
| 1942 |
+
"eval_runtime": 11.3571,
|
| 1943 |
+
"eval_samples_per_second": 22.013,
|
| 1944 |
+
"eval_steps_per_second": 2.818,
|
| 1945 |
+
"step": 121
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 1.952,
|
| 1949 |
+
"grad_norm": 16.691682815551758,
|
| 1950 |
+
"learning_rate": 3.278688524590164e-06,
|
| 1951 |
+
"loss": 0.2628,
|
| 1952 |
+
"step": 122
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 1.952,
|
| 1956 |
+
"eval_accuracy": 0.796,
|
| 1957 |
+
"eval_loss": 0.39687633514404297,
|
| 1958 |
+
"eval_runtime": 11.3028,
|
| 1959 |
+
"eval_samples_per_second": 22.118,
|
| 1960 |
+
"eval_steps_per_second": 2.831,
|
| 1961 |
+
"step": 122
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 1.968,
|
| 1965 |
+
"grad_norm": 6.603124618530273,
|
| 1966 |
+
"learning_rate": 2.8688524590163937e-06,
|
| 1967 |
+
"loss": 0.2998,
|
| 1968 |
+
"step": 123
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 1.968,
|
| 1972 |
+
"eval_accuracy": 0.824,
|
| 1973 |
+
"eval_loss": 0.3869865834712982,
|
| 1974 |
+
"eval_runtime": 11.2907,
|
| 1975 |
+
"eval_samples_per_second": 22.142,
|
| 1976 |
+
"eval_steps_per_second": 2.834,
|
| 1977 |
+
"step": 123
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.984,
|
| 1981 |
+
"grad_norm": 20.69419288635254,
|
| 1982 |
+
"learning_rate": 2.459016393442623e-06,
|
| 1983 |
+
"loss": 0.3104,
|
| 1984 |
+
"step": 124
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.984,
|
| 1988 |
+
"eval_accuracy": 0.824,
|
| 1989 |
+
"eval_loss": 0.38347548246383667,
|
| 1990 |
+
"eval_runtime": 11.3038,
|
| 1991 |
+
"eval_samples_per_second": 22.117,
|
| 1992 |
+
"eval_steps_per_second": 2.831,
|
| 1993 |
+
"step": 124
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 1.984,
|
| 1997 |
+
"step": 124,
|
| 1998 |
+
"total_flos": 1.6196776411267072e+16,
|
| 1999 |
+
"train_loss": 0.6168801505719462,
|
| 2000 |
+
"train_runtime": 1813.1247,
|
| 2001 |
+
"train_samples_per_second": 1.103,
|
| 2002 |
+
"train_steps_per_second": 0.068
|
| 2003 |
+
}
|
| 2004 |
+
],
|
| 2005 |
+
"logging_steps": 1,
|
| 2006 |
+
"max_steps": 124,
|
| 2007 |
+
"num_input_tokens_seen": 0,
|
| 2008 |
+
"num_train_epochs": 2,
|
| 2009 |
+
"save_steps": 500,
|
| 2010 |
+
"total_flos": 1.6196776411267072e+16,
|
| 2011 |
+
"train_batch_size": 2,
|
| 2012 |
+
"trial_name": null,
|
| 2013 |
+
"trial_params": null
|
| 2014 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1986f4a40fd6bc597f97e0c94ab5f343578e515047e50e4acf28ef950ec036e1
|
| 3 |
+
size 5048
|