Task: SequenceClassification
Browse files- README.md +202 -0
- adapter_config.json +35 -0
- adapter_model.safetensors +3 -0
- merges.txt +0 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +30 -0
- trainer_state-opt-gptq-QLORA-super_glue-rte-sequence_classification.json +2590 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: RMHalak/opt-6.7b-GPTQ-4bits-128g-wikitext2
|
| 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 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "RMHalak/opt-6.7b-GPTQ-4bits-128g-wikitext2",
|
| 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 |
+
"q_proj",
|
| 26 |
+
"fc1",
|
| 27 |
+
"fc2",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"out_proj"
|
| 31 |
+
],
|
| 32 |
+
"task_type": "SEQ_CLS",
|
| 33 |
+
"use_dora": false,
|
| 34 |
+
"use_rslora": false
|
| 35 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48212fb853601b0d361ff3f02b86ae4adaa2d6cb5c63f4da58ce1e6a6d84a079
|
| 3 |
+
size 75566824
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "</s>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 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_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"1": {
|
| 6 |
+
"content": "<pad>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"2": {
|
| 14 |
+
"content": "</s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"bos_token": "</s>",
|
| 23 |
+
"clean_up_tokenization_spaces": true,
|
| 24 |
+
"eos_token": "</s>",
|
| 25 |
+
"errors": "replace",
|
| 26 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 27 |
+
"pad_token": "</s>",
|
| 28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 29 |
+
"unk_token": "</s>"
|
| 30 |
+
}
|
trainer_state-opt-gptq-QLORA-super_glue-rte-sequence_classification.json
ADDED
|
@@ -0,0 +1,2590 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 160,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0625,
|
| 13 |
+
"grad_norm": 17.75647735595703,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 0.8699,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0625,
|
| 20 |
+
"eval_accuracy": 0.496,
|
| 21 |
+
"eval_loss": 0.837658703327179,
|
| 22 |
+
"eval_runtime": 4.5469,
|
| 23 |
+
"eval_samples_per_second": 54.983,
|
| 24 |
+
"eval_steps_per_second": 1.759,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.125,
|
| 29 |
+
"grad_norm": 10.630256652832031,
|
| 30 |
+
"learning_rate": 5e-05,
|
| 31 |
+
"loss": 0.8372,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.125,
|
| 36 |
+
"eval_accuracy": 0.496,
|
| 37 |
+
"eval_loss": 0.8297348618507385,
|
| 38 |
+
"eval_runtime": 4.4856,
|
| 39 |
+
"eval_samples_per_second": 55.733,
|
| 40 |
+
"eval_steps_per_second": 1.783,
|
| 41 |
+
"step": 2
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.1875,
|
| 45 |
+
"grad_norm": 18.88325309753418,
|
| 46 |
+
"learning_rate": 4.968354430379747e-05,
|
| 47 |
+
"loss": 0.8813,
|
| 48 |
+
"step": 3
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.1875,
|
| 52 |
+
"eval_accuracy": 0.496,
|
| 53 |
+
"eval_loss": 0.8005664348602295,
|
| 54 |
+
"eval_runtime": 4.5427,
|
| 55 |
+
"eval_samples_per_second": 55.034,
|
| 56 |
+
"eval_steps_per_second": 1.761,
|
| 57 |
+
"step": 3
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.25,
|
| 61 |
+
"grad_norm": 14.382352828979492,
|
| 62 |
+
"learning_rate": 4.936708860759494e-05,
|
| 63 |
+
"loss": 0.8725,
|
| 64 |
+
"step": 4
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.25,
|
| 68 |
+
"eval_accuracy": 0.5,
|
| 69 |
+
"eval_loss": 0.7717475295066833,
|
| 70 |
+
"eval_runtime": 4.495,
|
| 71 |
+
"eval_samples_per_second": 55.618,
|
| 72 |
+
"eval_steps_per_second": 1.78,
|
| 73 |
+
"step": 4
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3125,
|
| 77 |
+
"grad_norm": 18.139081954956055,
|
| 78 |
+
"learning_rate": 4.905063291139241e-05,
|
| 79 |
+
"loss": 0.8504,
|
| 80 |
+
"step": 5
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3125,
|
| 84 |
+
"eval_accuracy": 0.496,
|
| 85 |
+
"eval_loss": 0.7444770336151123,
|
| 86 |
+
"eval_runtime": 4.5407,
|
| 87 |
+
"eval_samples_per_second": 55.057,
|
| 88 |
+
"eval_steps_per_second": 1.762,
|
| 89 |
+
"step": 5
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.375,
|
| 93 |
+
"grad_norm": 7.32247257232666,
|
| 94 |
+
"learning_rate": 4.8734177215189874e-05,
|
| 95 |
+
"loss": 0.8015,
|
| 96 |
+
"step": 6
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.375,
|
| 100 |
+
"eval_accuracy": 0.5,
|
| 101 |
+
"eval_loss": 0.7214609384536743,
|
| 102 |
+
"eval_runtime": 4.5353,
|
| 103 |
+
"eval_samples_per_second": 55.123,
|
| 104 |
+
"eval_steps_per_second": 1.764,
|
| 105 |
+
"step": 6
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.4375,
|
| 109 |
+
"grad_norm": 4.8535966873168945,
|
| 110 |
+
"learning_rate": 4.8417721518987346e-05,
|
| 111 |
+
"loss": 0.7165,
|
| 112 |
+
"step": 7
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.4375,
|
| 116 |
+
"eval_accuracy": 0.512,
|
| 117 |
+
"eval_loss": 0.7035966515541077,
|
| 118 |
+
"eval_runtime": 4.5437,
|
| 119 |
+
"eval_samples_per_second": 55.021,
|
| 120 |
+
"eval_steps_per_second": 1.761,
|
| 121 |
+
"step": 7
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5,
|
| 125 |
+
"grad_norm": 7.805424690246582,
|
| 126 |
+
"learning_rate": 4.810126582278481e-05,
|
| 127 |
+
"loss": 0.766,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5,
|
| 132 |
+
"eval_accuracy": 0.52,
|
| 133 |
+
"eval_loss": 0.6936992406845093,
|
| 134 |
+
"eval_runtime": 4.5422,
|
| 135 |
+
"eval_samples_per_second": 55.04,
|
| 136 |
+
"eval_steps_per_second": 1.761,
|
| 137 |
+
"step": 8
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5625,
|
| 141 |
+
"grad_norm": 2.8888654708862305,
|
| 142 |
+
"learning_rate": 4.778481012658228e-05,
|
| 143 |
+
"loss": 0.6915,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.5625,
|
| 148 |
+
"eval_accuracy": 0.524,
|
| 149 |
+
"eval_loss": 0.6935371160507202,
|
| 150 |
+
"eval_runtime": 4.4937,
|
| 151 |
+
"eval_samples_per_second": 55.633,
|
| 152 |
+
"eval_steps_per_second": 1.78,
|
| 153 |
+
"step": 9
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.625,
|
| 157 |
+
"grad_norm": 7.086565971374512,
|
| 158 |
+
"learning_rate": 4.7468354430379746e-05,
|
| 159 |
+
"loss": 0.7093,
|
| 160 |
+
"step": 10
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.625,
|
| 164 |
+
"eval_accuracy": 0.532,
|
| 165 |
+
"eval_loss": 0.6983515620231628,
|
| 166 |
+
"eval_runtime": 4.4948,
|
| 167 |
+
"eval_samples_per_second": 55.619,
|
| 168 |
+
"eval_steps_per_second": 1.78,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.6875,
|
| 173 |
+
"grad_norm": 2.0717809200286865,
|
| 174 |
+
"learning_rate": 4.715189873417722e-05,
|
| 175 |
+
"loss": 0.7107,
|
| 176 |
+
"step": 11
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.6875,
|
| 180 |
+
"eval_accuracy": 0.524,
|
| 181 |
+
"eval_loss": 0.7018242478370667,
|
| 182 |
+
"eval_runtime": 4.5362,
|
| 183 |
+
"eval_samples_per_second": 55.112,
|
| 184 |
+
"eval_steps_per_second": 1.764,
|
| 185 |
+
"step": 11
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.75,
|
| 189 |
+
"grad_norm": 4.748137474060059,
|
| 190 |
+
"learning_rate": 4.683544303797468e-05,
|
| 191 |
+
"loss": 0.729,
|
| 192 |
+
"step": 12
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.75,
|
| 196 |
+
"eval_accuracy": 0.524,
|
| 197 |
+
"eval_loss": 0.7031621336936951,
|
| 198 |
+
"eval_runtime": 4.5441,
|
| 199 |
+
"eval_samples_per_second": 55.017,
|
| 200 |
+
"eval_steps_per_second": 1.761,
|
| 201 |
+
"step": 12
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.8125,
|
| 205 |
+
"grad_norm": 5.206336975097656,
|
| 206 |
+
"learning_rate": 4.6518987341772154e-05,
|
| 207 |
+
"loss": 0.7819,
|
| 208 |
+
"step": 13
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.8125,
|
| 212 |
+
"eval_accuracy": 0.524,
|
| 213 |
+
"eval_loss": 0.7015683650970459,
|
| 214 |
+
"eval_runtime": 4.5432,
|
| 215 |
+
"eval_samples_per_second": 55.028,
|
| 216 |
+
"eval_steps_per_second": 1.761,
|
| 217 |
+
"step": 13
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.875,
|
| 221 |
+
"grad_norm": 5.746586322784424,
|
| 222 |
+
"learning_rate": 4.6202531645569625e-05,
|
| 223 |
+
"loss": 0.7343,
|
| 224 |
+
"step": 14
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.875,
|
| 228 |
+
"eval_accuracy": 0.524,
|
| 229 |
+
"eval_loss": 0.6985683441162109,
|
| 230 |
+
"eval_runtime": 4.5466,
|
| 231 |
+
"eval_samples_per_second": 54.986,
|
| 232 |
+
"eval_steps_per_second": 1.76,
|
| 233 |
+
"step": 14
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9375,
|
| 237 |
+
"grad_norm": 2.441669464111328,
|
| 238 |
+
"learning_rate": 4.588607594936709e-05,
|
| 239 |
+
"loss": 0.7052,
|
| 240 |
+
"step": 15
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.9375,
|
| 244 |
+
"eval_accuracy": 0.536,
|
| 245 |
+
"eval_loss": 0.6962031126022339,
|
| 246 |
+
"eval_runtime": 4.5479,
|
| 247 |
+
"eval_samples_per_second": 54.97,
|
| 248 |
+
"eval_steps_per_second": 1.759,
|
| 249 |
+
"step": 15
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.0,
|
| 253 |
+
"grad_norm": 8.590319633483887,
|
| 254 |
+
"learning_rate": 4.556962025316456e-05,
|
| 255 |
+
"loss": 0.7406,
|
| 256 |
+
"step": 16
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.0,
|
| 260 |
+
"eval_accuracy": 0.54,
|
| 261 |
+
"eval_loss": 0.6932148337364197,
|
| 262 |
+
"eval_runtime": 4.5474,
|
| 263 |
+
"eval_samples_per_second": 54.977,
|
| 264 |
+
"eval_steps_per_second": 1.759,
|
| 265 |
+
"step": 16
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.0625,
|
| 269 |
+
"grad_norm": 3.343947172164917,
|
| 270 |
+
"learning_rate": 4.525316455696203e-05,
|
| 271 |
+
"loss": 0.6939,
|
| 272 |
+
"step": 17
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.0625,
|
| 276 |
+
"eval_accuracy": 0.524,
|
| 277 |
+
"eval_loss": 0.6910995841026306,
|
| 278 |
+
"eval_runtime": 4.5426,
|
| 279 |
+
"eval_samples_per_second": 55.035,
|
| 280 |
+
"eval_steps_per_second": 1.761,
|
| 281 |
+
"step": 17
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.125,
|
| 285 |
+
"grad_norm": 5.235752582550049,
|
| 286 |
+
"learning_rate": 4.49367088607595e-05,
|
| 287 |
+
"loss": 0.6857,
|
| 288 |
+
"step": 18
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.125,
|
| 292 |
+
"eval_accuracy": 0.528,
|
| 293 |
+
"eval_loss": 0.690261721611023,
|
| 294 |
+
"eval_runtime": 4.5449,
|
| 295 |
+
"eval_samples_per_second": 55.006,
|
| 296 |
+
"eval_steps_per_second": 1.76,
|
| 297 |
+
"step": 18
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.1875,
|
| 301 |
+
"grad_norm": 8.583759307861328,
|
| 302 |
+
"learning_rate": 4.462025316455696e-05,
|
| 303 |
+
"loss": 0.6932,
|
| 304 |
+
"step": 19
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.1875,
|
| 308 |
+
"eval_accuracy": 0.52,
|
| 309 |
+
"eval_loss": 0.6894707083702087,
|
| 310 |
+
"eval_runtime": 4.5371,
|
| 311 |
+
"eval_samples_per_second": 55.101,
|
| 312 |
+
"eval_steps_per_second": 1.763,
|
| 313 |
+
"step": 19
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.25,
|
| 317 |
+
"grad_norm": 9.518383979797363,
|
| 318 |
+
"learning_rate": 4.430379746835443e-05,
|
| 319 |
+
"loss": 0.6993,
|
| 320 |
+
"step": 20
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.25,
|
| 324 |
+
"eval_accuracy": 0.516,
|
| 325 |
+
"eval_loss": 0.6895566582679749,
|
| 326 |
+
"eval_runtime": 4.5489,
|
| 327 |
+
"eval_samples_per_second": 54.958,
|
| 328 |
+
"eval_steps_per_second": 1.759,
|
| 329 |
+
"step": 20
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.3125,
|
| 333 |
+
"grad_norm": 7.239161014556885,
|
| 334 |
+
"learning_rate": 4.3987341772151904e-05,
|
| 335 |
+
"loss": 0.763,
|
| 336 |
+
"step": 21
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.3125,
|
| 340 |
+
"eval_accuracy": 0.52,
|
| 341 |
+
"eval_loss": 0.690017580986023,
|
| 342 |
+
"eval_runtime": 4.4884,
|
| 343 |
+
"eval_samples_per_second": 55.699,
|
| 344 |
+
"eval_steps_per_second": 1.782,
|
| 345 |
+
"step": 21
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.375,
|
| 349 |
+
"grad_norm": 7.390464782714844,
|
| 350 |
+
"learning_rate": 4.367088607594937e-05,
|
| 351 |
+
"loss": 0.6954,
|
| 352 |
+
"step": 22
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.375,
|
| 356 |
+
"eval_accuracy": 0.512,
|
| 357 |
+
"eval_loss": 0.6905702948570251,
|
| 358 |
+
"eval_runtime": 4.5375,
|
| 359 |
+
"eval_samples_per_second": 55.097,
|
| 360 |
+
"eval_steps_per_second": 1.763,
|
| 361 |
+
"step": 22
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.4375,
|
| 365 |
+
"grad_norm": 3.728330135345459,
|
| 366 |
+
"learning_rate": 4.3354430379746834e-05,
|
| 367 |
+
"loss": 0.7282,
|
| 368 |
+
"step": 23
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.4375,
|
| 372 |
+
"eval_accuracy": 0.524,
|
| 373 |
+
"eval_loss": 0.690304696559906,
|
| 374 |
+
"eval_runtime": 4.5427,
|
| 375 |
+
"eval_samples_per_second": 55.033,
|
| 376 |
+
"eval_steps_per_second": 1.761,
|
| 377 |
+
"step": 23
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.5,
|
| 381 |
+
"grad_norm": 5.795580863952637,
|
| 382 |
+
"learning_rate": 4.3037974683544305e-05,
|
| 383 |
+
"loss": 0.7534,
|
| 384 |
+
"step": 24
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.5,
|
| 388 |
+
"eval_accuracy": 0.52,
|
| 389 |
+
"eval_loss": 0.6902949213981628,
|
| 390 |
+
"eval_runtime": 4.5361,
|
| 391 |
+
"eval_samples_per_second": 55.113,
|
| 392 |
+
"eval_steps_per_second": 1.764,
|
| 393 |
+
"step": 24
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.5625,
|
| 397 |
+
"grad_norm": 2.294114589691162,
|
| 398 |
+
"learning_rate": 4.2721518987341776e-05,
|
| 399 |
+
"loss": 0.7245,
|
| 400 |
+
"step": 25
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.5625,
|
| 404 |
+
"eval_accuracy": 0.52,
|
| 405 |
+
"eval_loss": 0.6901406049728394,
|
| 406 |
+
"eval_runtime": 4.4936,
|
| 407 |
+
"eval_samples_per_second": 55.634,
|
| 408 |
+
"eval_steps_per_second": 1.78,
|
| 409 |
+
"step": 25
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.625,
|
| 413 |
+
"grad_norm": 7.018092155456543,
|
| 414 |
+
"learning_rate": 4.240506329113924e-05,
|
| 415 |
+
"loss": 0.692,
|
| 416 |
+
"step": 26
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.625,
|
| 420 |
+
"eval_accuracy": 0.508,
|
| 421 |
+
"eval_loss": 0.6903828382492065,
|
| 422 |
+
"eval_runtime": 4.5453,
|
| 423 |
+
"eval_samples_per_second": 55.002,
|
| 424 |
+
"eval_steps_per_second": 1.76,
|
| 425 |
+
"step": 26
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.6875,
|
| 429 |
+
"grad_norm": 7.2787909507751465,
|
| 430 |
+
"learning_rate": 4.208860759493671e-05,
|
| 431 |
+
"loss": 0.754,
|
| 432 |
+
"step": 27
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.6875,
|
| 436 |
+
"eval_accuracy": 0.512,
|
| 437 |
+
"eval_loss": 0.6910136938095093,
|
| 438 |
+
"eval_runtime": 4.5501,
|
| 439 |
+
"eval_samples_per_second": 54.944,
|
| 440 |
+
"eval_steps_per_second": 1.758,
|
| 441 |
+
"step": 27
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.75,
|
| 445 |
+
"grad_norm": 6.70567512512207,
|
| 446 |
+
"learning_rate": 4.177215189873418e-05,
|
| 447 |
+
"loss": 0.7132,
|
| 448 |
+
"step": 28
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.75,
|
| 452 |
+
"eval_accuracy": 0.508,
|
| 453 |
+
"eval_loss": 0.691275417804718,
|
| 454 |
+
"eval_runtime": 4.4942,
|
| 455 |
+
"eval_samples_per_second": 55.627,
|
| 456 |
+
"eval_steps_per_second": 1.78,
|
| 457 |
+
"step": 28
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.8125,
|
| 461 |
+
"grad_norm": 7.861635208129883,
|
| 462 |
+
"learning_rate": 4.145569620253165e-05,
|
| 463 |
+
"loss": 0.7075,
|
| 464 |
+
"step": 29
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.8125,
|
| 468 |
+
"eval_accuracy": 0.52,
|
| 469 |
+
"eval_loss": 0.6910507678985596,
|
| 470 |
+
"eval_runtime": 4.5518,
|
| 471 |
+
"eval_samples_per_second": 54.924,
|
| 472 |
+
"eval_steps_per_second": 1.758,
|
| 473 |
+
"step": 29
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.875,
|
| 477 |
+
"grad_norm": 6.021241188049316,
|
| 478 |
+
"learning_rate": 4.113924050632912e-05,
|
| 479 |
+
"loss": 0.7013,
|
| 480 |
+
"step": 30
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.875,
|
| 484 |
+
"eval_accuracy": 0.528,
|
| 485 |
+
"eval_loss": 0.6917343735694885,
|
| 486 |
+
"eval_runtime": 4.5466,
|
| 487 |
+
"eval_samples_per_second": 54.986,
|
| 488 |
+
"eval_steps_per_second": 1.76,
|
| 489 |
+
"step": 30
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.9375,
|
| 493 |
+
"grad_norm": 4.954082012176514,
|
| 494 |
+
"learning_rate": 4.0822784810126584e-05,
|
| 495 |
+
"loss": 0.7059,
|
| 496 |
+
"step": 31
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.9375,
|
| 500 |
+
"eval_accuracy": 0.508,
|
| 501 |
+
"eval_loss": 0.692550778388977,
|
| 502 |
+
"eval_runtime": 4.5373,
|
| 503 |
+
"eval_samples_per_second": 55.099,
|
| 504 |
+
"eval_steps_per_second": 1.763,
|
| 505 |
+
"step": 31
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.0,
|
| 509 |
+
"grad_norm": 4.5776824951171875,
|
| 510 |
+
"learning_rate": 4.050632911392405e-05,
|
| 511 |
+
"loss": 0.6932,
|
| 512 |
+
"step": 32
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.0,
|
| 516 |
+
"eval_accuracy": 0.52,
|
| 517 |
+
"eval_loss": 0.692632794380188,
|
| 518 |
+
"eval_runtime": 4.5448,
|
| 519 |
+
"eval_samples_per_second": 55.008,
|
| 520 |
+
"eval_steps_per_second": 1.76,
|
| 521 |
+
"step": 32
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.0625,
|
| 525 |
+
"grad_norm": 8.209676742553711,
|
| 526 |
+
"learning_rate": 4.018987341772152e-05,
|
| 527 |
+
"loss": 0.7083,
|
| 528 |
+
"step": 33
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.0625,
|
| 532 |
+
"eval_accuracy": 0.52,
|
| 533 |
+
"eval_loss": 0.6923945546150208,
|
| 534 |
+
"eval_runtime": 4.5461,
|
| 535 |
+
"eval_samples_per_second": 54.993,
|
| 536 |
+
"eval_steps_per_second": 1.76,
|
| 537 |
+
"step": 33
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.125,
|
| 541 |
+
"grad_norm": 2.001976490020752,
|
| 542 |
+
"learning_rate": 3.987341772151899e-05,
|
| 543 |
+
"loss": 0.7423,
|
| 544 |
+
"step": 34
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.125,
|
| 548 |
+
"eval_accuracy": 0.528,
|
| 549 |
+
"eval_loss": 0.692144513130188,
|
| 550 |
+
"eval_runtime": 4.5419,
|
| 551 |
+
"eval_samples_per_second": 55.043,
|
| 552 |
+
"eval_steps_per_second": 1.761,
|
| 553 |
+
"step": 34
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.1875,
|
| 557 |
+
"grad_norm": 7.856252670288086,
|
| 558 |
+
"learning_rate": 3.9556962025316456e-05,
|
| 559 |
+
"loss": 0.6794,
|
| 560 |
+
"step": 35
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.1875,
|
| 564 |
+
"eval_accuracy": 0.532,
|
| 565 |
+
"eval_loss": 0.6922343969345093,
|
| 566 |
+
"eval_runtime": 4.5401,
|
| 567 |
+
"eval_samples_per_second": 55.065,
|
| 568 |
+
"eval_steps_per_second": 1.762,
|
| 569 |
+
"step": 35
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.25,
|
| 573 |
+
"grad_norm": 10.469124794006348,
|
| 574 |
+
"learning_rate": 3.924050632911392e-05,
|
| 575 |
+
"loss": 0.7089,
|
| 576 |
+
"step": 36
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.25,
|
| 580 |
+
"eval_accuracy": 0.52,
|
| 581 |
+
"eval_loss": 0.6925742030143738,
|
| 582 |
+
"eval_runtime": 4.4947,
|
| 583 |
+
"eval_samples_per_second": 55.621,
|
| 584 |
+
"eval_steps_per_second": 1.78,
|
| 585 |
+
"step": 36
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.3125,
|
| 589 |
+
"grad_norm": 12.528965950012207,
|
| 590 |
+
"learning_rate": 3.89240506329114e-05,
|
| 591 |
+
"loss": 0.738,
|
| 592 |
+
"step": 37
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.3125,
|
| 596 |
+
"eval_accuracy": 0.512,
|
| 597 |
+
"eval_loss": 0.6928867101669312,
|
| 598 |
+
"eval_runtime": 4.4904,
|
| 599 |
+
"eval_samples_per_second": 55.674,
|
| 600 |
+
"eval_steps_per_second": 1.782,
|
| 601 |
+
"step": 37
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.375,
|
| 605 |
+
"grad_norm": 10.900518417358398,
|
| 606 |
+
"learning_rate": 3.8607594936708864e-05,
|
| 607 |
+
"loss": 0.6796,
|
| 608 |
+
"step": 38
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.375,
|
| 612 |
+
"eval_accuracy": 0.512,
|
| 613 |
+
"eval_loss": 0.6924609541893005,
|
| 614 |
+
"eval_runtime": 4.5411,
|
| 615 |
+
"eval_samples_per_second": 55.052,
|
| 616 |
+
"eval_steps_per_second": 1.762,
|
| 617 |
+
"step": 38
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 2.4375,
|
| 621 |
+
"grad_norm": 1.5410585403442383,
|
| 622 |
+
"learning_rate": 3.829113924050633e-05,
|
| 623 |
+
"loss": 0.6729,
|
| 624 |
+
"step": 39
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.4375,
|
| 628 |
+
"eval_accuracy": 0.512,
|
| 629 |
+
"eval_loss": 0.6923437714576721,
|
| 630 |
+
"eval_runtime": 4.5412,
|
| 631 |
+
"eval_samples_per_second": 55.052,
|
| 632 |
+
"eval_steps_per_second": 1.762,
|
| 633 |
+
"step": 39
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.5,
|
| 637 |
+
"grad_norm": 5.861754894256592,
|
| 638 |
+
"learning_rate": 3.79746835443038e-05,
|
| 639 |
+
"loss": 0.6589,
|
| 640 |
+
"step": 40
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.5,
|
| 644 |
+
"eval_accuracy": 0.512,
|
| 645 |
+
"eval_loss": 0.6922851800918579,
|
| 646 |
+
"eval_runtime": 4.5478,
|
| 647 |
+
"eval_samples_per_second": 54.971,
|
| 648 |
+
"eval_steps_per_second": 1.759,
|
| 649 |
+
"step": 40
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.5625,
|
| 653 |
+
"grad_norm": 2.633316993713379,
|
| 654 |
+
"learning_rate": 3.765822784810127e-05,
|
| 655 |
+
"loss": 0.7336,
|
| 656 |
+
"step": 41
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.5625,
|
| 660 |
+
"eval_accuracy": 0.512,
|
| 661 |
+
"eval_loss": 0.6914882659912109,
|
| 662 |
+
"eval_runtime": 4.4965,
|
| 663 |
+
"eval_samples_per_second": 55.598,
|
| 664 |
+
"eval_steps_per_second": 1.779,
|
| 665 |
+
"step": 41
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.625,
|
| 669 |
+
"grad_norm": 4.3643693923950195,
|
| 670 |
+
"learning_rate": 3.7341772151898736e-05,
|
| 671 |
+
"loss": 0.7018,
|
| 672 |
+
"step": 42
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.625,
|
| 676 |
+
"eval_accuracy": 0.524,
|
| 677 |
+
"eval_loss": 0.690136730670929,
|
| 678 |
+
"eval_runtime": 4.5418,
|
| 679 |
+
"eval_samples_per_second": 55.045,
|
| 680 |
+
"eval_steps_per_second": 1.761,
|
| 681 |
+
"step": 42
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.6875,
|
| 685 |
+
"grad_norm": 4.561107158660889,
|
| 686 |
+
"learning_rate": 3.70253164556962e-05,
|
| 687 |
+
"loss": 0.7331,
|
| 688 |
+
"step": 43
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.6875,
|
| 692 |
+
"eval_accuracy": 0.536,
|
| 693 |
+
"eval_loss": 0.6878847479820251,
|
| 694 |
+
"eval_runtime": 4.5431,
|
| 695 |
+
"eval_samples_per_second": 55.028,
|
| 696 |
+
"eval_steps_per_second": 1.761,
|
| 697 |
+
"step": 43
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.75,
|
| 701 |
+
"grad_norm": 2.425762891769409,
|
| 702 |
+
"learning_rate": 3.670886075949367e-05,
|
| 703 |
+
"loss": 0.6961,
|
| 704 |
+
"step": 44
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.75,
|
| 708 |
+
"eval_accuracy": 0.544,
|
| 709 |
+
"eval_loss": 0.6869159936904907,
|
| 710 |
+
"eval_runtime": 4.5385,
|
| 711 |
+
"eval_samples_per_second": 55.084,
|
| 712 |
+
"eval_steps_per_second": 1.763,
|
| 713 |
+
"step": 44
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.8125,
|
| 717 |
+
"grad_norm": 7.950039863586426,
|
| 718 |
+
"learning_rate": 3.639240506329114e-05,
|
| 719 |
+
"loss": 0.7228,
|
| 720 |
+
"step": 45
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.8125,
|
| 724 |
+
"eval_accuracy": 0.544,
|
| 725 |
+
"eval_loss": 0.6861679553985596,
|
| 726 |
+
"eval_runtime": 4.5403,
|
| 727 |
+
"eval_samples_per_second": 55.063,
|
| 728 |
+
"eval_steps_per_second": 1.762,
|
| 729 |
+
"step": 45
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.875,
|
| 733 |
+
"grad_norm": 12.410717964172363,
|
| 734 |
+
"learning_rate": 3.607594936708861e-05,
|
| 735 |
+
"loss": 0.7031,
|
| 736 |
+
"step": 46
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.875,
|
| 740 |
+
"eval_accuracy": 0.532,
|
| 741 |
+
"eval_loss": 0.685476541519165,
|
| 742 |
+
"eval_runtime": 4.5437,
|
| 743 |
+
"eval_samples_per_second": 55.022,
|
| 744 |
+
"eval_steps_per_second": 1.761,
|
| 745 |
+
"step": 46
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.9375,
|
| 749 |
+
"grad_norm": 3.116471767425537,
|
| 750 |
+
"learning_rate": 3.575949367088608e-05,
|
| 751 |
+
"loss": 0.6885,
|
| 752 |
+
"step": 47
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.9375,
|
| 756 |
+
"eval_accuracy": 0.544,
|
| 757 |
+
"eval_loss": 0.6849316358566284,
|
| 758 |
+
"eval_runtime": 4.5418,
|
| 759 |
+
"eval_samples_per_second": 55.045,
|
| 760 |
+
"eval_steps_per_second": 1.761,
|
| 761 |
+
"step": 47
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 3.0,
|
| 765 |
+
"grad_norm": 6.724969387054443,
|
| 766 |
+
"learning_rate": 3.5443037974683544e-05,
|
| 767 |
+
"loss": 0.7062,
|
| 768 |
+
"step": 48
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 3.0,
|
| 772 |
+
"eval_accuracy": 0.532,
|
| 773 |
+
"eval_loss": 0.6846718788146973,
|
| 774 |
+
"eval_runtime": 4.4458,
|
| 775 |
+
"eval_samples_per_second": 56.233,
|
| 776 |
+
"eval_steps_per_second": 1.799,
|
| 777 |
+
"step": 48
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.0625,
|
| 781 |
+
"grad_norm": 2.1322343349456787,
|
| 782 |
+
"learning_rate": 3.5126582278481015e-05,
|
| 783 |
+
"loss": 0.6679,
|
| 784 |
+
"step": 49
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 3.0625,
|
| 788 |
+
"eval_accuracy": 0.532,
|
| 789 |
+
"eval_loss": 0.6838710904121399,
|
| 790 |
+
"eval_runtime": 4.4926,
|
| 791 |
+
"eval_samples_per_second": 55.648,
|
| 792 |
+
"eval_steps_per_second": 1.781,
|
| 793 |
+
"step": 49
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 3.125,
|
| 797 |
+
"grad_norm": 6.895395278930664,
|
| 798 |
+
"learning_rate": 3.4810126582278487e-05,
|
| 799 |
+
"loss": 0.6956,
|
| 800 |
+
"step": 50
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.125,
|
| 804 |
+
"eval_accuracy": 0.532,
|
| 805 |
+
"eval_loss": 0.6838496327400208,
|
| 806 |
+
"eval_runtime": 4.5422,
|
| 807 |
+
"eval_samples_per_second": 55.04,
|
| 808 |
+
"eval_steps_per_second": 1.761,
|
| 809 |
+
"step": 50
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.1875,
|
| 813 |
+
"grad_norm": 10.101134300231934,
|
| 814 |
+
"learning_rate": 3.449367088607595e-05,
|
| 815 |
+
"loss": 0.7449,
|
| 816 |
+
"step": 51
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.1875,
|
| 820 |
+
"eval_accuracy": 0.528,
|
| 821 |
+
"eval_loss": 0.6836503744125366,
|
| 822 |
+
"eval_runtime": 4.5,
|
| 823 |
+
"eval_samples_per_second": 55.556,
|
| 824 |
+
"eval_steps_per_second": 1.778,
|
| 825 |
+
"step": 51
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.25,
|
| 829 |
+
"grad_norm": 5.3039422035217285,
|
| 830 |
+
"learning_rate": 3.4177215189873416e-05,
|
| 831 |
+
"loss": 0.6853,
|
| 832 |
+
"step": 52
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 3.25,
|
| 836 |
+
"eval_accuracy": 0.536,
|
| 837 |
+
"eval_loss": 0.6831699013710022,
|
| 838 |
+
"eval_runtime": 4.4953,
|
| 839 |
+
"eval_samples_per_second": 55.613,
|
| 840 |
+
"eval_steps_per_second": 1.78,
|
| 841 |
+
"step": 52
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.3125,
|
| 845 |
+
"grad_norm": 2.962162733078003,
|
| 846 |
+
"learning_rate": 3.386075949367089e-05,
|
| 847 |
+
"loss": 0.7127,
|
| 848 |
+
"step": 53
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.3125,
|
| 852 |
+
"eval_accuracy": 0.536,
|
| 853 |
+
"eval_loss": 0.6828047037124634,
|
| 854 |
+
"eval_runtime": 4.5467,
|
| 855 |
+
"eval_samples_per_second": 54.985,
|
| 856 |
+
"eval_steps_per_second": 1.76,
|
| 857 |
+
"step": 53
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.375,
|
| 861 |
+
"grad_norm": 4.858814239501953,
|
| 862 |
+
"learning_rate": 3.354430379746836e-05,
|
| 863 |
+
"loss": 0.6544,
|
| 864 |
+
"step": 54
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.375,
|
| 868 |
+
"eval_accuracy": 0.556,
|
| 869 |
+
"eval_loss": 0.6824140548706055,
|
| 870 |
+
"eval_runtime": 4.5474,
|
| 871 |
+
"eval_samples_per_second": 54.976,
|
| 872 |
+
"eval_steps_per_second": 1.759,
|
| 873 |
+
"step": 54
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.4375,
|
| 877 |
+
"grad_norm": 5.237043380737305,
|
| 878 |
+
"learning_rate": 3.322784810126582e-05,
|
| 879 |
+
"loss": 0.6638,
|
| 880 |
+
"step": 55
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.4375,
|
| 884 |
+
"eval_accuracy": 0.532,
|
| 885 |
+
"eval_loss": 0.6816914081573486,
|
| 886 |
+
"eval_runtime": 4.5453,
|
| 887 |
+
"eval_samples_per_second": 55.002,
|
| 888 |
+
"eval_steps_per_second": 1.76,
|
| 889 |
+
"step": 55
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 3.5,
|
| 893 |
+
"grad_norm": 3.878478527069092,
|
| 894 |
+
"learning_rate": 3.291139240506329e-05,
|
| 895 |
+
"loss": 0.7148,
|
| 896 |
+
"step": 56
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.5,
|
| 900 |
+
"eval_accuracy": 0.536,
|
| 901 |
+
"eval_loss": 0.6814433336257935,
|
| 902 |
+
"eval_runtime": 4.5412,
|
| 903 |
+
"eval_samples_per_second": 55.052,
|
| 904 |
+
"eval_steps_per_second": 1.762,
|
| 905 |
+
"step": 56
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.5625,
|
| 909 |
+
"grad_norm": 4.188953399658203,
|
| 910 |
+
"learning_rate": 3.2594936708860766e-05,
|
| 911 |
+
"loss": 0.7003,
|
| 912 |
+
"step": 57
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 3.5625,
|
| 916 |
+
"eval_accuracy": 0.528,
|
| 917 |
+
"eval_loss": 0.6815546751022339,
|
| 918 |
+
"eval_runtime": 4.5437,
|
| 919 |
+
"eval_samples_per_second": 55.021,
|
| 920 |
+
"eval_steps_per_second": 1.761,
|
| 921 |
+
"step": 57
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 3.625,
|
| 925 |
+
"grad_norm": 12.408546447753906,
|
| 926 |
+
"learning_rate": 3.227848101265823e-05,
|
| 927 |
+
"loss": 0.771,
|
| 928 |
+
"step": 58
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.625,
|
| 932 |
+
"eval_accuracy": 0.528,
|
| 933 |
+
"eval_loss": 0.681021511554718,
|
| 934 |
+
"eval_runtime": 4.5384,
|
| 935 |
+
"eval_samples_per_second": 55.086,
|
| 936 |
+
"eval_steps_per_second": 1.763,
|
| 937 |
+
"step": 58
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 3.6875,
|
| 941 |
+
"grad_norm": 3.4157402515411377,
|
| 942 |
+
"learning_rate": 3.1962025316455695e-05,
|
| 943 |
+
"loss": 0.6973,
|
| 944 |
+
"step": 59
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.6875,
|
| 948 |
+
"eval_accuracy": 0.512,
|
| 949 |
+
"eval_loss": 0.6810234189033508,
|
| 950 |
+
"eval_runtime": 4.5487,
|
| 951 |
+
"eval_samples_per_second": 54.96,
|
| 952 |
+
"eval_steps_per_second": 1.759,
|
| 953 |
+
"step": 59
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.75,
|
| 957 |
+
"grad_norm": 7.873476028442383,
|
| 958 |
+
"learning_rate": 3.1645569620253167e-05,
|
| 959 |
+
"loss": 0.7426,
|
| 960 |
+
"step": 60
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.75,
|
| 964 |
+
"eval_accuracy": 0.512,
|
| 965 |
+
"eval_loss": 0.6811171770095825,
|
| 966 |
+
"eval_runtime": 4.5472,
|
| 967 |
+
"eval_samples_per_second": 54.978,
|
| 968 |
+
"eval_steps_per_second": 1.759,
|
| 969 |
+
"step": 60
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.8125,
|
| 973 |
+
"grad_norm": 5.3661322593688965,
|
| 974 |
+
"learning_rate": 3.132911392405064e-05,
|
| 975 |
+
"loss": 0.6969,
|
| 976 |
+
"step": 61
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.8125,
|
| 980 |
+
"eval_accuracy": 0.528,
|
| 981 |
+
"eval_loss": 0.6811054944992065,
|
| 982 |
+
"eval_runtime": 4.5489,
|
| 983 |
+
"eval_samples_per_second": 54.959,
|
| 984 |
+
"eval_steps_per_second": 1.759,
|
| 985 |
+
"step": 61
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 3.875,
|
| 989 |
+
"grad_norm": 2.467409372329712,
|
| 990 |
+
"learning_rate": 3.10126582278481e-05,
|
| 991 |
+
"loss": 0.7369,
|
| 992 |
+
"step": 62
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.875,
|
| 996 |
+
"eval_accuracy": 0.54,
|
| 997 |
+
"eval_loss": 0.6803652048110962,
|
| 998 |
+
"eval_runtime": 4.5424,
|
| 999 |
+
"eval_samples_per_second": 55.037,
|
| 1000 |
+
"eval_steps_per_second": 1.761,
|
| 1001 |
+
"step": 62
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.9375,
|
| 1005 |
+
"grad_norm": 2.4884164333343506,
|
| 1006 |
+
"learning_rate": 3.0696202531645574e-05,
|
| 1007 |
+
"loss": 0.6572,
|
| 1008 |
+
"step": 63
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.9375,
|
| 1012 |
+
"eval_accuracy": 0.56,
|
| 1013 |
+
"eval_loss": 0.6803945302963257,
|
| 1014 |
+
"eval_runtime": 4.5015,
|
| 1015 |
+
"eval_samples_per_second": 55.537,
|
| 1016 |
+
"eval_steps_per_second": 1.777,
|
| 1017 |
+
"step": 63
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 4.0,
|
| 1021 |
+
"grad_norm": 1.9957572221755981,
|
| 1022 |
+
"learning_rate": 3.0379746835443042e-05,
|
| 1023 |
+
"loss": 0.758,
|
| 1024 |
+
"step": 64
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 4.0,
|
| 1028 |
+
"eval_accuracy": 0.544,
|
| 1029 |
+
"eval_loss": 0.6798281073570251,
|
| 1030 |
+
"eval_runtime": 4.5427,
|
| 1031 |
+
"eval_samples_per_second": 55.033,
|
| 1032 |
+
"eval_steps_per_second": 1.761,
|
| 1033 |
+
"step": 64
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 4.0625,
|
| 1037 |
+
"grad_norm": 11.552275657653809,
|
| 1038 |
+
"learning_rate": 3.0063291139240506e-05,
|
| 1039 |
+
"loss": 0.7428,
|
| 1040 |
+
"step": 65
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 4.0625,
|
| 1044 |
+
"eval_accuracy": 0.524,
|
| 1045 |
+
"eval_loss": 0.679925799369812,
|
| 1046 |
+
"eval_runtime": 4.539,
|
| 1047 |
+
"eval_samples_per_second": 55.078,
|
| 1048 |
+
"eval_steps_per_second": 1.763,
|
| 1049 |
+
"step": 65
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.125,
|
| 1053 |
+
"grad_norm": 2.6973438262939453,
|
| 1054 |
+
"learning_rate": 2.9746835443037974e-05,
|
| 1055 |
+
"loss": 0.6784,
|
| 1056 |
+
"step": 66
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 4.125,
|
| 1060 |
+
"eval_accuracy": 0.536,
|
| 1061 |
+
"eval_loss": 0.6790605187416077,
|
| 1062 |
+
"eval_runtime": 4.5462,
|
| 1063 |
+
"eval_samples_per_second": 54.991,
|
| 1064 |
+
"eval_steps_per_second": 1.76,
|
| 1065 |
+
"step": 66
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.1875,
|
| 1069 |
+
"grad_norm": 3.727440595626831,
|
| 1070 |
+
"learning_rate": 2.9430379746835446e-05,
|
| 1071 |
+
"loss": 0.7045,
|
| 1072 |
+
"step": 67
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 4.1875,
|
| 1076 |
+
"eval_accuracy": 0.528,
|
| 1077 |
+
"eval_loss": 0.6793281435966492,
|
| 1078 |
+
"eval_runtime": 4.5469,
|
| 1079 |
+
"eval_samples_per_second": 54.983,
|
| 1080 |
+
"eval_steps_per_second": 1.759,
|
| 1081 |
+
"step": 67
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.25,
|
| 1085 |
+
"grad_norm": 1.7801040410995483,
|
| 1086 |
+
"learning_rate": 2.9113924050632914e-05,
|
| 1087 |
+
"loss": 0.643,
|
| 1088 |
+
"step": 68
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.25,
|
| 1092 |
+
"eval_accuracy": 0.512,
|
| 1093 |
+
"eval_loss": 0.6788183450698853,
|
| 1094 |
+
"eval_runtime": 4.5354,
|
| 1095 |
+
"eval_samples_per_second": 55.122,
|
| 1096 |
+
"eval_steps_per_second": 1.764,
|
| 1097 |
+
"step": 68
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.3125,
|
| 1101 |
+
"grad_norm": 3.4789085388183594,
|
| 1102 |
+
"learning_rate": 2.879746835443038e-05,
|
| 1103 |
+
"loss": 0.675,
|
| 1104 |
+
"step": 69
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 4.3125,
|
| 1108 |
+
"eval_accuracy": 0.52,
|
| 1109 |
+
"eval_loss": 0.6782128810882568,
|
| 1110 |
+
"eval_runtime": 4.5402,
|
| 1111 |
+
"eval_samples_per_second": 55.063,
|
| 1112 |
+
"eval_steps_per_second": 1.762,
|
| 1113 |
+
"step": 69
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 4.375,
|
| 1117 |
+
"grad_norm": 4.243752956390381,
|
| 1118 |
+
"learning_rate": 2.848101265822785e-05,
|
| 1119 |
+
"loss": 0.6469,
|
| 1120 |
+
"step": 70
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 4.375,
|
| 1124 |
+
"eval_accuracy": 0.508,
|
| 1125 |
+
"eval_loss": 0.6780292987823486,
|
| 1126 |
+
"eval_runtime": 4.543,
|
| 1127 |
+
"eval_samples_per_second": 55.029,
|
| 1128 |
+
"eval_steps_per_second": 1.761,
|
| 1129 |
+
"step": 70
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 4.4375,
|
| 1133 |
+
"grad_norm": 6.593841552734375,
|
| 1134 |
+
"learning_rate": 2.8164556962025318e-05,
|
| 1135 |
+
"loss": 0.7455,
|
| 1136 |
+
"step": 71
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.4375,
|
| 1140 |
+
"eval_accuracy": 0.516,
|
| 1141 |
+
"eval_loss": 0.6775800585746765,
|
| 1142 |
+
"eval_runtime": 4.545,
|
| 1143 |
+
"eval_samples_per_second": 55.005,
|
| 1144 |
+
"eval_steps_per_second": 1.76,
|
| 1145 |
+
"step": 71
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.5,
|
| 1149 |
+
"grad_norm": 12.047831535339355,
|
| 1150 |
+
"learning_rate": 2.7848101265822786e-05,
|
| 1151 |
+
"loss": 0.6985,
|
| 1152 |
+
"step": 72
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.5,
|
| 1156 |
+
"eval_accuracy": 0.516,
|
| 1157 |
+
"eval_loss": 0.6778261661529541,
|
| 1158 |
+
"eval_runtime": 4.5527,
|
| 1159 |
+
"eval_samples_per_second": 54.912,
|
| 1160 |
+
"eval_steps_per_second": 1.757,
|
| 1161 |
+
"step": 72
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 4.5625,
|
| 1165 |
+
"grad_norm": 3.4566452503204346,
|
| 1166 |
+
"learning_rate": 2.7531645569620257e-05,
|
| 1167 |
+
"loss": 0.7616,
|
| 1168 |
+
"step": 73
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 4.5625,
|
| 1172 |
+
"eval_accuracy": 0.52,
|
| 1173 |
+
"eval_loss": 0.6769921779632568,
|
| 1174 |
+
"eval_runtime": 4.545,
|
| 1175 |
+
"eval_samples_per_second": 55.005,
|
| 1176 |
+
"eval_steps_per_second": 1.76,
|
| 1177 |
+
"step": 73
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 4.625,
|
| 1181 |
+
"grad_norm": 2.8978374004364014,
|
| 1182 |
+
"learning_rate": 2.7215189873417722e-05,
|
| 1183 |
+
"loss": 0.7135,
|
| 1184 |
+
"step": 74
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.625,
|
| 1188 |
+
"eval_accuracy": 0.516,
|
| 1189 |
+
"eval_loss": 0.6770429611206055,
|
| 1190 |
+
"eval_runtime": 4.541,
|
| 1191 |
+
"eval_samples_per_second": 55.054,
|
| 1192 |
+
"eval_steps_per_second": 1.762,
|
| 1193 |
+
"step": 74
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.6875,
|
| 1197 |
+
"grad_norm": 3.3244338035583496,
|
| 1198 |
+
"learning_rate": 2.689873417721519e-05,
|
| 1199 |
+
"loss": 0.7157,
|
| 1200 |
+
"step": 75
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.6875,
|
| 1204 |
+
"eval_accuracy": 0.528,
|
| 1205 |
+
"eval_loss": 0.6766347885131836,
|
| 1206 |
+
"eval_runtime": 4.5403,
|
| 1207 |
+
"eval_samples_per_second": 55.062,
|
| 1208 |
+
"eval_steps_per_second": 1.762,
|
| 1209 |
+
"step": 75
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 4.75,
|
| 1213 |
+
"grad_norm": 5.23004150390625,
|
| 1214 |
+
"learning_rate": 2.6582278481012658e-05,
|
| 1215 |
+
"loss": 0.7058,
|
| 1216 |
+
"step": 76
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 4.75,
|
| 1220 |
+
"eval_accuracy": 0.528,
|
| 1221 |
+
"eval_loss": 0.6764668226242065,
|
| 1222 |
+
"eval_runtime": 4.54,
|
| 1223 |
+
"eval_samples_per_second": 55.066,
|
| 1224 |
+
"eval_steps_per_second": 1.762,
|
| 1225 |
+
"step": 76
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 4.8125,
|
| 1229 |
+
"grad_norm": 8.803872108459473,
|
| 1230 |
+
"learning_rate": 2.626582278481013e-05,
|
| 1231 |
+
"loss": 0.7127,
|
| 1232 |
+
"step": 77
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 4.8125,
|
| 1236 |
+
"eval_accuracy": 0.524,
|
| 1237 |
+
"eval_loss": 0.6759433746337891,
|
| 1238 |
+
"eval_runtime": 4.5454,
|
| 1239 |
+
"eval_samples_per_second": 55.0,
|
| 1240 |
+
"eval_steps_per_second": 1.76,
|
| 1241 |
+
"step": 77
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 4.875,
|
| 1245 |
+
"grad_norm": 3.5992655754089355,
|
| 1246 |
+
"learning_rate": 2.5949367088607597e-05,
|
| 1247 |
+
"loss": 0.7004,
|
| 1248 |
+
"step": 78
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 4.875,
|
| 1252 |
+
"eval_accuracy": 0.536,
|
| 1253 |
+
"eval_loss": 0.6762988567352295,
|
| 1254 |
+
"eval_runtime": 4.4993,
|
| 1255 |
+
"eval_samples_per_second": 55.565,
|
| 1256 |
+
"eval_steps_per_second": 1.778,
|
| 1257 |
+
"step": 78
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 4.9375,
|
| 1261 |
+
"grad_norm": 3.1371684074401855,
|
| 1262 |
+
"learning_rate": 2.5632911392405062e-05,
|
| 1263 |
+
"loss": 0.6827,
|
| 1264 |
+
"step": 79
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 4.9375,
|
| 1268 |
+
"eval_accuracy": 0.552,
|
| 1269 |
+
"eval_loss": 0.6757890582084656,
|
| 1270 |
+
"eval_runtime": 4.5476,
|
| 1271 |
+
"eval_samples_per_second": 54.974,
|
| 1272 |
+
"eval_steps_per_second": 1.759,
|
| 1273 |
+
"step": 79
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 5.0,
|
| 1277 |
+
"grad_norm": 3.854306697845459,
|
| 1278 |
+
"learning_rate": 2.5316455696202533e-05,
|
| 1279 |
+
"loss": 0.7649,
|
| 1280 |
+
"step": 80
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 5.0,
|
| 1284 |
+
"eval_accuracy": 0.54,
|
| 1285 |
+
"eval_loss": 0.6760488152503967,
|
| 1286 |
+
"eval_runtime": 4.539,
|
| 1287 |
+
"eval_samples_per_second": 55.079,
|
| 1288 |
+
"eval_steps_per_second": 1.763,
|
| 1289 |
+
"step": 80
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 5.0625,
|
| 1293 |
+
"grad_norm": 4.356711387634277,
|
| 1294 |
+
"learning_rate": 2.5e-05,
|
| 1295 |
+
"loss": 0.7461,
|
| 1296 |
+
"step": 81
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 5.0625,
|
| 1300 |
+
"eval_accuracy": 0.54,
|
| 1301 |
+
"eval_loss": 0.6765702962875366,
|
| 1302 |
+
"eval_runtime": 4.4883,
|
| 1303 |
+
"eval_samples_per_second": 55.701,
|
| 1304 |
+
"eval_steps_per_second": 1.782,
|
| 1305 |
+
"step": 81
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 5.125,
|
| 1309 |
+
"grad_norm": 4.030115127563477,
|
| 1310 |
+
"learning_rate": 2.468354430379747e-05,
|
| 1311 |
+
"loss": 0.6346,
|
| 1312 |
+
"step": 82
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 5.125,
|
| 1316 |
+
"eval_accuracy": 0.536,
|
| 1317 |
+
"eval_loss": 0.6769394278526306,
|
| 1318 |
+
"eval_runtime": 4.5387,
|
| 1319 |
+
"eval_samples_per_second": 55.082,
|
| 1320 |
+
"eval_steps_per_second": 1.763,
|
| 1321 |
+
"step": 82
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 5.1875,
|
| 1325 |
+
"grad_norm": 3.892704486846924,
|
| 1326 |
+
"learning_rate": 2.4367088607594937e-05,
|
| 1327 |
+
"loss": 0.6245,
|
| 1328 |
+
"step": 83
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 5.1875,
|
| 1332 |
+
"eval_accuracy": 0.548,
|
| 1333 |
+
"eval_loss": 0.6764355301856995,
|
| 1334 |
+
"eval_runtime": 4.548,
|
| 1335 |
+
"eval_samples_per_second": 54.969,
|
| 1336 |
+
"eval_steps_per_second": 1.759,
|
| 1337 |
+
"step": 83
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 5.25,
|
| 1341 |
+
"grad_norm": 2.755213975906372,
|
| 1342 |
+
"learning_rate": 2.4050632911392405e-05,
|
| 1343 |
+
"loss": 0.6595,
|
| 1344 |
+
"step": 84
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 5.25,
|
| 1348 |
+
"eval_accuracy": 0.548,
|
| 1349 |
+
"eval_loss": 0.6767304539680481,
|
| 1350 |
+
"eval_runtime": 4.5445,
|
| 1351 |
+
"eval_samples_per_second": 55.012,
|
| 1352 |
+
"eval_steps_per_second": 1.76,
|
| 1353 |
+
"step": 84
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 5.3125,
|
| 1357 |
+
"grad_norm": 9.109251976013184,
|
| 1358 |
+
"learning_rate": 2.3734177215189873e-05,
|
| 1359 |
+
"loss": 0.6507,
|
| 1360 |
+
"step": 85
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 5.3125,
|
| 1364 |
+
"eval_accuracy": 0.552,
|
| 1365 |
+
"eval_loss": 0.6769980192184448,
|
| 1366 |
+
"eval_runtime": 4.4987,
|
| 1367 |
+
"eval_samples_per_second": 55.572,
|
| 1368 |
+
"eval_steps_per_second": 1.778,
|
| 1369 |
+
"step": 85
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 5.375,
|
| 1373 |
+
"grad_norm": 4.487890720367432,
|
| 1374 |
+
"learning_rate": 2.341772151898734e-05,
|
| 1375 |
+
"loss": 0.6528,
|
| 1376 |
+
"step": 86
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 5.375,
|
| 1380 |
+
"eval_accuracy": 0.552,
|
| 1381 |
+
"eval_loss": 0.6765019297599792,
|
| 1382 |
+
"eval_runtime": 4.544,
|
| 1383 |
+
"eval_samples_per_second": 55.017,
|
| 1384 |
+
"eval_steps_per_second": 1.761,
|
| 1385 |
+
"step": 86
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 5.4375,
|
| 1389 |
+
"grad_norm": 2.2593257427215576,
|
| 1390 |
+
"learning_rate": 2.3101265822784813e-05,
|
| 1391 |
+
"loss": 0.687,
|
| 1392 |
+
"step": 87
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 5.4375,
|
| 1396 |
+
"eval_accuracy": 0.564,
|
| 1397 |
+
"eval_loss": 0.6773359179496765,
|
| 1398 |
+
"eval_runtime": 4.5397,
|
| 1399 |
+
"eval_samples_per_second": 55.07,
|
| 1400 |
+
"eval_steps_per_second": 1.762,
|
| 1401 |
+
"step": 87
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 5.5,
|
| 1405 |
+
"grad_norm": 9.76685905456543,
|
| 1406 |
+
"learning_rate": 2.278481012658228e-05,
|
| 1407 |
+
"loss": 0.6913,
|
| 1408 |
+
"step": 88
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 5.5,
|
| 1412 |
+
"eval_accuracy": 0.56,
|
| 1413 |
+
"eval_loss": 0.6779413819313049,
|
| 1414 |
+
"eval_runtime": 4.5446,
|
| 1415 |
+
"eval_samples_per_second": 55.01,
|
| 1416 |
+
"eval_steps_per_second": 1.76,
|
| 1417 |
+
"step": 88
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 5.5625,
|
| 1421 |
+
"grad_norm": 1.9855612516403198,
|
| 1422 |
+
"learning_rate": 2.246835443037975e-05,
|
| 1423 |
+
"loss": 0.6799,
|
| 1424 |
+
"step": 89
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 5.5625,
|
| 1428 |
+
"eval_accuracy": 0.56,
|
| 1429 |
+
"eval_loss": 0.6777753829956055,
|
| 1430 |
+
"eval_runtime": 4.5453,
|
| 1431 |
+
"eval_samples_per_second": 55.002,
|
| 1432 |
+
"eval_steps_per_second": 1.76,
|
| 1433 |
+
"step": 89
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 5.625,
|
| 1437 |
+
"grad_norm": 6.978314399719238,
|
| 1438 |
+
"learning_rate": 2.2151898734177217e-05,
|
| 1439 |
+
"loss": 0.6616,
|
| 1440 |
+
"step": 90
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 5.625,
|
| 1444 |
+
"eval_accuracy": 0.568,
|
| 1445 |
+
"eval_loss": 0.6782050728797913,
|
| 1446 |
+
"eval_runtime": 4.5005,
|
| 1447 |
+
"eval_samples_per_second": 55.549,
|
| 1448 |
+
"eval_steps_per_second": 1.778,
|
| 1449 |
+
"step": 90
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 5.6875,
|
| 1453 |
+
"grad_norm": 2.3891565799713135,
|
| 1454 |
+
"learning_rate": 2.1835443037974685e-05,
|
| 1455 |
+
"loss": 0.6577,
|
| 1456 |
+
"step": 91
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 5.6875,
|
| 1460 |
+
"eval_accuracy": 0.552,
|
| 1461 |
+
"eval_loss": 0.6784765720367432,
|
| 1462 |
+
"eval_runtime": 4.5406,
|
| 1463 |
+
"eval_samples_per_second": 55.059,
|
| 1464 |
+
"eval_steps_per_second": 1.762,
|
| 1465 |
+
"step": 91
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 5.75,
|
| 1469 |
+
"grad_norm": 4.9778313636779785,
|
| 1470 |
+
"learning_rate": 2.1518987341772153e-05,
|
| 1471 |
+
"loss": 0.6248,
|
| 1472 |
+
"step": 92
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 5.75,
|
| 1476 |
+
"eval_accuracy": 0.556,
|
| 1477 |
+
"eval_loss": 0.678955078125,
|
| 1478 |
+
"eval_runtime": 4.5404,
|
| 1479 |
+
"eval_samples_per_second": 55.062,
|
| 1480 |
+
"eval_steps_per_second": 1.762,
|
| 1481 |
+
"step": 92
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 5.8125,
|
| 1485 |
+
"grad_norm": 1.9475889205932617,
|
| 1486 |
+
"learning_rate": 2.120253164556962e-05,
|
| 1487 |
+
"loss": 0.7026,
|
| 1488 |
+
"step": 93
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 5.8125,
|
| 1492 |
+
"eval_accuracy": 0.552,
|
| 1493 |
+
"eval_loss": 0.6784570217132568,
|
| 1494 |
+
"eval_runtime": 4.5434,
|
| 1495 |
+
"eval_samples_per_second": 55.025,
|
| 1496 |
+
"eval_steps_per_second": 1.761,
|
| 1497 |
+
"step": 93
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 5.875,
|
| 1501 |
+
"grad_norm": 6.539444923400879,
|
| 1502 |
+
"learning_rate": 2.088607594936709e-05,
|
| 1503 |
+
"loss": 0.6816,
|
| 1504 |
+
"step": 94
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 5.875,
|
| 1508 |
+
"eval_accuracy": 0.536,
|
| 1509 |
+
"eval_loss": 0.6789179444313049,
|
| 1510 |
+
"eval_runtime": 4.5418,
|
| 1511 |
+
"eval_samples_per_second": 55.044,
|
| 1512 |
+
"eval_steps_per_second": 1.761,
|
| 1513 |
+
"step": 94
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 5.9375,
|
| 1517 |
+
"grad_norm": 1.8745115995407104,
|
| 1518 |
+
"learning_rate": 2.056962025316456e-05,
|
| 1519 |
+
"loss": 0.6476,
|
| 1520 |
+
"step": 95
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 5.9375,
|
| 1524 |
+
"eval_accuracy": 0.532,
|
| 1525 |
+
"eval_loss": 0.6787148714065552,
|
| 1526 |
+
"eval_runtime": 4.5397,
|
| 1527 |
+
"eval_samples_per_second": 55.069,
|
| 1528 |
+
"eval_steps_per_second": 1.762,
|
| 1529 |
+
"step": 95
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 6.0,
|
| 1533 |
+
"grad_norm": 7.960897922515869,
|
| 1534 |
+
"learning_rate": 2.0253164556962025e-05,
|
| 1535 |
+
"loss": 0.6797,
|
| 1536 |
+
"step": 96
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 6.0,
|
| 1540 |
+
"eval_accuracy": 0.54,
|
| 1541 |
+
"eval_loss": 0.6785527467727661,
|
| 1542 |
+
"eval_runtime": 4.5395,
|
| 1543 |
+
"eval_samples_per_second": 55.072,
|
| 1544 |
+
"eval_steps_per_second": 1.762,
|
| 1545 |
+
"step": 96
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 6.0625,
|
| 1549 |
+
"grad_norm": 6.119703769683838,
|
| 1550 |
+
"learning_rate": 1.9936708860759496e-05,
|
| 1551 |
+
"loss": 0.6603,
|
| 1552 |
+
"step": 97
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 6.0625,
|
| 1556 |
+
"eval_accuracy": 0.532,
|
| 1557 |
+
"eval_loss": 0.6781836152076721,
|
| 1558 |
+
"eval_runtime": 4.5394,
|
| 1559 |
+
"eval_samples_per_second": 55.073,
|
| 1560 |
+
"eval_steps_per_second": 1.762,
|
| 1561 |
+
"step": 97
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 6.125,
|
| 1565 |
+
"grad_norm": 2.6292548179626465,
|
| 1566 |
+
"learning_rate": 1.962025316455696e-05,
|
| 1567 |
+
"loss": 0.6892,
|
| 1568 |
+
"step": 98
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 6.125,
|
| 1572 |
+
"eval_accuracy": 0.54,
|
| 1573 |
+
"eval_loss": 0.6773242354393005,
|
| 1574 |
+
"eval_runtime": 4.5436,
|
| 1575 |
+
"eval_samples_per_second": 55.022,
|
| 1576 |
+
"eval_steps_per_second": 1.761,
|
| 1577 |
+
"step": 98
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 6.1875,
|
| 1581 |
+
"grad_norm": 5.301840305328369,
|
| 1582 |
+
"learning_rate": 1.9303797468354432e-05,
|
| 1583 |
+
"loss": 0.677,
|
| 1584 |
+
"step": 99
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 6.1875,
|
| 1588 |
+
"eval_accuracy": 0.548,
|
| 1589 |
+
"eval_loss": 0.6762461066246033,
|
| 1590 |
+
"eval_runtime": 4.5432,
|
| 1591 |
+
"eval_samples_per_second": 55.027,
|
| 1592 |
+
"eval_steps_per_second": 1.761,
|
| 1593 |
+
"step": 99
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 6.25,
|
| 1597 |
+
"grad_norm": 3.4270968437194824,
|
| 1598 |
+
"learning_rate": 1.89873417721519e-05,
|
| 1599 |
+
"loss": 0.6696,
|
| 1600 |
+
"step": 100
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 6.25,
|
| 1604 |
+
"eval_accuracy": 0.544,
|
| 1605 |
+
"eval_loss": 0.6752324104309082,
|
| 1606 |
+
"eval_runtime": 4.5411,
|
| 1607 |
+
"eval_samples_per_second": 55.052,
|
| 1608 |
+
"eval_steps_per_second": 1.762,
|
| 1609 |
+
"step": 100
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 6.3125,
|
| 1613 |
+
"grad_norm": 2.9809482097625732,
|
| 1614 |
+
"learning_rate": 1.8670886075949368e-05,
|
| 1615 |
+
"loss": 0.666,
|
| 1616 |
+
"step": 101
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 6.3125,
|
| 1620 |
+
"eval_accuracy": 0.56,
|
| 1621 |
+
"eval_loss": 0.6741093993186951,
|
| 1622 |
+
"eval_runtime": 4.5435,
|
| 1623 |
+
"eval_samples_per_second": 55.024,
|
| 1624 |
+
"eval_steps_per_second": 1.761,
|
| 1625 |
+
"step": 101
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 6.375,
|
| 1629 |
+
"grad_norm": 3.612354278564453,
|
| 1630 |
+
"learning_rate": 1.8354430379746836e-05,
|
| 1631 |
+
"loss": 0.6552,
|
| 1632 |
+
"step": 102
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 6.375,
|
| 1636 |
+
"eval_accuracy": 0.564,
|
| 1637 |
+
"eval_loss": 0.6736387014389038,
|
| 1638 |
+
"eval_runtime": 4.5443,
|
| 1639 |
+
"eval_samples_per_second": 55.014,
|
| 1640 |
+
"eval_steps_per_second": 1.76,
|
| 1641 |
+
"step": 102
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 6.4375,
|
| 1645 |
+
"grad_norm": 13.848094940185547,
|
| 1646 |
+
"learning_rate": 1.8037974683544304e-05,
|
| 1647 |
+
"loss": 0.6958,
|
| 1648 |
+
"step": 103
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 6.4375,
|
| 1652 |
+
"eval_accuracy": 0.564,
|
| 1653 |
+
"eval_loss": 0.6730585694313049,
|
| 1654 |
+
"eval_runtime": 4.537,
|
| 1655 |
+
"eval_samples_per_second": 55.102,
|
| 1656 |
+
"eval_steps_per_second": 1.763,
|
| 1657 |
+
"step": 103
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 6.5,
|
| 1661 |
+
"grad_norm": 2.657895565032959,
|
| 1662 |
+
"learning_rate": 1.7721518987341772e-05,
|
| 1663 |
+
"loss": 0.6779,
|
| 1664 |
+
"step": 104
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 6.5,
|
| 1668 |
+
"eval_accuracy": 0.576,
|
| 1669 |
+
"eval_loss": 0.6721835732460022,
|
| 1670 |
+
"eval_runtime": 4.5416,
|
| 1671 |
+
"eval_samples_per_second": 55.047,
|
| 1672 |
+
"eval_steps_per_second": 1.762,
|
| 1673 |
+
"step": 104
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 6.5625,
|
| 1677 |
+
"grad_norm": 3.6230475902557373,
|
| 1678 |
+
"learning_rate": 1.7405063291139243e-05,
|
| 1679 |
+
"loss": 0.662,
|
| 1680 |
+
"step": 105
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 6.5625,
|
| 1684 |
+
"eval_accuracy": 0.576,
|
| 1685 |
+
"eval_loss": 0.6725234389305115,
|
| 1686 |
+
"eval_runtime": 4.4966,
|
| 1687 |
+
"eval_samples_per_second": 55.598,
|
| 1688 |
+
"eval_steps_per_second": 1.779,
|
| 1689 |
+
"step": 105
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 6.625,
|
| 1693 |
+
"grad_norm": 2.817807674407959,
|
| 1694 |
+
"learning_rate": 1.7088607594936708e-05,
|
| 1695 |
+
"loss": 0.639,
|
| 1696 |
+
"step": 106
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 6.625,
|
| 1700 |
+
"eval_accuracy": 0.58,
|
| 1701 |
+
"eval_loss": 0.6714980602264404,
|
| 1702 |
+
"eval_runtime": 4.4976,
|
| 1703 |
+
"eval_samples_per_second": 55.585,
|
| 1704 |
+
"eval_steps_per_second": 1.779,
|
| 1705 |
+
"step": 106
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 6.6875,
|
| 1709 |
+
"grad_norm": 2.2491910457611084,
|
| 1710 |
+
"learning_rate": 1.677215189873418e-05,
|
| 1711 |
+
"loss": 0.6469,
|
| 1712 |
+
"step": 107
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 6.6875,
|
| 1716 |
+
"eval_accuracy": 0.564,
|
| 1717 |
+
"eval_loss": 0.6703847646713257,
|
| 1718 |
+
"eval_runtime": 4.5015,
|
| 1719 |
+
"eval_samples_per_second": 55.537,
|
| 1720 |
+
"eval_steps_per_second": 1.777,
|
| 1721 |
+
"step": 107
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 6.75,
|
| 1725 |
+
"grad_norm": 6.607123851776123,
|
| 1726 |
+
"learning_rate": 1.6455696202531644e-05,
|
| 1727 |
+
"loss": 0.6494,
|
| 1728 |
+
"step": 108
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 6.75,
|
| 1732 |
+
"eval_accuracy": 0.544,
|
| 1733 |
+
"eval_loss": 0.6705585718154907,
|
| 1734 |
+
"eval_runtime": 4.5512,
|
| 1735 |
+
"eval_samples_per_second": 54.931,
|
| 1736 |
+
"eval_steps_per_second": 1.758,
|
| 1737 |
+
"step": 108
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 6.8125,
|
| 1741 |
+
"grad_norm": 3.7436728477478027,
|
| 1742 |
+
"learning_rate": 1.6139240506329115e-05,
|
| 1743 |
+
"loss": 0.6428,
|
| 1744 |
+
"step": 109
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 6.8125,
|
| 1748 |
+
"eval_accuracy": 0.556,
|
| 1749 |
+
"eval_loss": 0.6696659922599792,
|
| 1750 |
+
"eval_runtime": 4.5466,
|
| 1751 |
+
"eval_samples_per_second": 54.986,
|
| 1752 |
+
"eval_steps_per_second": 1.76,
|
| 1753 |
+
"step": 109
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 6.875,
|
| 1757 |
+
"grad_norm": 10.663908004760742,
|
| 1758 |
+
"learning_rate": 1.5822784810126583e-05,
|
| 1759 |
+
"loss": 0.6949,
|
| 1760 |
+
"step": 110
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 6.875,
|
| 1764 |
+
"eval_accuracy": 0.552,
|
| 1765 |
+
"eval_loss": 0.6699844002723694,
|
| 1766 |
+
"eval_runtime": 4.5417,
|
| 1767 |
+
"eval_samples_per_second": 55.046,
|
| 1768 |
+
"eval_steps_per_second": 1.761,
|
| 1769 |
+
"step": 110
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 6.9375,
|
| 1773 |
+
"grad_norm": 2.8781378269195557,
|
| 1774 |
+
"learning_rate": 1.550632911392405e-05,
|
| 1775 |
+
"loss": 0.6557,
|
| 1776 |
+
"step": 111
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 6.9375,
|
| 1780 |
+
"eval_accuracy": 0.556,
|
| 1781 |
+
"eval_loss": 0.6697744131088257,
|
| 1782 |
+
"eval_runtime": 4.5421,
|
| 1783 |
+
"eval_samples_per_second": 55.041,
|
| 1784 |
+
"eval_steps_per_second": 1.761,
|
| 1785 |
+
"step": 111
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 7.0,
|
| 1789 |
+
"grad_norm": 9.62548828125,
|
| 1790 |
+
"learning_rate": 1.5189873417721521e-05,
|
| 1791 |
+
"loss": 0.625,
|
| 1792 |
+
"step": 112
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 7.0,
|
| 1796 |
+
"eval_accuracy": 0.56,
|
| 1797 |
+
"eval_loss": 0.6696327924728394,
|
| 1798 |
+
"eval_runtime": 4.5434,
|
| 1799 |
+
"eval_samples_per_second": 55.025,
|
| 1800 |
+
"eval_steps_per_second": 1.761,
|
| 1801 |
+
"step": 112
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 7.0625,
|
| 1805 |
+
"grad_norm": 3.4376492500305176,
|
| 1806 |
+
"learning_rate": 1.4873417721518987e-05,
|
| 1807 |
+
"loss": 0.6648,
|
| 1808 |
+
"step": 113
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 7.0625,
|
| 1812 |
+
"eval_accuracy": 0.556,
|
| 1813 |
+
"eval_loss": 0.6688730716705322,
|
| 1814 |
+
"eval_runtime": 4.5489,
|
| 1815 |
+
"eval_samples_per_second": 54.958,
|
| 1816 |
+
"eval_steps_per_second": 1.759,
|
| 1817 |
+
"step": 113
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 7.125,
|
| 1821 |
+
"grad_norm": 11.591545104980469,
|
| 1822 |
+
"learning_rate": 1.4556962025316457e-05,
|
| 1823 |
+
"loss": 0.6909,
|
| 1824 |
+
"step": 114
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 7.125,
|
| 1828 |
+
"eval_accuracy": 0.54,
|
| 1829 |
+
"eval_loss": 0.6680371165275574,
|
| 1830 |
+
"eval_runtime": 4.5477,
|
| 1831 |
+
"eval_samples_per_second": 54.973,
|
| 1832 |
+
"eval_steps_per_second": 1.759,
|
| 1833 |
+
"step": 114
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 7.1875,
|
| 1837 |
+
"grad_norm": 3.0911552906036377,
|
| 1838 |
+
"learning_rate": 1.4240506329113925e-05,
|
| 1839 |
+
"loss": 0.6548,
|
| 1840 |
+
"step": 115
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 7.1875,
|
| 1844 |
+
"eval_accuracy": 0.552,
|
| 1845 |
+
"eval_loss": 0.667611300945282,
|
| 1846 |
+
"eval_runtime": 4.5404,
|
| 1847 |
+
"eval_samples_per_second": 55.062,
|
| 1848 |
+
"eval_steps_per_second": 1.762,
|
| 1849 |
+
"step": 115
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 7.25,
|
| 1853 |
+
"grad_norm": 5.890276908874512,
|
| 1854 |
+
"learning_rate": 1.3924050632911393e-05,
|
| 1855 |
+
"loss": 0.6278,
|
| 1856 |
+
"step": 116
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 7.25,
|
| 1860 |
+
"eval_accuracy": 0.58,
|
| 1861 |
+
"eval_loss": 0.6670957207679749,
|
| 1862 |
+
"eval_runtime": 4.5443,
|
| 1863 |
+
"eval_samples_per_second": 55.014,
|
| 1864 |
+
"eval_steps_per_second": 1.76,
|
| 1865 |
+
"step": 116
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 7.3125,
|
| 1869 |
+
"grad_norm": 2.038860321044922,
|
| 1870 |
+
"learning_rate": 1.3607594936708861e-05,
|
| 1871 |
+
"loss": 0.6899,
|
| 1872 |
+
"step": 117
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 7.3125,
|
| 1876 |
+
"eval_accuracy": 0.596,
|
| 1877 |
+
"eval_loss": 0.6669042706489563,
|
| 1878 |
+
"eval_runtime": 4.5442,
|
| 1879 |
+
"eval_samples_per_second": 55.015,
|
| 1880 |
+
"eval_steps_per_second": 1.76,
|
| 1881 |
+
"step": 117
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 7.375,
|
| 1885 |
+
"grad_norm": 7.413594722747803,
|
| 1886 |
+
"learning_rate": 1.3291139240506329e-05,
|
| 1887 |
+
"loss": 0.6197,
|
| 1888 |
+
"step": 118
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 7.375,
|
| 1892 |
+
"eval_accuracy": 0.588,
|
| 1893 |
+
"eval_loss": 0.6667382717132568,
|
| 1894 |
+
"eval_runtime": 4.5391,
|
| 1895 |
+
"eval_samples_per_second": 55.077,
|
| 1896 |
+
"eval_steps_per_second": 1.762,
|
| 1897 |
+
"step": 118
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 7.4375,
|
| 1901 |
+
"grad_norm": 3.1535215377807617,
|
| 1902 |
+
"learning_rate": 1.2974683544303799e-05,
|
| 1903 |
+
"loss": 0.653,
|
| 1904 |
+
"step": 119
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 7.4375,
|
| 1908 |
+
"eval_accuracy": 0.588,
|
| 1909 |
+
"eval_loss": 0.666509747505188,
|
| 1910 |
+
"eval_runtime": 4.5431,
|
| 1911 |
+
"eval_samples_per_second": 55.028,
|
| 1912 |
+
"eval_steps_per_second": 1.761,
|
| 1913 |
+
"step": 119
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 7.5,
|
| 1917 |
+
"grad_norm": 5.736833095550537,
|
| 1918 |
+
"learning_rate": 1.2658227848101267e-05,
|
| 1919 |
+
"loss": 0.6531,
|
| 1920 |
+
"step": 120
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 7.5,
|
| 1924 |
+
"eval_accuracy": 0.592,
|
| 1925 |
+
"eval_loss": 0.6669736504554749,
|
| 1926 |
+
"eval_runtime": 4.5365,
|
| 1927 |
+
"eval_samples_per_second": 55.108,
|
| 1928 |
+
"eval_steps_per_second": 1.763,
|
| 1929 |
+
"step": 120
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 7.5625,
|
| 1933 |
+
"grad_norm": 3.403089761734009,
|
| 1934 |
+
"learning_rate": 1.2341772151898735e-05,
|
| 1935 |
+
"loss": 0.6494,
|
| 1936 |
+
"step": 121
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 7.5625,
|
| 1940 |
+
"eval_accuracy": 0.584,
|
| 1941 |
+
"eval_loss": 0.6666631102561951,
|
| 1942 |
+
"eval_runtime": 4.5001,
|
| 1943 |
+
"eval_samples_per_second": 55.555,
|
| 1944 |
+
"eval_steps_per_second": 1.778,
|
| 1945 |
+
"step": 121
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 7.625,
|
| 1949 |
+
"grad_norm": 2.2943952083587646,
|
| 1950 |
+
"learning_rate": 1.2025316455696203e-05,
|
| 1951 |
+
"loss": 0.6914,
|
| 1952 |
+
"step": 122
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 7.625,
|
| 1956 |
+
"eval_accuracy": 0.588,
|
| 1957 |
+
"eval_loss": 0.6671044826507568,
|
| 1958 |
+
"eval_runtime": 4.5495,
|
| 1959 |
+
"eval_samples_per_second": 54.952,
|
| 1960 |
+
"eval_steps_per_second": 1.758,
|
| 1961 |
+
"step": 122
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 7.6875,
|
| 1965 |
+
"grad_norm": 1.8052605390548706,
|
| 1966 |
+
"learning_rate": 1.170886075949367e-05,
|
| 1967 |
+
"loss": 0.6506,
|
| 1968 |
+
"step": 123
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 7.6875,
|
| 1972 |
+
"eval_accuracy": 0.592,
|
| 1973 |
+
"eval_loss": 0.6672109365463257,
|
| 1974 |
+
"eval_runtime": 4.5468,
|
| 1975 |
+
"eval_samples_per_second": 54.984,
|
| 1976 |
+
"eval_steps_per_second": 1.759,
|
| 1977 |
+
"step": 123
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 7.75,
|
| 1981 |
+
"grad_norm": 2.0512139797210693,
|
| 1982 |
+
"learning_rate": 1.139240506329114e-05,
|
| 1983 |
+
"loss": 0.6647,
|
| 1984 |
+
"step": 124
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 7.75,
|
| 1988 |
+
"eval_accuracy": 0.592,
|
| 1989 |
+
"eval_loss": 0.6669785380363464,
|
| 1990 |
+
"eval_runtime": 4.5423,
|
| 1991 |
+
"eval_samples_per_second": 55.039,
|
| 1992 |
+
"eval_steps_per_second": 1.761,
|
| 1993 |
+
"step": 124
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 7.8125,
|
| 1997 |
+
"grad_norm": 9.648463249206543,
|
| 1998 |
+
"learning_rate": 1.1075949367088608e-05,
|
| 1999 |
+
"loss": 0.6476,
|
| 2000 |
+
"step": 125
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 7.8125,
|
| 2004 |
+
"eval_accuracy": 0.592,
|
| 2005 |
+
"eval_loss": 0.6669345498085022,
|
| 2006 |
+
"eval_runtime": 4.5447,
|
| 2007 |
+
"eval_samples_per_second": 55.009,
|
| 2008 |
+
"eval_steps_per_second": 1.76,
|
| 2009 |
+
"step": 125
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 7.875,
|
| 2013 |
+
"grad_norm": 3.750437021255493,
|
| 2014 |
+
"learning_rate": 1.0759493670886076e-05,
|
| 2015 |
+
"loss": 0.6609,
|
| 2016 |
+
"step": 126
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 7.875,
|
| 2020 |
+
"eval_accuracy": 0.592,
|
| 2021 |
+
"eval_loss": 0.6669287085533142,
|
| 2022 |
+
"eval_runtime": 4.5377,
|
| 2023 |
+
"eval_samples_per_second": 55.094,
|
| 2024 |
+
"eval_steps_per_second": 1.763,
|
| 2025 |
+
"step": 126
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 7.9375,
|
| 2029 |
+
"grad_norm": 2.9882094860076904,
|
| 2030 |
+
"learning_rate": 1.0443037974683544e-05,
|
| 2031 |
+
"loss": 0.6497,
|
| 2032 |
+
"step": 127
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 7.9375,
|
| 2036 |
+
"eval_accuracy": 0.596,
|
| 2037 |
+
"eval_loss": 0.6663134694099426,
|
| 2038 |
+
"eval_runtime": 4.5412,
|
| 2039 |
+
"eval_samples_per_second": 55.052,
|
| 2040 |
+
"eval_steps_per_second": 1.762,
|
| 2041 |
+
"step": 127
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 8.0,
|
| 2045 |
+
"grad_norm": 5.13292932510376,
|
| 2046 |
+
"learning_rate": 1.0126582278481012e-05,
|
| 2047 |
+
"loss": 0.6773,
|
| 2048 |
+
"step": 128
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 8.0,
|
| 2052 |
+
"eval_accuracy": 0.588,
|
| 2053 |
+
"eval_loss": 0.6660781502723694,
|
| 2054 |
+
"eval_runtime": 4.4907,
|
| 2055 |
+
"eval_samples_per_second": 55.671,
|
| 2056 |
+
"eval_steps_per_second": 1.781,
|
| 2057 |
+
"step": 128
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 8.0625,
|
| 2061 |
+
"grad_norm": 4.037117958068848,
|
| 2062 |
+
"learning_rate": 9.81012658227848e-06,
|
| 2063 |
+
"loss": 0.6841,
|
| 2064 |
+
"step": 129
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 8.0625,
|
| 2068 |
+
"eval_accuracy": 0.596,
|
| 2069 |
+
"eval_loss": 0.6660195589065552,
|
| 2070 |
+
"eval_runtime": 4.4945,
|
| 2071 |
+
"eval_samples_per_second": 55.623,
|
| 2072 |
+
"eval_steps_per_second": 1.78,
|
| 2073 |
+
"step": 129
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 8.125,
|
| 2077 |
+
"grad_norm": 9.9661865234375,
|
| 2078 |
+
"learning_rate": 9.49367088607595e-06,
|
| 2079 |
+
"loss": 0.657,
|
| 2080 |
+
"step": 130
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 8.125,
|
| 2084 |
+
"eval_accuracy": 0.592,
|
| 2085 |
+
"eval_loss": 0.6656200885772705,
|
| 2086 |
+
"eval_runtime": 4.5383,
|
| 2087 |
+
"eval_samples_per_second": 55.086,
|
| 2088 |
+
"eval_steps_per_second": 1.763,
|
| 2089 |
+
"step": 130
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 8.1875,
|
| 2093 |
+
"grad_norm": 8.460039138793945,
|
| 2094 |
+
"learning_rate": 9.177215189873418e-06,
|
| 2095 |
+
"loss": 0.6622,
|
| 2096 |
+
"step": 131
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 8.1875,
|
| 2100 |
+
"eval_accuracy": 0.6,
|
| 2101 |
+
"eval_loss": 0.6657363176345825,
|
| 2102 |
+
"eval_runtime": 4.549,
|
| 2103 |
+
"eval_samples_per_second": 54.957,
|
| 2104 |
+
"eval_steps_per_second": 1.759,
|
| 2105 |
+
"step": 131
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 8.25,
|
| 2109 |
+
"grad_norm": 2.761270046234131,
|
| 2110 |
+
"learning_rate": 8.860759493670886e-06,
|
| 2111 |
+
"loss": 0.667,
|
| 2112 |
+
"step": 132
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 8.25,
|
| 2116 |
+
"eval_accuracy": 0.592,
|
| 2117 |
+
"eval_loss": 0.665112316608429,
|
| 2118 |
+
"eval_runtime": 4.5498,
|
| 2119 |
+
"eval_samples_per_second": 54.947,
|
| 2120 |
+
"eval_steps_per_second": 1.758,
|
| 2121 |
+
"step": 132
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 8.3125,
|
| 2125 |
+
"grad_norm": 4.367539405822754,
|
| 2126 |
+
"learning_rate": 8.544303797468354e-06,
|
| 2127 |
+
"loss": 0.6662,
|
| 2128 |
+
"step": 133
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 8.3125,
|
| 2132 |
+
"eval_accuracy": 0.596,
|
| 2133 |
+
"eval_loss": 0.6654492020606995,
|
| 2134 |
+
"eval_runtime": 4.5418,
|
| 2135 |
+
"eval_samples_per_second": 55.044,
|
| 2136 |
+
"eval_steps_per_second": 1.761,
|
| 2137 |
+
"step": 133
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 8.375,
|
| 2141 |
+
"grad_norm": 3.8258039951324463,
|
| 2142 |
+
"learning_rate": 8.227848101265822e-06,
|
| 2143 |
+
"loss": 0.615,
|
| 2144 |
+
"step": 134
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 8.375,
|
| 2148 |
+
"eval_accuracy": 0.588,
|
| 2149 |
+
"eval_loss": 0.6657968759536743,
|
| 2150 |
+
"eval_runtime": 4.5412,
|
| 2151 |
+
"eval_samples_per_second": 55.051,
|
| 2152 |
+
"eval_steps_per_second": 1.762,
|
| 2153 |
+
"step": 134
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 8.4375,
|
| 2157 |
+
"grad_norm": 2.691741466522217,
|
| 2158 |
+
"learning_rate": 7.911392405063292e-06,
|
| 2159 |
+
"loss": 0.6961,
|
| 2160 |
+
"step": 135
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 8.4375,
|
| 2164 |
+
"eval_accuracy": 0.596,
|
| 2165 |
+
"eval_loss": 0.6653828024864197,
|
| 2166 |
+
"eval_runtime": 4.5434,
|
| 2167 |
+
"eval_samples_per_second": 55.025,
|
| 2168 |
+
"eval_steps_per_second": 1.761,
|
| 2169 |
+
"step": 135
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 8.5,
|
| 2173 |
+
"grad_norm": 5.671183109283447,
|
| 2174 |
+
"learning_rate": 7.5949367088607605e-06,
|
| 2175 |
+
"loss": 0.6134,
|
| 2176 |
+
"step": 136
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 8.5,
|
| 2180 |
+
"eval_accuracy": 0.6,
|
| 2181 |
+
"eval_loss": 0.6660419702529907,
|
| 2182 |
+
"eval_runtime": 4.5413,
|
| 2183 |
+
"eval_samples_per_second": 55.05,
|
| 2184 |
+
"eval_steps_per_second": 1.762,
|
| 2185 |
+
"step": 136
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 8.5625,
|
| 2189 |
+
"grad_norm": 7.398742198944092,
|
| 2190 |
+
"learning_rate": 7.2784810126582285e-06,
|
| 2191 |
+
"loss": 0.6839,
|
| 2192 |
+
"step": 137
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 8.5625,
|
| 2196 |
+
"eval_accuracy": 0.592,
|
| 2197 |
+
"eval_loss": 0.6657724380493164,
|
| 2198 |
+
"eval_runtime": 4.5404,
|
| 2199 |
+
"eval_samples_per_second": 55.061,
|
| 2200 |
+
"eval_steps_per_second": 1.762,
|
| 2201 |
+
"step": 137
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 8.625,
|
| 2205 |
+
"grad_norm": 4.798144340515137,
|
| 2206 |
+
"learning_rate": 6.9620253164556965e-06,
|
| 2207 |
+
"loss": 0.6482,
|
| 2208 |
+
"step": 138
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 8.625,
|
| 2212 |
+
"eval_accuracy": 0.596,
|
| 2213 |
+
"eval_loss": 0.666140615940094,
|
| 2214 |
+
"eval_runtime": 4.5422,
|
| 2215 |
+
"eval_samples_per_second": 55.039,
|
| 2216 |
+
"eval_steps_per_second": 1.761,
|
| 2217 |
+
"step": 138
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 8.6875,
|
| 2221 |
+
"grad_norm": 8.25437068939209,
|
| 2222 |
+
"learning_rate": 6.6455696202531645e-06,
|
| 2223 |
+
"loss": 0.6635,
|
| 2224 |
+
"step": 139
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 8.6875,
|
| 2228 |
+
"eval_accuracy": 0.604,
|
| 2229 |
+
"eval_loss": 0.6665273308753967,
|
| 2230 |
+
"eval_runtime": 4.5468,
|
| 2231 |
+
"eval_samples_per_second": 54.984,
|
| 2232 |
+
"eval_steps_per_second": 1.759,
|
| 2233 |
+
"step": 139
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 8.75,
|
| 2237 |
+
"grad_norm": 2.5796449184417725,
|
| 2238 |
+
"learning_rate": 6.329113924050633e-06,
|
| 2239 |
+
"loss": 0.6229,
|
| 2240 |
+
"step": 140
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 8.75,
|
| 2244 |
+
"eval_accuracy": 0.608,
|
| 2245 |
+
"eval_loss": 0.6665956974029541,
|
| 2246 |
+
"eval_runtime": 4.5394,
|
| 2247 |
+
"eval_samples_per_second": 55.073,
|
| 2248 |
+
"eval_steps_per_second": 1.762,
|
| 2249 |
+
"step": 140
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 8.8125,
|
| 2253 |
+
"grad_norm": 2.3988282680511475,
|
| 2254 |
+
"learning_rate": 6.012658227848101e-06,
|
| 2255 |
+
"loss": 0.6205,
|
| 2256 |
+
"step": 141
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 8.8125,
|
| 2260 |
+
"eval_accuracy": 0.604,
|
| 2261 |
+
"eval_loss": 0.6665576100349426,
|
| 2262 |
+
"eval_runtime": 4.5397,
|
| 2263 |
+
"eval_samples_per_second": 55.07,
|
| 2264 |
+
"eval_steps_per_second": 1.762,
|
| 2265 |
+
"step": 141
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 8.875,
|
| 2269 |
+
"grad_norm": 3.2234578132629395,
|
| 2270 |
+
"learning_rate": 5.69620253164557e-06,
|
| 2271 |
+
"loss": 0.6347,
|
| 2272 |
+
"step": 142
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 8.875,
|
| 2276 |
+
"eval_accuracy": 0.596,
|
| 2277 |
+
"eval_loss": 0.6664531230926514,
|
| 2278 |
+
"eval_runtime": 4.4932,
|
| 2279 |
+
"eval_samples_per_second": 55.64,
|
| 2280 |
+
"eval_steps_per_second": 1.78,
|
| 2281 |
+
"step": 142
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 8.9375,
|
| 2285 |
+
"grad_norm": 3.1038153171539307,
|
| 2286 |
+
"learning_rate": 5.379746835443038e-06,
|
| 2287 |
+
"loss": 0.6868,
|
| 2288 |
+
"step": 143
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 8.9375,
|
| 2292 |
+
"eval_accuracy": 0.608,
|
| 2293 |
+
"eval_loss": 0.6668280959129333,
|
| 2294 |
+
"eval_runtime": 4.5461,
|
| 2295 |
+
"eval_samples_per_second": 54.993,
|
| 2296 |
+
"eval_steps_per_second": 1.76,
|
| 2297 |
+
"step": 143
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 9.0,
|
| 2301 |
+
"grad_norm": 5.682613849639893,
|
| 2302 |
+
"learning_rate": 5.063291139240506e-06,
|
| 2303 |
+
"loss": 0.6447,
|
| 2304 |
+
"step": 144
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 9.0,
|
| 2308 |
+
"eval_accuracy": 0.604,
|
| 2309 |
+
"eval_loss": 0.6665273308753967,
|
| 2310 |
+
"eval_runtime": 4.5397,
|
| 2311 |
+
"eval_samples_per_second": 55.069,
|
| 2312 |
+
"eval_steps_per_second": 1.762,
|
| 2313 |
+
"step": 144
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 9.0625,
|
| 2317 |
+
"grad_norm": 8.149535179138184,
|
| 2318 |
+
"learning_rate": 4.746835443037975e-06,
|
| 2319 |
+
"loss": 0.6755,
|
| 2320 |
+
"step": 145
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 9.0625,
|
| 2324 |
+
"eval_accuracy": 0.596,
|
| 2325 |
+
"eval_loss": 0.6669501662254333,
|
| 2326 |
+
"eval_runtime": 4.497,
|
| 2327 |
+
"eval_samples_per_second": 55.592,
|
| 2328 |
+
"eval_steps_per_second": 1.779,
|
| 2329 |
+
"step": 145
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 9.125,
|
| 2333 |
+
"grad_norm": 3.2166755199432373,
|
| 2334 |
+
"learning_rate": 4.430379746835443e-06,
|
| 2335 |
+
"loss": 0.6749,
|
| 2336 |
+
"step": 146
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 9.125,
|
| 2340 |
+
"eval_accuracy": 0.604,
|
| 2341 |
+
"eval_loss": 0.667477548122406,
|
| 2342 |
+
"eval_runtime": 4.549,
|
| 2343 |
+
"eval_samples_per_second": 54.957,
|
| 2344 |
+
"eval_steps_per_second": 1.759,
|
| 2345 |
+
"step": 146
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 9.1875,
|
| 2349 |
+
"grad_norm": 2.9138267040252686,
|
| 2350 |
+
"learning_rate": 4.113924050632911e-06,
|
| 2351 |
+
"loss": 0.6681,
|
| 2352 |
+
"step": 147
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 9.1875,
|
| 2356 |
+
"eval_accuracy": 0.596,
|
| 2357 |
+
"eval_loss": 0.6679531335830688,
|
| 2358 |
+
"eval_runtime": 4.5432,
|
| 2359 |
+
"eval_samples_per_second": 55.027,
|
| 2360 |
+
"eval_steps_per_second": 1.761,
|
| 2361 |
+
"step": 147
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 9.25,
|
| 2365 |
+
"grad_norm": 8.955977439880371,
|
| 2366 |
+
"learning_rate": 3.7974683544303802e-06,
|
| 2367 |
+
"loss": 0.6768,
|
| 2368 |
+
"step": 148
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 9.25,
|
| 2372 |
+
"eval_accuracy": 0.6,
|
| 2373 |
+
"eval_loss": 0.667892575263977,
|
| 2374 |
+
"eval_runtime": 4.5414,
|
| 2375 |
+
"eval_samples_per_second": 55.049,
|
| 2376 |
+
"eval_steps_per_second": 1.762,
|
| 2377 |
+
"step": 148
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 9.3125,
|
| 2381 |
+
"grad_norm": 4.039650917053223,
|
| 2382 |
+
"learning_rate": 3.4810126582278482e-06,
|
| 2383 |
+
"loss": 0.6291,
|
| 2384 |
+
"step": 149
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 9.3125,
|
| 2388 |
+
"eval_accuracy": 0.596,
|
| 2389 |
+
"eval_loss": 0.6680244207382202,
|
| 2390 |
+
"eval_runtime": 4.5436,
|
| 2391 |
+
"eval_samples_per_second": 55.022,
|
| 2392 |
+
"eval_steps_per_second": 1.761,
|
| 2393 |
+
"step": 149
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 9.375,
|
| 2397 |
+
"grad_norm": 3.648364543914795,
|
| 2398 |
+
"learning_rate": 3.1645569620253167e-06,
|
| 2399 |
+
"loss": 0.6857,
|
| 2400 |
+
"step": 150
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 9.375,
|
| 2404 |
+
"eval_accuracy": 0.596,
|
| 2405 |
+
"eval_loss": 0.6680644750595093,
|
| 2406 |
+
"eval_runtime": 4.5475,
|
| 2407 |
+
"eval_samples_per_second": 54.975,
|
| 2408 |
+
"eval_steps_per_second": 1.759,
|
| 2409 |
+
"step": 150
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 9.4375,
|
| 2413 |
+
"grad_norm": 2.3928475379943848,
|
| 2414 |
+
"learning_rate": 2.848101265822785e-06,
|
| 2415 |
+
"loss": 0.6454,
|
| 2416 |
+
"step": 151
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 9.4375,
|
| 2420 |
+
"eval_accuracy": 0.604,
|
| 2421 |
+
"eval_loss": 0.6678046584129333,
|
| 2422 |
+
"eval_runtime": 4.5472,
|
| 2423 |
+
"eval_samples_per_second": 54.979,
|
| 2424 |
+
"eval_steps_per_second": 1.759,
|
| 2425 |
+
"step": 151
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 9.5,
|
| 2429 |
+
"grad_norm": 1.8685684204101562,
|
| 2430 |
+
"learning_rate": 2.531645569620253e-06,
|
| 2431 |
+
"loss": 0.648,
|
| 2432 |
+
"step": 152
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 9.5,
|
| 2436 |
+
"eval_accuracy": 0.592,
|
| 2437 |
+
"eval_loss": 0.6684179902076721,
|
| 2438 |
+
"eval_runtime": 4.5422,
|
| 2439 |
+
"eval_samples_per_second": 55.04,
|
| 2440 |
+
"eval_steps_per_second": 1.761,
|
| 2441 |
+
"step": 152
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 9.5625,
|
| 2445 |
+
"grad_norm": 6.94075345993042,
|
| 2446 |
+
"learning_rate": 2.2151898734177215e-06,
|
| 2447 |
+
"loss": 0.5989,
|
| 2448 |
+
"step": 153
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 9.5625,
|
| 2452 |
+
"eval_accuracy": 0.604,
|
| 2453 |
+
"eval_loss": 0.6686621308326721,
|
| 2454 |
+
"eval_runtime": 4.549,
|
| 2455 |
+
"eval_samples_per_second": 54.957,
|
| 2456 |
+
"eval_steps_per_second": 1.759,
|
| 2457 |
+
"step": 153
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 9.625,
|
| 2461 |
+
"grad_norm": 2.2033395767211914,
|
| 2462 |
+
"learning_rate": 1.8987341772151901e-06,
|
| 2463 |
+
"loss": 0.6334,
|
| 2464 |
+
"step": 154
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"epoch": 9.625,
|
| 2468 |
+
"eval_accuracy": 0.588,
|
| 2469 |
+
"eval_loss": 0.6692119240760803,
|
| 2470 |
+
"eval_runtime": 4.5415,
|
| 2471 |
+
"eval_samples_per_second": 55.048,
|
| 2472 |
+
"eval_steps_per_second": 1.762,
|
| 2473 |
+
"step": 154
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 9.6875,
|
| 2477 |
+
"grad_norm": 4.624488353729248,
|
| 2478 |
+
"learning_rate": 1.5822784810126583e-06,
|
| 2479 |
+
"loss": 0.6086,
|
| 2480 |
+
"step": 155
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 9.6875,
|
| 2484 |
+
"eval_accuracy": 0.592,
|
| 2485 |
+
"eval_loss": 0.6682060360908508,
|
| 2486 |
+
"eval_runtime": 4.5376,
|
| 2487 |
+
"eval_samples_per_second": 55.095,
|
| 2488 |
+
"eval_steps_per_second": 1.763,
|
| 2489 |
+
"step": 155
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 9.75,
|
| 2493 |
+
"grad_norm": 8.24832820892334,
|
| 2494 |
+
"learning_rate": 1.2658227848101265e-06,
|
| 2495 |
+
"loss": 0.6355,
|
| 2496 |
+
"step": 156
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 9.75,
|
| 2500 |
+
"eval_accuracy": 0.6,
|
| 2501 |
+
"eval_loss": 0.6689130663871765,
|
| 2502 |
+
"eval_runtime": 4.5365,
|
| 2503 |
+
"eval_samples_per_second": 55.109,
|
| 2504 |
+
"eval_steps_per_second": 1.763,
|
| 2505 |
+
"step": 156
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 9.8125,
|
| 2509 |
+
"grad_norm": 1.9968777894973755,
|
| 2510 |
+
"learning_rate": 9.493670886075951e-07,
|
| 2511 |
+
"loss": 0.618,
|
| 2512 |
+
"step": 157
|
| 2513 |
+
},
|
| 2514 |
+
{
|
| 2515 |
+
"epoch": 9.8125,
|
| 2516 |
+
"eval_accuracy": 0.596,
|
| 2517 |
+
"eval_loss": 0.6689111590385437,
|
| 2518 |
+
"eval_runtime": 4.547,
|
| 2519 |
+
"eval_samples_per_second": 54.981,
|
| 2520 |
+
"eval_steps_per_second": 1.759,
|
| 2521 |
+
"step": 157
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 9.875,
|
| 2525 |
+
"grad_norm": 2.4490880966186523,
|
| 2526 |
+
"learning_rate": 6.329113924050633e-07,
|
| 2527 |
+
"loss": 0.6603,
|
| 2528 |
+
"step": 158
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 9.875,
|
| 2532 |
+
"eval_accuracy": 0.596,
|
| 2533 |
+
"eval_loss": 0.6684619188308716,
|
| 2534 |
+
"eval_runtime": 4.5445,
|
| 2535 |
+
"eval_samples_per_second": 55.012,
|
| 2536 |
+
"eval_steps_per_second": 1.76,
|
| 2537 |
+
"step": 158
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 9.9375,
|
| 2541 |
+
"grad_norm": 5.009583950042725,
|
| 2542 |
+
"learning_rate": 3.1645569620253163e-07,
|
| 2543 |
+
"loss": 0.6585,
|
| 2544 |
+
"step": 159
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 9.9375,
|
| 2548 |
+
"eval_accuracy": 0.6,
|
| 2549 |
+
"eval_loss": 0.6681816577911377,
|
| 2550 |
+
"eval_runtime": 4.5393,
|
| 2551 |
+
"eval_samples_per_second": 55.075,
|
| 2552 |
+
"eval_steps_per_second": 1.762,
|
| 2553 |
+
"step": 159
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 10.0,
|
| 2557 |
+
"grad_norm": 3.7535176277160645,
|
| 2558 |
+
"learning_rate": 0.0,
|
| 2559 |
+
"loss": 0.6705,
|
| 2560 |
+
"step": 160
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 10.0,
|
| 2564 |
+
"eval_accuracy": 0.6,
|
| 2565 |
+
"eval_loss": 0.6681679487228394,
|
| 2566 |
+
"eval_runtime": 4.4878,
|
| 2567 |
+
"eval_samples_per_second": 55.706,
|
| 2568 |
+
"eval_steps_per_second": 1.783,
|
| 2569 |
+
"step": 160
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 10.0,
|
| 2573 |
+
"step": 160,
|
| 2574 |
+
"total_flos": 174253428178944.0,
|
| 2575 |
+
"train_loss": 0.6897118806838989,
|
| 2576 |
+
"train_runtime": 1349.6743,
|
| 2577 |
+
"train_samples_per_second": 7.409,
|
| 2578 |
+
"train_steps_per_second": 0.119
|
| 2579 |
+
}
|
| 2580 |
+
],
|
| 2581 |
+
"logging_steps": 1,
|
| 2582 |
+
"max_steps": 160,
|
| 2583 |
+
"num_input_tokens_seen": 0,
|
| 2584 |
+
"num_train_epochs": 10,
|
| 2585 |
+
"save_steps": 500,
|
| 2586 |
+
"total_flos": 174253428178944.0,
|
| 2587 |
+
"train_batch_size": 8,
|
| 2588 |
+
"trial_name": null,
|
| 2589 |
+
"trial_params": null
|
| 2590 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:951bc5536f89534f6ab717cdb4d91e26b154c003b078b79ebfa90cfa4ccef005
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|