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-bnb8-QLORA-super_glue-cb-sequence_classification.json +1390 -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: facebook/opt-6.7b
|
| 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": "facebook/opt-6.7b",
|
| 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 |
+
"k_proj",
|
| 27 |
+
"fc2",
|
| 28 |
+
"out_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"fc1"
|
| 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 sha256:0f2bfa0e08eac47e203f1385724485bbf5d41ff8c2b535dc23af0ca62aceec59
|
| 3 |
+
size 75599592
|
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-bnb8-QLORA-super_glue-cb-sequence_classification.json
ADDED
|
@@ -0,0 +1,1390 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 80,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.125,
|
| 13 |
+
"grad_norm": 21.28069305419922,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 1.2067,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.125,
|
| 20 |
+
"eval_accuracy": 0.3548387096774194,
|
| 21 |
+
"eval_f1": 0.2145748987854251,
|
| 22 |
+
"eval_loss": 1.2299962043762207,
|
| 23 |
+
"eval_runtime": 1.8781,
|
| 24 |
+
"eval_samples_per_second": 33.012,
|
| 25 |
+
"eval_steps_per_second": 2.13,
|
| 26 |
+
"step": 1
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.25,
|
| 30 |
+
"grad_norm": 16.937559127807617,
|
| 31 |
+
"learning_rate": 5e-05,
|
| 32 |
+
"loss": 1.3485,
|
| 33 |
+
"step": 2
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.25,
|
| 37 |
+
"eval_accuracy": 0.3709677419354839,
|
| 38 |
+
"eval_f1": 0.18930041152263377,
|
| 39 |
+
"eval_loss": 1.1593687534332275,
|
| 40 |
+
"eval_runtime": 1.874,
|
| 41 |
+
"eval_samples_per_second": 33.084,
|
| 42 |
+
"eval_steps_per_second": 2.134,
|
| 43 |
+
"step": 2
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.375,
|
| 47 |
+
"grad_norm": 21.755922317504883,
|
| 48 |
+
"learning_rate": 4.935897435897436e-05,
|
| 49 |
+
"loss": 1.2559,
|
| 50 |
+
"step": 3
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.375,
|
| 54 |
+
"eval_accuracy": 0.46774193548387094,
|
| 55 |
+
"eval_f1": 0.23272633346248225,
|
| 56 |
+
"eval_loss": 1.0302419662475586,
|
| 57 |
+
"eval_runtime": 1.875,
|
| 58 |
+
"eval_samples_per_second": 33.067,
|
| 59 |
+
"eval_steps_per_second": 2.133,
|
| 60 |
+
"step": 3
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.5,
|
| 64 |
+
"grad_norm": 10.690485954284668,
|
| 65 |
+
"learning_rate": 4.871794871794872e-05,
|
| 66 |
+
"loss": 1.0408,
|
| 67 |
+
"step": 4
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.5,
|
| 71 |
+
"eval_accuracy": 0.46774193548387094,
|
| 72 |
+
"eval_f1": 0.24990730441231,
|
| 73 |
+
"eval_loss": 0.9755544066429138,
|
| 74 |
+
"eval_runtime": 1.8757,
|
| 75 |
+
"eval_samples_per_second": 33.055,
|
| 76 |
+
"eval_steps_per_second": 2.133,
|
| 77 |
+
"step": 4
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.625,
|
| 81 |
+
"grad_norm": 8.635258674621582,
|
| 82 |
+
"learning_rate": 4.8076923076923084e-05,
|
| 83 |
+
"loss": 0.8126,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.625,
|
| 88 |
+
"eval_accuracy": 0.46774193548387094,
|
| 89 |
+
"eval_f1": 0.2485632183908046,
|
| 90 |
+
"eval_loss": 0.9575037956237793,
|
| 91 |
+
"eval_runtime": 1.9274,
|
| 92 |
+
"eval_samples_per_second": 32.168,
|
| 93 |
+
"eval_steps_per_second": 2.075,
|
| 94 |
+
"step": 5
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.75,
|
| 98 |
+
"grad_norm": 11.213544845581055,
|
| 99 |
+
"learning_rate": 4.7435897435897435e-05,
|
| 100 |
+
"loss": 0.9848,
|
| 101 |
+
"step": 6
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.75,
|
| 105 |
+
"eval_accuracy": 0.5161290322580645,
|
| 106 |
+
"eval_f1": 0.28421309872922773,
|
| 107 |
+
"eval_loss": 0.951880693435669,
|
| 108 |
+
"eval_runtime": 1.9311,
|
| 109 |
+
"eval_samples_per_second": 32.106,
|
| 110 |
+
"eval_steps_per_second": 2.071,
|
| 111 |
+
"step": 6
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.875,
|
| 115 |
+
"grad_norm": 7.83177375793457,
|
| 116 |
+
"learning_rate": 4.67948717948718e-05,
|
| 117 |
+
"loss": 0.8319,
|
| 118 |
+
"step": 7
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.875,
|
| 122 |
+
"eval_accuracy": 0.532258064516129,
|
| 123 |
+
"eval_f1": 0.3174603174603175,
|
| 124 |
+
"eval_loss": 0.962181806564331,
|
| 125 |
+
"eval_runtime": 1.8805,
|
| 126 |
+
"eval_samples_per_second": 32.97,
|
| 127 |
+
"eval_steps_per_second": 2.127,
|
| 128 |
+
"step": 7
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0,
|
| 132 |
+
"grad_norm": 12.740473747253418,
|
| 133 |
+
"learning_rate": 4.615384615384616e-05,
|
| 134 |
+
"loss": 1.0211,
|
| 135 |
+
"step": 8
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.0,
|
| 139 |
+
"eval_accuracy": 0.5,
|
| 140 |
+
"eval_f1": 0.3313632781717888,
|
| 141 |
+
"eval_loss": 0.9630481600761414,
|
| 142 |
+
"eval_runtime": 1.8802,
|
| 143 |
+
"eval_samples_per_second": 32.975,
|
| 144 |
+
"eval_steps_per_second": 2.127,
|
| 145 |
+
"step": 8
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.125,
|
| 149 |
+
"grad_norm": 12.164949417114258,
|
| 150 |
+
"learning_rate": 4.5512820512820516e-05,
|
| 151 |
+
"loss": 0.8899,
|
| 152 |
+
"step": 9
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.125,
|
| 156 |
+
"eval_accuracy": 0.5,
|
| 157 |
+
"eval_f1": 0.3108974358974359,
|
| 158 |
+
"eval_loss": 0.9681987166404724,
|
| 159 |
+
"eval_runtime": 1.8773,
|
| 160 |
+
"eval_samples_per_second": 33.026,
|
| 161 |
+
"eval_steps_per_second": 2.131,
|
| 162 |
+
"step": 9
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.25,
|
| 166 |
+
"grad_norm": 6.146948337554932,
|
| 167 |
+
"learning_rate": 4.4871794871794874e-05,
|
| 168 |
+
"loss": 0.7234,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.25,
|
| 173 |
+
"eval_accuracy": 0.5,
|
| 174 |
+
"eval_f1": 0.3108974358974359,
|
| 175 |
+
"eval_loss": 0.9844852685928345,
|
| 176 |
+
"eval_runtime": 1.8795,
|
| 177 |
+
"eval_samples_per_second": 32.988,
|
| 178 |
+
"eval_steps_per_second": 2.128,
|
| 179 |
+
"step": 10
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.375,
|
| 183 |
+
"grad_norm": 8.822149276733398,
|
| 184 |
+
"learning_rate": 4.423076923076923e-05,
|
| 185 |
+
"loss": 1.0579,
|
| 186 |
+
"step": 11
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.375,
|
| 190 |
+
"eval_accuracy": 0.5,
|
| 191 |
+
"eval_f1": 0.3108974358974359,
|
| 192 |
+
"eval_loss": 0.9911479353904724,
|
| 193 |
+
"eval_runtime": 1.8777,
|
| 194 |
+
"eval_samples_per_second": 33.019,
|
| 195 |
+
"eval_steps_per_second": 2.13,
|
| 196 |
+
"step": 11
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.5,
|
| 200 |
+
"grad_norm": 9.482677459716797,
|
| 201 |
+
"learning_rate": 4.358974358974359e-05,
|
| 202 |
+
"loss": 0.8232,
|
| 203 |
+
"step": 12
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.5,
|
| 207 |
+
"eval_accuracy": 0.5,
|
| 208 |
+
"eval_f1": 0.3108974358974359,
|
| 209 |
+
"eval_loss": 0.9866904020309448,
|
| 210 |
+
"eval_runtime": 1.9302,
|
| 211 |
+
"eval_samples_per_second": 32.121,
|
| 212 |
+
"eval_steps_per_second": 2.072,
|
| 213 |
+
"step": 12
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.625,
|
| 217 |
+
"grad_norm": 17.120052337646484,
|
| 218 |
+
"learning_rate": 4.294871794871795e-05,
|
| 219 |
+
"loss": 1.063,
|
| 220 |
+
"step": 13
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.625,
|
| 224 |
+
"eval_accuracy": 0.5,
|
| 225 |
+
"eval_f1": 0.3108974358974359,
|
| 226 |
+
"eval_loss": 0.9797441959381104,
|
| 227 |
+
"eval_runtime": 1.9281,
|
| 228 |
+
"eval_samples_per_second": 32.157,
|
| 229 |
+
"eval_steps_per_second": 2.075,
|
| 230 |
+
"step": 13
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.75,
|
| 234 |
+
"grad_norm": 8.349448204040527,
|
| 235 |
+
"learning_rate": 4.230769230769231e-05,
|
| 236 |
+
"loss": 0.9684,
|
| 237 |
+
"step": 14
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.75,
|
| 241 |
+
"eval_accuracy": 0.46774193548387094,
|
| 242 |
+
"eval_f1": 0.2941421721909527,
|
| 243 |
+
"eval_loss": 0.9708881974220276,
|
| 244 |
+
"eval_runtime": 1.9314,
|
| 245 |
+
"eval_samples_per_second": 32.1,
|
| 246 |
+
"eval_steps_per_second": 2.071,
|
| 247 |
+
"step": 14
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.875,
|
| 251 |
+
"grad_norm": 4.90641975402832,
|
| 252 |
+
"learning_rate": 4.166666666666667e-05,
|
| 253 |
+
"loss": 0.9342,
|
| 254 |
+
"step": 15
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.875,
|
| 258 |
+
"eval_accuracy": 0.4838709677419355,
|
| 259 |
+
"eval_f1": 0.31024531024531027,
|
| 260 |
+
"eval_loss": 0.9690807461738586,
|
| 261 |
+
"eval_runtime": 1.8766,
|
| 262 |
+
"eval_samples_per_second": 33.038,
|
| 263 |
+
"eval_steps_per_second": 2.131,
|
| 264 |
+
"step": 15
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.0,
|
| 268 |
+
"grad_norm": 9.04134750366211,
|
| 269 |
+
"learning_rate": 4.1025641025641023e-05,
|
| 270 |
+
"loss": 0.7387,
|
| 271 |
+
"step": 16
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.0,
|
| 275 |
+
"eval_accuracy": 0.4838709677419355,
|
| 276 |
+
"eval_f1": 0.31024531024531027,
|
| 277 |
+
"eval_loss": 0.9698801636695862,
|
| 278 |
+
"eval_runtime": 1.8773,
|
| 279 |
+
"eval_samples_per_second": 33.026,
|
| 280 |
+
"eval_steps_per_second": 2.131,
|
| 281 |
+
"step": 16
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.125,
|
| 285 |
+
"grad_norm": 5.919072151184082,
|
| 286 |
+
"learning_rate": 4.038461538461539e-05,
|
| 287 |
+
"loss": 0.8603,
|
| 288 |
+
"step": 17
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.125,
|
| 292 |
+
"eval_accuracy": 0.4838709677419355,
|
| 293 |
+
"eval_f1": 0.30253164556962026,
|
| 294 |
+
"eval_loss": 0.9661668539047241,
|
| 295 |
+
"eval_runtime": 1.928,
|
| 296 |
+
"eval_samples_per_second": 32.158,
|
| 297 |
+
"eval_steps_per_second": 2.075,
|
| 298 |
+
"step": 17
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.25,
|
| 302 |
+
"grad_norm": 7.429778575897217,
|
| 303 |
+
"learning_rate": 3.974358974358974e-05,
|
| 304 |
+
"loss": 0.8114,
|
| 305 |
+
"step": 18
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.25,
|
| 309 |
+
"eval_accuracy": 0.5,
|
| 310 |
+
"eval_f1": 0.3189493433395872,
|
| 311 |
+
"eval_loss": 0.9636289477348328,
|
| 312 |
+
"eval_runtime": 1.9287,
|
| 313 |
+
"eval_samples_per_second": 32.145,
|
| 314 |
+
"eval_steps_per_second": 2.074,
|
| 315 |
+
"step": 18
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.375,
|
| 319 |
+
"grad_norm": 6.09760046005249,
|
| 320 |
+
"learning_rate": 3.9102564102564105e-05,
|
| 321 |
+
"loss": 0.9508,
|
| 322 |
+
"step": 19
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.375,
|
| 326 |
+
"eval_accuracy": 0.5,
|
| 327 |
+
"eval_f1": 0.3189493433395872,
|
| 328 |
+
"eval_loss": 0.9564090967178345,
|
| 329 |
+
"eval_runtime": 1.8792,
|
| 330 |
+
"eval_samples_per_second": 32.992,
|
| 331 |
+
"eval_steps_per_second": 2.129,
|
| 332 |
+
"step": 19
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.5,
|
| 336 |
+
"grad_norm": 4.588860988616943,
|
| 337 |
+
"learning_rate": 3.846153846153846e-05,
|
| 338 |
+
"loss": 0.7554,
|
| 339 |
+
"step": 20
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.5,
|
| 343 |
+
"eval_accuracy": 0.5161290322580645,
|
| 344 |
+
"eval_f1": 0.33455732354141166,
|
| 345 |
+
"eval_loss": 0.9543712735176086,
|
| 346 |
+
"eval_runtime": 1.9285,
|
| 347 |
+
"eval_samples_per_second": 32.15,
|
| 348 |
+
"eval_steps_per_second": 2.074,
|
| 349 |
+
"step": 20
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.625,
|
| 353 |
+
"grad_norm": 4.015089988708496,
|
| 354 |
+
"learning_rate": 3.782051282051282e-05,
|
| 355 |
+
"loss": 0.8772,
|
| 356 |
+
"step": 21
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.625,
|
| 360 |
+
"eval_accuracy": 0.5483870967741935,
|
| 361 |
+
"eval_f1": 0.36436436436436437,
|
| 362 |
+
"eval_loss": 0.9526702165603638,
|
| 363 |
+
"eval_runtime": 1.9277,
|
| 364 |
+
"eval_samples_per_second": 32.162,
|
| 365 |
+
"eval_steps_per_second": 2.075,
|
| 366 |
+
"step": 21
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.75,
|
| 370 |
+
"grad_norm": 7.522365570068359,
|
| 371 |
+
"learning_rate": 3.717948717948718e-05,
|
| 372 |
+
"loss": 0.848,
|
| 373 |
+
"step": 22
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.75,
|
| 377 |
+
"eval_accuracy": 0.5806451612903226,
|
| 378 |
+
"eval_f1": 0.3924349881796691,
|
| 379 |
+
"eval_loss": 0.9473089575767517,
|
| 380 |
+
"eval_runtime": 1.927,
|
| 381 |
+
"eval_samples_per_second": 32.175,
|
| 382 |
+
"eval_steps_per_second": 2.076,
|
| 383 |
+
"step": 22
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.875,
|
| 387 |
+
"grad_norm": 10.20969295501709,
|
| 388 |
+
"learning_rate": 3.653846153846154e-05,
|
| 389 |
+
"loss": 0.6632,
|
| 390 |
+
"step": 23
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.875,
|
| 394 |
+
"eval_accuracy": 0.6451612903225806,
|
| 395 |
+
"eval_f1": 0.4470854555744199,
|
| 396 |
+
"eval_loss": 0.9435995817184448,
|
| 397 |
+
"eval_runtime": 1.9274,
|
| 398 |
+
"eval_samples_per_second": 32.168,
|
| 399 |
+
"eval_steps_per_second": 2.075,
|
| 400 |
+
"step": 23
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.0,
|
| 404 |
+
"grad_norm": 4.576776027679443,
|
| 405 |
+
"learning_rate": 3.58974358974359e-05,
|
| 406 |
+
"loss": 0.7259,
|
| 407 |
+
"step": 24
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.0,
|
| 411 |
+
"eval_accuracy": 0.6774193548387096,
|
| 412 |
+
"eval_f1": 0.47088750706613897,
|
| 413 |
+
"eval_loss": 0.9455369710922241,
|
| 414 |
+
"eval_runtime": 1.9275,
|
| 415 |
+
"eval_samples_per_second": 32.166,
|
| 416 |
+
"eval_steps_per_second": 2.075,
|
| 417 |
+
"step": 24
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.125,
|
| 421 |
+
"grad_norm": 8.878484725952148,
|
| 422 |
+
"learning_rate": 3.525641025641026e-05,
|
| 423 |
+
"loss": 0.7974,
|
| 424 |
+
"step": 25
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 3.125,
|
| 428 |
+
"eval_accuracy": 0.6935483870967742,
|
| 429 |
+
"eval_f1": 0.48200757575757575,
|
| 430 |
+
"eval_loss": 0.9411699771881104,
|
| 431 |
+
"eval_runtime": 1.9284,
|
| 432 |
+
"eval_samples_per_second": 32.151,
|
| 433 |
+
"eval_steps_per_second": 2.074,
|
| 434 |
+
"step": 25
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.25,
|
| 438 |
+
"grad_norm": 7.3488450050354,
|
| 439 |
+
"learning_rate": 3.461538461538462e-05,
|
| 440 |
+
"loss": 0.7728,
|
| 441 |
+
"step": 26
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.25,
|
| 445 |
+
"eval_accuracy": 0.6612903225806451,
|
| 446 |
+
"eval_f1": 0.45350669818754924,
|
| 447 |
+
"eval_loss": 0.9431821703910828,
|
| 448 |
+
"eval_runtime": 1.928,
|
| 449 |
+
"eval_samples_per_second": 32.157,
|
| 450 |
+
"eval_steps_per_second": 2.075,
|
| 451 |
+
"step": 26
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 3.375,
|
| 455 |
+
"grad_norm": 4.182816028594971,
|
| 456 |
+
"learning_rate": 3.397435897435898e-05,
|
| 457 |
+
"loss": 0.9005,
|
| 458 |
+
"step": 27
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.375,
|
| 462 |
+
"eval_accuracy": 0.5806451612903226,
|
| 463 |
+
"eval_f1": 0.3848238482384824,
|
| 464 |
+
"eval_loss": 0.9425324201583862,
|
| 465 |
+
"eval_runtime": 1.9307,
|
| 466 |
+
"eval_samples_per_second": 32.112,
|
| 467 |
+
"eval_steps_per_second": 2.072,
|
| 468 |
+
"step": 27
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 3.5,
|
| 472 |
+
"grad_norm": 6.473806858062744,
|
| 473 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 474 |
+
"loss": 0.8324,
|
| 475 |
+
"step": 28
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 3.5,
|
| 479 |
+
"eval_accuracy": 0.5483870967741935,
|
| 480 |
+
"eval_f1": 0.35341880341880344,
|
| 481 |
+
"eval_loss": 0.9440051913261414,
|
| 482 |
+
"eval_runtime": 1.9291,
|
| 483 |
+
"eval_samples_per_second": 32.139,
|
| 484 |
+
"eval_steps_per_second": 2.073,
|
| 485 |
+
"step": 28
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 3.625,
|
| 489 |
+
"grad_norm": 7.45881986618042,
|
| 490 |
+
"learning_rate": 3.269230769230769e-05,
|
| 491 |
+
"loss": 0.7577,
|
| 492 |
+
"step": 29
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 3.625,
|
| 496 |
+
"eval_accuracy": 0.532258064516129,
|
| 497 |
+
"eval_f1": 0.33679878709118477,
|
| 498 |
+
"eval_loss": 0.9446666836738586,
|
| 499 |
+
"eval_runtime": 1.929,
|
| 500 |
+
"eval_samples_per_second": 32.142,
|
| 501 |
+
"eval_steps_per_second": 2.074,
|
| 502 |
+
"step": 29
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 3.75,
|
| 506 |
+
"grad_norm": 5.7591633796691895,
|
| 507 |
+
"learning_rate": 3.205128205128206e-05,
|
| 508 |
+
"loss": 0.7887,
|
| 509 |
+
"step": 30
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 3.75,
|
| 513 |
+
"eval_accuracy": 0.532258064516129,
|
| 514 |
+
"eval_f1": 0.33679878709118477,
|
| 515 |
+
"eval_loss": 0.9500220417976379,
|
| 516 |
+
"eval_runtime": 1.9285,
|
| 517 |
+
"eval_samples_per_second": 32.149,
|
| 518 |
+
"eval_steps_per_second": 2.074,
|
| 519 |
+
"step": 30
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.875,
|
| 523 |
+
"grad_norm": 11.719704627990723,
|
| 524 |
+
"learning_rate": 3.141025641025641e-05,
|
| 525 |
+
"loss": 0.6706,
|
| 526 |
+
"step": 31
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 3.875,
|
| 530 |
+
"eval_accuracy": 0.5806451612903226,
|
| 531 |
+
"eval_f1": 0.38984088127294986,
|
| 532 |
+
"eval_loss": 0.9507701992988586,
|
| 533 |
+
"eval_runtime": 1.9302,
|
| 534 |
+
"eval_samples_per_second": 32.121,
|
| 535 |
+
"eval_steps_per_second": 2.072,
|
| 536 |
+
"step": 31
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 4.0,
|
| 540 |
+
"grad_norm": 6.659142017364502,
|
| 541 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 542 |
+
"loss": 0.7348,
|
| 543 |
+
"step": 32
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 4.0,
|
| 547 |
+
"eval_accuracy": 0.6774193548387096,
|
| 548 |
+
"eval_f1": 0.4682125603864735,
|
| 549 |
+
"eval_loss": 0.9422016739845276,
|
| 550 |
+
"eval_runtime": 1.9309,
|
| 551 |
+
"eval_samples_per_second": 32.109,
|
| 552 |
+
"eval_steps_per_second": 2.072,
|
| 553 |
+
"step": 32
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 4.125,
|
| 557 |
+
"grad_norm": 8.99232006072998,
|
| 558 |
+
"learning_rate": 3.012820512820513e-05,
|
| 559 |
+
"loss": 0.797,
|
| 560 |
+
"step": 33
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.125,
|
| 564 |
+
"eval_accuracy": 0.6774193548387096,
|
| 565 |
+
"eval_f1": 0.46957520091848454,
|
| 566 |
+
"eval_loss": 0.9406993985176086,
|
| 567 |
+
"eval_runtime": 1.8808,
|
| 568 |
+
"eval_samples_per_second": 32.965,
|
| 569 |
+
"eval_steps_per_second": 2.127,
|
| 570 |
+
"step": 33
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 4.25,
|
| 574 |
+
"grad_norm": 15.037948608398438,
|
| 575 |
+
"learning_rate": 2.948717948717949e-05,
|
| 576 |
+
"loss": 0.7472,
|
| 577 |
+
"step": 34
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 4.25,
|
| 581 |
+
"eval_accuracy": 0.6774193548387096,
|
| 582 |
+
"eval_f1": 0.4708994708994709,
|
| 583 |
+
"eval_loss": 0.9398488402366638,
|
| 584 |
+
"eval_runtime": 1.9301,
|
| 585 |
+
"eval_samples_per_second": 32.122,
|
| 586 |
+
"eval_steps_per_second": 2.072,
|
| 587 |
+
"step": 34
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 4.375,
|
| 591 |
+
"grad_norm": 9.858637809753418,
|
| 592 |
+
"learning_rate": 2.8846153846153845e-05,
|
| 593 |
+
"loss": 0.7184,
|
| 594 |
+
"step": 35
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 4.375,
|
| 598 |
+
"eval_accuracy": 0.6612903225806451,
|
| 599 |
+
"eval_f1": 0.45972458026787394,
|
| 600 |
+
"eval_loss": 0.9320343732833862,
|
| 601 |
+
"eval_runtime": 1.9306,
|
| 602 |
+
"eval_samples_per_second": 32.115,
|
| 603 |
+
"eval_steps_per_second": 2.072,
|
| 604 |
+
"step": 35
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 4.5,
|
| 608 |
+
"grad_norm": 9.198653221130371,
|
| 609 |
+
"learning_rate": 2.8205128205128207e-05,
|
| 610 |
+
"loss": 0.8042,
|
| 611 |
+
"step": 36
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 4.5,
|
| 615 |
+
"eval_accuracy": 0.6612903225806451,
|
| 616 |
+
"eval_f1": 0.45972458026787394,
|
| 617 |
+
"eval_loss": 0.9294925928115845,
|
| 618 |
+
"eval_runtime": 1.9308,
|
| 619 |
+
"eval_samples_per_second": 32.111,
|
| 620 |
+
"eval_steps_per_second": 2.072,
|
| 621 |
+
"step": 36
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 4.625,
|
| 625 |
+
"grad_norm": 5.223246097564697,
|
| 626 |
+
"learning_rate": 2.756410256410257e-05,
|
| 627 |
+
"loss": 0.7408,
|
| 628 |
+
"step": 37
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 4.625,
|
| 632 |
+
"eval_accuracy": 0.6774193548387096,
|
| 633 |
+
"eval_f1": 0.4708994708994709,
|
| 634 |
+
"eval_loss": 0.9262655973434448,
|
| 635 |
+
"eval_runtime": 1.9307,
|
| 636 |
+
"eval_samples_per_second": 32.113,
|
| 637 |
+
"eval_steps_per_second": 2.072,
|
| 638 |
+
"step": 37
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.75,
|
| 642 |
+
"grad_norm": 6.609065532684326,
|
| 643 |
+
"learning_rate": 2.6923076923076923e-05,
|
| 644 |
+
"loss": 0.5936,
|
| 645 |
+
"step": 38
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 4.75,
|
| 649 |
+
"eval_accuracy": 0.6935483870967742,
|
| 650 |
+
"eval_f1": 0.48192090395480225,
|
| 651 |
+
"eval_loss": 0.9254209399223328,
|
| 652 |
+
"eval_runtime": 1.9339,
|
| 653 |
+
"eval_samples_per_second": 32.059,
|
| 654 |
+
"eval_steps_per_second": 2.068,
|
| 655 |
+
"step": 38
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 4.875,
|
| 659 |
+
"grad_norm": 6.2056803703308105,
|
| 660 |
+
"learning_rate": 2.6282051282051285e-05,
|
| 661 |
+
"loss": 0.5937,
|
| 662 |
+
"step": 39
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 4.875,
|
| 666 |
+
"eval_accuracy": 0.6935483870967742,
|
| 667 |
+
"eval_f1": 0.48192090395480225,
|
| 668 |
+
"eval_loss": 0.9212784171104431,
|
| 669 |
+
"eval_runtime": 1.9303,
|
| 670 |
+
"eval_samples_per_second": 32.12,
|
| 671 |
+
"eval_steps_per_second": 2.072,
|
| 672 |
+
"step": 39
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 5.0,
|
| 676 |
+
"grad_norm": 4.507566452026367,
|
| 677 |
+
"learning_rate": 2.564102564102564e-05,
|
| 678 |
+
"loss": 0.7497,
|
| 679 |
+
"step": 40
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 5.0,
|
| 683 |
+
"eval_accuracy": 0.6774193548387096,
|
| 684 |
+
"eval_f1": 0.4704331450094162,
|
| 685 |
+
"eval_loss": 0.9186185002326965,
|
| 686 |
+
"eval_runtime": 1.9335,
|
| 687 |
+
"eval_samples_per_second": 32.066,
|
| 688 |
+
"eval_steps_per_second": 2.069,
|
| 689 |
+
"step": 40
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 5.125,
|
| 693 |
+
"grad_norm": 13.483494758605957,
|
| 694 |
+
"learning_rate": 2.5e-05,
|
| 695 |
+
"loss": 1.135,
|
| 696 |
+
"step": 41
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 5.125,
|
| 700 |
+
"eval_accuracy": 0.6774193548387096,
|
| 701 |
+
"eval_f1": 0.4704331450094162,
|
| 702 |
+
"eval_loss": 0.9170433878898621,
|
| 703 |
+
"eval_runtime": 1.9361,
|
| 704 |
+
"eval_samples_per_second": 32.023,
|
| 705 |
+
"eval_steps_per_second": 2.066,
|
| 706 |
+
"step": 41
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 5.25,
|
| 710 |
+
"grad_norm": 8.313968658447266,
|
| 711 |
+
"learning_rate": 2.435897435897436e-05,
|
| 712 |
+
"loss": 0.6677,
|
| 713 |
+
"step": 42
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 5.25,
|
| 717 |
+
"eval_accuracy": 0.6774193548387096,
|
| 718 |
+
"eval_f1": 0.4704331450094162,
|
| 719 |
+
"eval_loss": 0.9127059578895569,
|
| 720 |
+
"eval_runtime": 1.9338,
|
| 721 |
+
"eval_samples_per_second": 32.061,
|
| 722 |
+
"eval_steps_per_second": 2.068,
|
| 723 |
+
"step": 42
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 5.375,
|
| 727 |
+
"grad_norm": 7.541636943817139,
|
| 728 |
+
"learning_rate": 2.3717948717948718e-05,
|
| 729 |
+
"loss": 0.7515,
|
| 730 |
+
"step": 43
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 5.375,
|
| 734 |
+
"eval_accuracy": 0.6774193548387096,
|
| 735 |
+
"eval_f1": 0.4704331450094162,
|
| 736 |
+
"eval_loss": 0.9163720011711121,
|
| 737 |
+
"eval_runtime": 1.9345,
|
| 738 |
+
"eval_samples_per_second": 32.049,
|
| 739 |
+
"eval_steps_per_second": 2.068,
|
| 740 |
+
"step": 43
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 5.5,
|
| 744 |
+
"grad_norm": 9.568167686462402,
|
| 745 |
+
"learning_rate": 2.307692307692308e-05,
|
| 746 |
+
"loss": 0.6488,
|
| 747 |
+
"step": 44
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 5.5,
|
| 751 |
+
"eval_accuracy": 0.6774193548387096,
|
| 752 |
+
"eval_f1": 0.4704331450094162,
|
| 753 |
+
"eval_loss": 0.9121409058570862,
|
| 754 |
+
"eval_runtime": 1.8843,
|
| 755 |
+
"eval_samples_per_second": 32.904,
|
| 756 |
+
"eval_steps_per_second": 2.123,
|
| 757 |
+
"step": 44
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 5.625,
|
| 761 |
+
"grad_norm": 3.9321157932281494,
|
| 762 |
+
"learning_rate": 2.2435897435897437e-05,
|
| 763 |
+
"loss": 0.7113,
|
| 764 |
+
"step": 45
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 5.625,
|
| 768 |
+
"eval_accuracy": 0.6774193548387096,
|
| 769 |
+
"eval_f1": 0.4704331450094162,
|
| 770 |
+
"eval_loss": 0.9119479060173035,
|
| 771 |
+
"eval_runtime": 1.9363,
|
| 772 |
+
"eval_samples_per_second": 32.02,
|
| 773 |
+
"eval_steps_per_second": 2.066,
|
| 774 |
+
"step": 45
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 5.75,
|
| 778 |
+
"grad_norm": 4.554017543792725,
|
| 779 |
+
"learning_rate": 2.1794871794871795e-05,
|
| 780 |
+
"loss": 0.6476,
|
| 781 |
+
"step": 46
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 5.75,
|
| 785 |
+
"eval_accuracy": 0.6935483870967742,
|
| 786 |
+
"eval_f1": 0.48192090395480225,
|
| 787 |
+
"eval_loss": 0.9131627082824707,
|
| 788 |
+
"eval_runtime": 1.8815,
|
| 789 |
+
"eval_samples_per_second": 32.953,
|
| 790 |
+
"eval_steps_per_second": 2.126,
|
| 791 |
+
"step": 46
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 5.875,
|
| 795 |
+
"grad_norm": 4.490871429443359,
|
| 796 |
+
"learning_rate": 2.1153846153846154e-05,
|
| 797 |
+
"loss": 0.5748,
|
| 798 |
+
"step": 47
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 5.875,
|
| 802 |
+
"eval_accuracy": 0.6935483870967742,
|
| 803 |
+
"eval_f1": 0.48192090395480225,
|
| 804 |
+
"eval_loss": 0.9163798689842224,
|
| 805 |
+
"eval_runtime": 1.8811,
|
| 806 |
+
"eval_samples_per_second": 32.959,
|
| 807 |
+
"eval_steps_per_second": 2.126,
|
| 808 |
+
"step": 47
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 6.0,
|
| 812 |
+
"grad_norm": 4.915560722351074,
|
| 813 |
+
"learning_rate": 2.0512820512820512e-05,
|
| 814 |
+
"loss": 0.7456,
|
| 815 |
+
"step": 48
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 6.0,
|
| 819 |
+
"eval_accuracy": 0.6935483870967742,
|
| 820 |
+
"eval_f1": 0.48192090395480225,
|
| 821 |
+
"eval_loss": 0.9137986898422241,
|
| 822 |
+
"eval_runtime": 1.9333,
|
| 823 |
+
"eval_samples_per_second": 32.069,
|
| 824 |
+
"eval_steps_per_second": 2.069,
|
| 825 |
+
"step": 48
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 6.125,
|
| 829 |
+
"grad_norm": 5.666485786437988,
|
| 830 |
+
"learning_rate": 1.987179487179487e-05,
|
| 831 |
+
"loss": 0.7035,
|
| 832 |
+
"step": 49
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 6.125,
|
| 836 |
+
"eval_accuracy": 0.6935483870967742,
|
| 837 |
+
"eval_f1": 0.48192090395480225,
|
| 838 |
+
"eval_loss": 0.9176655411720276,
|
| 839 |
+
"eval_runtime": 1.8845,
|
| 840 |
+
"eval_samples_per_second": 32.9,
|
| 841 |
+
"eval_steps_per_second": 2.123,
|
| 842 |
+
"step": 49
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 6.25,
|
| 846 |
+
"grad_norm": 4.38871431350708,
|
| 847 |
+
"learning_rate": 1.923076923076923e-05,
|
| 848 |
+
"loss": 0.6157,
|
| 849 |
+
"step": 50
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 6.25,
|
| 853 |
+
"eval_accuracy": 0.6935483870967742,
|
| 854 |
+
"eval_f1": 0.48192090395480225,
|
| 855 |
+
"eval_loss": 0.9223140478134155,
|
| 856 |
+
"eval_runtime": 1.8794,
|
| 857 |
+
"eval_samples_per_second": 32.99,
|
| 858 |
+
"eval_steps_per_second": 2.128,
|
| 859 |
+
"step": 50
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 6.375,
|
| 863 |
+
"grad_norm": 11.442863464355469,
|
| 864 |
+
"learning_rate": 1.858974358974359e-05,
|
| 865 |
+
"loss": 0.561,
|
| 866 |
+
"step": 51
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 6.375,
|
| 870 |
+
"eval_accuracy": 0.6935483870967742,
|
| 871 |
+
"eval_f1": 0.48192090395480225,
|
| 872 |
+
"eval_loss": 0.9202437996864319,
|
| 873 |
+
"eval_runtime": 1.9299,
|
| 874 |
+
"eval_samples_per_second": 32.125,
|
| 875 |
+
"eval_steps_per_second": 2.073,
|
| 876 |
+
"step": 51
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 6.5,
|
| 880 |
+
"grad_norm": 7.4318928718566895,
|
| 881 |
+
"learning_rate": 1.794871794871795e-05,
|
| 882 |
+
"loss": 0.7139,
|
| 883 |
+
"step": 52
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 6.5,
|
| 887 |
+
"eval_accuracy": 0.6774193548387096,
|
| 888 |
+
"eval_f1": 0.4704331450094162,
|
| 889 |
+
"eval_loss": 0.9179559350013733,
|
| 890 |
+
"eval_runtime": 1.8777,
|
| 891 |
+
"eval_samples_per_second": 33.02,
|
| 892 |
+
"eval_steps_per_second": 2.13,
|
| 893 |
+
"step": 52
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 6.625,
|
| 897 |
+
"grad_norm": 5.853055477142334,
|
| 898 |
+
"learning_rate": 1.730769230769231e-05,
|
| 899 |
+
"loss": 0.6748,
|
| 900 |
+
"step": 53
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 6.625,
|
| 904 |
+
"eval_accuracy": 0.6774193548387096,
|
| 905 |
+
"eval_f1": 0.4704331450094162,
|
| 906 |
+
"eval_loss": 0.9139246940612793,
|
| 907 |
+
"eval_runtime": 1.9266,
|
| 908 |
+
"eval_samples_per_second": 32.182,
|
| 909 |
+
"eval_steps_per_second": 2.076,
|
| 910 |
+
"step": 53
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 6.75,
|
| 914 |
+
"grad_norm": 5.003907680511475,
|
| 915 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 916 |
+
"loss": 0.5338,
|
| 917 |
+
"step": 54
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 6.75,
|
| 921 |
+
"eval_accuracy": 0.6774193548387096,
|
| 922 |
+
"eval_f1": 0.4704331450094162,
|
| 923 |
+
"eval_loss": 0.9166889786720276,
|
| 924 |
+
"eval_runtime": 1.9286,
|
| 925 |
+
"eval_samples_per_second": 32.148,
|
| 926 |
+
"eval_steps_per_second": 2.074,
|
| 927 |
+
"step": 54
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 6.875,
|
| 931 |
+
"grad_norm": 4.901527404785156,
|
| 932 |
+
"learning_rate": 1.602564102564103e-05,
|
| 933 |
+
"loss": 0.6889,
|
| 934 |
+
"step": 55
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 6.875,
|
| 938 |
+
"eval_accuracy": 0.6774193548387096,
|
| 939 |
+
"eval_f1": 0.4704331450094162,
|
| 940 |
+
"eval_loss": 0.9157655835151672,
|
| 941 |
+
"eval_runtime": 1.9276,
|
| 942 |
+
"eval_samples_per_second": 32.164,
|
| 943 |
+
"eval_steps_per_second": 2.075,
|
| 944 |
+
"step": 55
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 7.0,
|
| 948 |
+
"grad_norm": 5.2783918380737305,
|
| 949 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 950 |
+
"loss": 0.8556,
|
| 951 |
+
"step": 56
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 7.0,
|
| 955 |
+
"eval_accuracy": 0.6774193548387096,
|
| 956 |
+
"eval_f1": 0.4704331450094162,
|
| 957 |
+
"eval_loss": 0.921044647693634,
|
| 958 |
+
"eval_runtime": 1.9306,
|
| 959 |
+
"eval_samples_per_second": 32.115,
|
| 960 |
+
"eval_steps_per_second": 2.072,
|
| 961 |
+
"step": 56
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 7.125,
|
| 965 |
+
"grad_norm": 10.69826602935791,
|
| 966 |
+
"learning_rate": 1.4743589743589745e-05,
|
| 967 |
+
"loss": 0.8448,
|
| 968 |
+
"step": 57
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 7.125,
|
| 972 |
+
"eval_accuracy": 0.6774193548387096,
|
| 973 |
+
"eval_f1": 0.4704331450094162,
|
| 974 |
+
"eval_loss": 0.916961669921875,
|
| 975 |
+
"eval_runtime": 1.9308,
|
| 976 |
+
"eval_samples_per_second": 32.111,
|
| 977 |
+
"eval_steps_per_second": 2.072,
|
| 978 |
+
"step": 57
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 7.25,
|
| 982 |
+
"grad_norm": 6.701515197753906,
|
| 983 |
+
"learning_rate": 1.4102564102564104e-05,
|
| 984 |
+
"loss": 0.6535,
|
| 985 |
+
"step": 58
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 7.25,
|
| 989 |
+
"eval_accuracy": 0.6774193548387096,
|
| 990 |
+
"eval_f1": 0.4704331450094162,
|
| 991 |
+
"eval_loss": 0.9177826642990112,
|
| 992 |
+
"eval_runtime": 1.9295,
|
| 993 |
+
"eval_samples_per_second": 32.133,
|
| 994 |
+
"eval_steps_per_second": 2.073,
|
| 995 |
+
"step": 58
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 7.375,
|
| 999 |
+
"grad_norm": 5.344858646392822,
|
| 1000 |
+
"learning_rate": 1.3461538461538462e-05,
|
| 1001 |
+
"loss": 0.6185,
|
| 1002 |
+
"step": 59
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 7.375,
|
| 1006 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1007 |
+
"eval_f1": 0.4704331450094162,
|
| 1008 |
+
"eval_loss": 0.9164468050003052,
|
| 1009 |
+
"eval_runtime": 1.9345,
|
| 1010 |
+
"eval_samples_per_second": 32.049,
|
| 1011 |
+
"eval_steps_per_second": 2.068,
|
| 1012 |
+
"step": 59
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 7.5,
|
| 1016 |
+
"grad_norm": 5.061964511871338,
|
| 1017 |
+
"learning_rate": 1.282051282051282e-05,
|
| 1018 |
+
"loss": 0.7128,
|
| 1019 |
+
"step": 60
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 7.5,
|
| 1023 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1024 |
+
"eval_f1": 0.4704331450094162,
|
| 1025 |
+
"eval_loss": 0.9154215455055237,
|
| 1026 |
+
"eval_runtime": 1.9313,
|
| 1027 |
+
"eval_samples_per_second": 32.103,
|
| 1028 |
+
"eval_steps_per_second": 2.071,
|
| 1029 |
+
"step": 60
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 7.625,
|
| 1033 |
+
"grad_norm": 6.167932033538818,
|
| 1034 |
+
"learning_rate": 1.217948717948718e-05,
|
| 1035 |
+
"loss": 0.5839,
|
| 1036 |
+
"step": 61
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 7.625,
|
| 1040 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1041 |
+
"eval_f1": 0.4704331450094162,
|
| 1042 |
+
"eval_loss": 0.9095370173454285,
|
| 1043 |
+
"eval_runtime": 1.9307,
|
| 1044 |
+
"eval_samples_per_second": 32.112,
|
| 1045 |
+
"eval_steps_per_second": 2.072,
|
| 1046 |
+
"step": 61
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 7.75,
|
| 1050 |
+
"grad_norm": 2.6592514514923096,
|
| 1051 |
+
"learning_rate": 1.153846153846154e-05,
|
| 1052 |
+
"loss": 0.5118,
|
| 1053 |
+
"step": 62
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 7.75,
|
| 1057 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1058 |
+
"eval_f1": 0.4704331450094162,
|
| 1059 |
+
"eval_loss": 0.9109383821487427,
|
| 1060 |
+
"eval_runtime": 1.9289,
|
| 1061 |
+
"eval_samples_per_second": 32.143,
|
| 1062 |
+
"eval_steps_per_second": 2.074,
|
| 1063 |
+
"step": 62
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 7.875,
|
| 1067 |
+
"grad_norm": 10.835193634033203,
|
| 1068 |
+
"learning_rate": 1.0897435897435898e-05,
|
| 1069 |
+
"loss": 0.6146,
|
| 1070 |
+
"step": 63
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 7.875,
|
| 1074 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1075 |
+
"eval_f1": 0.4704331450094162,
|
| 1076 |
+
"eval_loss": 0.9067746996879578,
|
| 1077 |
+
"eval_runtime": 1.9278,
|
| 1078 |
+
"eval_samples_per_second": 32.161,
|
| 1079 |
+
"eval_steps_per_second": 2.075,
|
| 1080 |
+
"step": 63
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 8.0,
|
| 1084 |
+
"grad_norm": 11.179938316345215,
|
| 1085 |
+
"learning_rate": 1.0256410256410256e-05,
|
| 1086 |
+
"loss": 0.9724,
|
| 1087 |
+
"step": 64
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 8.0,
|
| 1091 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1092 |
+
"eval_f1": 0.4704331450094162,
|
| 1093 |
+
"eval_loss": 0.9018973112106323,
|
| 1094 |
+
"eval_runtime": 1.9274,
|
| 1095 |
+
"eval_samples_per_second": 32.168,
|
| 1096 |
+
"eval_steps_per_second": 2.075,
|
| 1097 |
+
"step": 64
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 8.125,
|
| 1101 |
+
"grad_norm": 6.455613136291504,
|
| 1102 |
+
"learning_rate": 9.615384615384616e-06,
|
| 1103 |
+
"loss": 0.6459,
|
| 1104 |
+
"step": 65
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 8.125,
|
| 1108 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1109 |
+
"eval_f1": 0.4704331450094162,
|
| 1110 |
+
"eval_loss": 0.9056165218353271,
|
| 1111 |
+
"eval_runtime": 1.9292,
|
| 1112 |
+
"eval_samples_per_second": 32.138,
|
| 1113 |
+
"eval_steps_per_second": 2.073,
|
| 1114 |
+
"step": 65
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 8.25,
|
| 1118 |
+
"grad_norm": 7.206265449523926,
|
| 1119 |
+
"learning_rate": 8.974358974358976e-06,
|
| 1120 |
+
"loss": 0.7838,
|
| 1121 |
+
"step": 66
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 8.25,
|
| 1125 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1126 |
+
"eval_f1": 0.4595103578154425,
|
| 1127 |
+
"eval_loss": 0.909091591835022,
|
| 1128 |
+
"eval_runtime": 1.9295,
|
| 1129 |
+
"eval_samples_per_second": 32.132,
|
| 1130 |
+
"eval_steps_per_second": 2.073,
|
| 1131 |
+
"step": 66
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 8.375,
|
| 1135 |
+
"grad_norm": 5.377885341644287,
|
| 1136 |
+
"learning_rate": 8.333333333333334e-06,
|
| 1137 |
+
"loss": 0.7472,
|
| 1138 |
+
"step": 67
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 8.375,
|
| 1142 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1143 |
+
"eval_f1": 0.4704331450094162,
|
| 1144 |
+
"eval_loss": 0.9005382657051086,
|
| 1145 |
+
"eval_runtime": 1.8794,
|
| 1146 |
+
"eval_samples_per_second": 32.99,
|
| 1147 |
+
"eval_steps_per_second": 2.128,
|
| 1148 |
+
"step": 67
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 8.5,
|
| 1152 |
+
"grad_norm": 5.025684356689453,
|
| 1153 |
+
"learning_rate": 7.692307692307694e-06,
|
| 1154 |
+
"loss": 0.4137,
|
| 1155 |
+
"step": 68
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 8.5,
|
| 1159 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1160 |
+
"eval_f1": 0.4704331450094162,
|
| 1161 |
+
"eval_loss": 0.9060821533203125,
|
| 1162 |
+
"eval_runtime": 1.8832,
|
| 1163 |
+
"eval_samples_per_second": 32.923,
|
| 1164 |
+
"eval_steps_per_second": 2.124,
|
| 1165 |
+
"step": 68
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 8.625,
|
| 1169 |
+
"grad_norm": 6.750956058502197,
|
| 1170 |
+
"learning_rate": 7.051282051282052e-06,
|
| 1171 |
+
"loss": 0.5145,
|
| 1172 |
+
"step": 69
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 8.625,
|
| 1176 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1177 |
+
"eval_f1": 0.4704331450094162,
|
| 1178 |
+
"eval_loss": 0.8989046216011047,
|
| 1179 |
+
"eval_runtime": 1.9282,
|
| 1180 |
+
"eval_samples_per_second": 32.155,
|
| 1181 |
+
"eval_steps_per_second": 2.075,
|
| 1182 |
+
"step": 69
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 8.75,
|
| 1186 |
+
"grad_norm": 5.707816123962402,
|
| 1187 |
+
"learning_rate": 6.41025641025641e-06,
|
| 1188 |
+
"loss": 0.7129,
|
| 1189 |
+
"step": 70
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 8.75,
|
| 1193 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1194 |
+
"eval_f1": 0.4595103578154425,
|
| 1195 |
+
"eval_loss": 0.8961211442947388,
|
| 1196 |
+
"eval_runtime": 1.929,
|
| 1197 |
+
"eval_samples_per_second": 32.14,
|
| 1198 |
+
"eval_steps_per_second": 2.074,
|
| 1199 |
+
"step": 70
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 8.875,
|
| 1203 |
+
"grad_norm": 3.8523380756378174,
|
| 1204 |
+
"learning_rate": 5.76923076923077e-06,
|
| 1205 |
+
"loss": 0.554,
|
| 1206 |
+
"step": 71
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 8.875,
|
| 1210 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1211 |
+
"eval_f1": 0.4595103578154425,
|
| 1212 |
+
"eval_loss": 0.8937899470329285,
|
| 1213 |
+
"eval_runtime": 1.9304,
|
| 1214 |
+
"eval_samples_per_second": 32.117,
|
| 1215 |
+
"eval_steps_per_second": 2.072,
|
| 1216 |
+
"step": 71
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 9.0,
|
| 1220 |
+
"grad_norm": 7.517840385437012,
|
| 1221 |
+
"learning_rate": 5.128205128205128e-06,
|
| 1222 |
+
"loss": 0.7014,
|
| 1223 |
+
"step": 72
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 9.0,
|
| 1227 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1228 |
+
"eval_f1": 0.4595103578154425,
|
| 1229 |
+
"eval_loss": 0.9007149934768677,
|
| 1230 |
+
"eval_runtime": 1.9291,
|
| 1231 |
+
"eval_samples_per_second": 32.139,
|
| 1232 |
+
"eval_steps_per_second": 2.073,
|
| 1233 |
+
"step": 72
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 9.125,
|
| 1237 |
+
"grad_norm": 7.3192362785339355,
|
| 1238 |
+
"learning_rate": 4.487179487179488e-06,
|
| 1239 |
+
"loss": 0.7076,
|
| 1240 |
+
"step": 73
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 9.125,
|
| 1244 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1245 |
+
"eval_f1": 0.4595103578154425,
|
| 1246 |
+
"eval_loss": 0.8964553475379944,
|
| 1247 |
+
"eval_runtime": 1.9292,
|
| 1248 |
+
"eval_samples_per_second": 32.137,
|
| 1249 |
+
"eval_steps_per_second": 2.073,
|
| 1250 |
+
"step": 73
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 9.25,
|
| 1254 |
+
"grad_norm": 6.544466495513916,
|
| 1255 |
+
"learning_rate": 3.846153846153847e-06,
|
| 1256 |
+
"loss": 0.6754,
|
| 1257 |
+
"step": 74
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 9.25,
|
| 1261 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1262 |
+
"eval_f1": 0.4704331450094162,
|
| 1263 |
+
"eval_loss": 0.9004920125007629,
|
| 1264 |
+
"eval_runtime": 1.9283,
|
| 1265 |
+
"eval_samples_per_second": 32.153,
|
| 1266 |
+
"eval_steps_per_second": 2.074,
|
| 1267 |
+
"step": 74
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 9.375,
|
| 1271 |
+
"grad_norm": 5.344063758850098,
|
| 1272 |
+
"learning_rate": 3.205128205128205e-06,
|
| 1273 |
+
"loss": 0.591,
|
| 1274 |
+
"step": 75
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 9.375,
|
| 1278 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1279 |
+
"eval_f1": 0.4595103578154425,
|
| 1280 |
+
"eval_loss": 0.8975746631622314,
|
| 1281 |
+
"eval_runtime": 1.8785,
|
| 1282 |
+
"eval_samples_per_second": 33.006,
|
| 1283 |
+
"eval_steps_per_second": 2.129,
|
| 1284 |
+
"step": 75
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 9.5,
|
| 1288 |
+
"grad_norm": 7.665821075439453,
|
| 1289 |
+
"learning_rate": 2.564102564102564e-06,
|
| 1290 |
+
"loss": 0.6753,
|
| 1291 |
+
"step": 76
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 9.5,
|
| 1295 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1296 |
+
"eval_f1": 0.4595103578154425,
|
| 1297 |
+
"eval_loss": 0.8977981209754944,
|
| 1298 |
+
"eval_runtime": 1.9303,
|
| 1299 |
+
"eval_samples_per_second": 32.119,
|
| 1300 |
+
"eval_steps_per_second": 2.072,
|
| 1301 |
+
"step": 76
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 9.625,
|
| 1305 |
+
"grad_norm": 6.320114612579346,
|
| 1306 |
+
"learning_rate": 1.9230769230769234e-06,
|
| 1307 |
+
"loss": 0.6099,
|
| 1308 |
+
"step": 77
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 9.625,
|
| 1312 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1313 |
+
"eval_f1": 0.4595103578154425,
|
| 1314 |
+
"eval_loss": 0.8969810009002686,
|
| 1315 |
+
"eval_runtime": 1.9299,
|
| 1316 |
+
"eval_samples_per_second": 32.126,
|
| 1317 |
+
"eval_steps_per_second": 2.073,
|
| 1318 |
+
"step": 77
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 9.75,
|
| 1322 |
+
"grad_norm": 7.137789249420166,
|
| 1323 |
+
"learning_rate": 1.282051282051282e-06,
|
| 1324 |
+
"loss": 0.7863,
|
| 1325 |
+
"step": 78
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 9.75,
|
| 1329 |
+
"eval_accuracy": 0.6774193548387096,
|
| 1330 |
+
"eval_f1": 0.4704331450094162,
|
| 1331 |
+
"eval_loss": 0.8956599235534668,
|
| 1332 |
+
"eval_runtime": 1.9278,
|
| 1333 |
+
"eval_samples_per_second": 32.161,
|
| 1334 |
+
"eval_steps_per_second": 2.075,
|
| 1335 |
+
"step": 78
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 9.875,
|
| 1339 |
+
"grad_norm": 5.855066299438477,
|
| 1340 |
+
"learning_rate": 6.41025641025641e-07,
|
| 1341 |
+
"loss": 0.5154,
|
| 1342 |
+
"step": 79
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 9.875,
|
| 1346 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1347 |
+
"eval_f1": 0.4595103578154425,
|
| 1348 |
+
"eval_loss": 0.8908558487892151,
|
| 1349 |
+
"eval_runtime": 1.8786,
|
| 1350 |
+
"eval_samples_per_second": 33.003,
|
| 1351 |
+
"eval_steps_per_second": 2.129,
|
| 1352 |
+
"step": 79
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 10.0,
|
| 1356 |
+
"grad_norm": 6.291125774383545,
|
| 1357 |
+
"learning_rate": 0.0,
|
| 1358 |
+
"loss": 0.6067,
|
| 1359 |
+
"step": 80
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 10.0,
|
| 1363 |
+
"eval_accuracy": 0.6612903225806451,
|
| 1364 |
+
"eval_f1": 0.4595103578154425,
|
| 1365 |
+
"eval_loss": 0.8924511075019836,
|
| 1366 |
+
"eval_runtime": 1.9287,
|
| 1367 |
+
"eval_samples_per_second": 32.145,
|
| 1368 |
+
"eval_steps_per_second": 2.074,
|
| 1369 |
+
"step": 80
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 10.0,
|
| 1373 |
+
"step": 80,
|
| 1374 |
+
"total_flos": 1.4174270632493056e+16,
|
| 1375 |
+
"train_loss": 0.7646934121847153,
|
| 1376 |
+
"train_runtime": 412.0561,
|
| 1377 |
+
"train_samples_per_second": 5.922,
|
| 1378 |
+
"train_steps_per_second": 0.194
|
| 1379 |
+
}
|
| 1380 |
+
],
|
| 1381 |
+
"logging_steps": 1,
|
| 1382 |
+
"max_steps": 80,
|
| 1383 |
+
"num_input_tokens_seen": 0,
|
| 1384 |
+
"num_train_epochs": 10,
|
| 1385 |
+
"save_steps": 500,
|
| 1386 |
+
"total_flos": 1.4174270632493056e+16,
|
| 1387 |
+
"train_batch_size": 4,
|
| 1388 |
+
"trial_name": null,
|
| 1389 |
+
"trial_params": null
|
| 1390 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b25a182e2d63f34aa9fe3c66636911fdde746bf2834712f7d5e99f563967a642
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|