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-wsc-sequence_classification.json +1150 -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 sha256:4db410d80b7bce70ebcb4d615cf2c80e528d6ad76af0252cf9a32378779d9343
|
| 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-wsc-sequence_classification.json
ADDED
|
@@ -0,0 +1,1150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 70,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14285714285714285,
|
| 13 |
+
"grad_norm": 30.89147186279297,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 1.1486,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.14285714285714285,
|
| 20 |
+
"eval_accuracy": 0.3712121212121212,
|
| 21 |
+
"eval_loss": 1.3744148015975952,
|
| 22 |
+
"eval_runtime": 1.5448,
|
| 23 |
+
"eval_samples_per_second": 85.447,
|
| 24 |
+
"eval_steps_per_second": 2.589,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.2857142857142857,
|
| 29 |
+
"grad_norm": 34.26921081542969,
|
| 30 |
+
"learning_rate": 5e-05,
|
| 31 |
+
"loss": 1.2255,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.2857142857142857,
|
| 36 |
+
"eval_accuracy": 0.3787878787878788,
|
| 37 |
+
"eval_loss": 1.354632019996643,
|
| 38 |
+
"eval_runtime": 1.4924,
|
| 39 |
+
"eval_samples_per_second": 88.447,
|
| 40 |
+
"eval_steps_per_second": 2.68,
|
| 41 |
+
"step": 2
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.42857142857142855,
|
| 45 |
+
"grad_norm": 33.26761245727539,
|
| 46 |
+
"learning_rate": 4.9264705882352944e-05,
|
| 47 |
+
"loss": 1.2041,
|
| 48 |
+
"step": 3
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.42857142857142855,
|
| 52 |
+
"eval_accuracy": 0.3787878787878788,
|
| 53 |
+
"eval_loss": 1.2853270769119263,
|
| 54 |
+
"eval_runtime": 1.4949,
|
| 55 |
+
"eval_samples_per_second": 88.301,
|
| 56 |
+
"eval_steps_per_second": 2.676,
|
| 57 |
+
"step": 3
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.5714285714285714,
|
| 61 |
+
"grad_norm": 34.27346420288086,
|
| 62 |
+
"learning_rate": 4.8529411764705885e-05,
|
| 63 |
+
"loss": 1.1975,
|
| 64 |
+
"step": 4
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.5714285714285714,
|
| 68 |
+
"eval_accuracy": 0.3787878787878788,
|
| 69 |
+
"eval_loss": 1.2138265371322632,
|
| 70 |
+
"eval_runtime": 1.4955,
|
| 71 |
+
"eval_samples_per_second": 88.263,
|
| 72 |
+
"eval_steps_per_second": 2.675,
|
| 73 |
+
"step": 4
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.7142857142857143,
|
| 77 |
+
"grad_norm": 26.523130416870117,
|
| 78 |
+
"learning_rate": 4.7794117647058826e-05,
|
| 79 |
+
"loss": 1.012,
|
| 80 |
+
"step": 5
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.7142857142857143,
|
| 84 |
+
"eval_accuracy": 0.4166666666666667,
|
| 85 |
+
"eval_loss": 1.1368831396102905,
|
| 86 |
+
"eval_runtime": 1.5429,
|
| 87 |
+
"eval_samples_per_second": 85.554,
|
| 88 |
+
"eval_steps_per_second": 2.593,
|
| 89 |
+
"step": 5
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.8571428571428571,
|
| 93 |
+
"grad_norm": 26.6580753326416,
|
| 94 |
+
"learning_rate": 4.705882352941177e-05,
|
| 95 |
+
"loss": 0.9865,
|
| 96 |
+
"step": 6
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.8571428571428571,
|
| 100 |
+
"eval_accuracy": 0.4166666666666667,
|
| 101 |
+
"eval_loss": 1.0571379661560059,
|
| 102 |
+
"eval_runtime": 1.5511,
|
| 103 |
+
"eval_samples_per_second": 85.102,
|
| 104 |
+
"eval_steps_per_second": 2.579,
|
| 105 |
+
"step": 6
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.0,
|
| 109 |
+
"grad_norm": 21.781848907470703,
|
| 110 |
+
"learning_rate": 4.632352941176471e-05,
|
| 111 |
+
"loss": 0.8759,
|
| 112 |
+
"step": 7
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.0,
|
| 116 |
+
"eval_accuracy": 0.42424242424242425,
|
| 117 |
+
"eval_loss": 0.9770345687866211,
|
| 118 |
+
"eval_runtime": 1.4987,
|
| 119 |
+
"eval_samples_per_second": 88.077,
|
| 120 |
+
"eval_steps_per_second": 2.669,
|
| 121 |
+
"step": 7
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.1428571428571428,
|
| 125 |
+
"grad_norm": 11.7108154296875,
|
| 126 |
+
"learning_rate": 4.558823529411765e-05,
|
| 127 |
+
"loss": 0.7938,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.1428571428571428,
|
| 132 |
+
"eval_accuracy": 0.42424242424242425,
|
| 133 |
+
"eval_loss": 0.9049923419952393,
|
| 134 |
+
"eval_runtime": 1.4998,
|
| 135 |
+
"eval_samples_per_second": 88.013,
|
| 136 |
+
"eval_steps_per_second": 2.667,
|
| 137 |
+
"step": 8
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.2857142857142856,
|
| 141 |
+
"grad_norm": 14.725457191467285,
|
| 142 |
+
"learning_rate": 4.485294117647059e-05,
|
| 143 |
+
"loss": 0.7778,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.2857142857142856,
|
| 148 |
+
"eval_accuracy": 0.42424242424242425,
|
| 149 |
+
"eval_loss": 0.8363458514213562,
|
| 150 |
+
"eval_runtime": 1.4943,
|
| 151 |
+
"eval_samples_per_second": 88.337,
|
| 152 |
+
"eval_steps_per_second": 2.677,
|
| 153 |
+
"step": 9
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.4285714285714286,
|
| 157 |
+
"grad_norm": 14.5535249710083,
|
| 158 |
+
"learning_rate": 4.411764705882353e-05,
|
| 159 |
+
"loss": 0.7377,
|
| 160 |
+
"step": 10
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.4285714285714286,
|
| 164 |
+
"eval_accuracy": 0.42424242424242425,
|
| 165 |
+
"eval_loss": 0.7730409502983093,
|
| 166 |
+
"eval_runtime": 1.5479,
|
| 167 |
+
"eval_samples_per_second": 85.277,
|
| 168 |
+
"eval_steps_per_second": 2.584,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.5714285714285714,
|
| 173 |
+
"grad_norm": 16.812053680419922,
|
| 174 |
+
"learning_rate": 4.3382352941176474e-05,
|
| 175 |
+
"loss": 0.7563,
|
| 176 |
+
"step": 11
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.5714285714285714,
|
| 180 |
+
"eval_accuracy": 0.42424242424242425,
|
| 181 |
+
"eval_loss": 0.7208273410797119,
|
| 182 |
+
"eval_runtime": 1.5435,
|
| 183 |
+
"eval_samples_per_second": 85.519,
|
| 184 |
+
"eval_steps_per_second": 2.591,
|
| 185 |
+
"step": 11
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.7142857142857144,
|
| 189 |
+
"grad_norm": 10.605402946472168,
|
| 190 |
+
"learning_rate": 4.2647058823529415e-05,
|
| 191 |
+
"loss": 0.755,
|
| 192 |
+
"step": 12
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.7142857142857144,
|
| 196 |
+
"eval_accuracy": 0.5681818181818182,
|
| 197 |
+
"eval_loss": 0.6822857856750488,
|
| 198 |
+
"eval_runtime": 1.5006,
|
| 199 |
+
"eval_samples_per_second": 87.968,
|
| 200 |
+
"eval_steps_per_second": 2.666,
|
| 201 |
+
"step": 12
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.8571428571428572,
|
| 205 |
+
"grad_norm": 5.790449619293213,
|
| 206 |
+
"learning_rate": 4.1911764705882356e-05,
|
| 207 |
+
"loss": 0.7331,
|
| 208 |
+
"step": 13
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.8571428571428572,
|
| 212 |
+
"eval_accuracy": 0.6287878787878788,
|
| 213 |
+
"eval_loss": 0.6623136401176453,
|
| 214 |
+
"eval_runtime": 1.4474,
|
| 215 |
+
"eval_samples_per_second": 91.196,
|
| 216 |
+
"eval_steps_per_second": 2.764,
|
| 217 |
+
"step": 13
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.0,
|
| 221 |
+
"grad_norm": 7.441537857055664,
|
| 222 |
+
"learning_rate": 4.11764705882353e-05,
|
| 223 |
+
"loss": 0.774,
|
| 224 |
+
"step": 14
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.0,
|
| 228 |
+
"eval_accuracy": 0.6287878787878788,
|
| 229 |
+
"eval_loss": 0.6604166626930237,
|
| 230 |
+
"eval_runtime": 1.5501,
|
| 231 |
+
"eval_samples_per_second": 85.155,
|
| 232 |
+
"eval_steps_per_second": 2.58,
|
| 233 |
+
"step": 14
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.142857142857143,
|
| 237 |
+
"grad_norm": 2.9518423080444336,
|
| 238 |
+
"learning_rate": 4.044117647058824e-05,
|
| 239 |
+
"loss": 0.6674,
|
| 240 |
+
"step": 15
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.142857142857143,
|
| 244 |
+
"eval_accuracy": 0.5984848484848485,
|
| 245 |
+
"eval_loss": 0.6644145846366882,
|
| 246 |
+
"eval_runtime": 1.498,
|
| 247 |
+
"eval_samples_per_second": 88.118,
|
| 248 |
+
"eval_steps_per_second": 2.67,
|
| 249 |
+
"step": 15
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.2857142857142856,
|
| 253 |
+
"grad_norm": 5.2332682609558105,
|
| 254 |
+
"learning_rate": 3.970588235294117e-05,
|
| 255 |
+
"loss": 0.7251,
|
| 256 |
+
"step": 16
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.2857142857142856,
|
| 260 |
+
"eval_accuracy": 0.5909090909090909,
|
| 261 |
+
"eval_loss": 0.6694009900093079,
|
| 262 |
+
"eval_runtime": 1.5426,
|
| 263 |
+
"eval_samples_per_second": 85.572,
|
| 264 |
+
"eval_steps_per_second": 2.593,
|
| 265 |
+
"step": 16
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.4285714285714284,
|
| 269 |
+
"grad_norm": 15.631101608276367,
|
| 270 |
+
"learning_rate": 3.897058823529412e-05,
|
| 271 |
+
"loss": 0.7931,
|
| 272 |
+
"step": 17
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.4285714285714284,
|
| 276 |
+
"eval_accuracy": 0.5833333333333334,
|
| 277 |
+
"eval_loss": 0.6746625900268555,
|
| 278 |
+
"eval_runtime": 1.5454,
|
| 279 |
+
"eval_samples_per_second": 85.415,
|
| 280 |
+
"eval_steps_per_second": 2.588,
|
| 281 |
+
"step": 17
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.571428571428571,
|
| 285 |
+
"grad_norm": 8.961908340454102,
|
| 286 |
+
"learning_rate": 3.8235294117647055e-05,
|
| 287 |
+
"loss": 0.7463,
|
| 288 |
+
"step": 18
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.571428571428571,
|
| 292 |
+
"eval_accuracy": 0.5757575757575758,
|
| 293 |
+
"eval_loss": 0.683046281337738,
|
| 294 |
+
"eval_runtime": 1.5455,
|
| 295 |
+
"eval_samples_per_second": 85.408,
|
| 296 |
+
"eval_steps_per_second": 2.588,
|
| 297 |
+
"step": 18
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.7142857142857144,
|
| 301 |
+
"grad_norm": 1.4260056018829346,
|
| 302 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 303 |
+
"loss": 0.6853,
|
| 304 |
+
"step": 19
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.7142857142857144,
|
| 308 |
+
"eval_accuracy": 0.5833333333333334,
|
| 309 |
+
"eval_loss": 0.6882531046867371,
|
| 310 |
+
"eval_runtime": 1.4995,
|
| 311 |
+
"eval_samples_per_second": 88.032,
|
| 312 |
+
"eval_steps_per_second": 2.668,
|
| 313 |
+
"step": 19
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.857142857142857,
|
| 317 |
+
"grad_norm": 4.879419326782227,
|
| 318 |
+
"learning_rate": 3.6764705882352945e-05,
|
| 319 |
+
"loss": 0.7112,
|
| 320 |
+
"step": 20
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.857142857142857,
|
| 324 |
+
"eval_accuracy": 0.5833333333333334,
|
| 325 |
+
"eval_loss": 0.6945282816886902,
|
| 326 |
+
"eval_runtime": 1.5509,
|
| 327 |
+
"eval_samples_per_second": 85.109,
|
| 328 |
+
"eval_steps_per_second": 2.579,
|
| 329 |
+
"step": 20
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.0,
|
| 333 |
+
"grad_norm": 2.966745615005493,
|
| 334 |
+
"learning_rate": 3.6029411764705886e-05,
|
| 335 |
+
"loss": 0.7261,
|
| 336 |
+
"step": 21
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 3.0,
|
| 340 |
+
"eval_accuracy": 0.5378787878787878,
|
| 341 |
+
"eval_loss": 0.705810546875,
|
| 342 |
+
"eval_runtime": 1.5516,
|
| 343 |
+
"eval_samples_per_second": 85.075,
|
| 344 |
+
"eval_steps_per_second": 2.578,
|
| 345 |
+
"step": 21
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.142857142857143,
|
| 349 |
+
"grad_norm": 1.4628124237060547,
|
| 350 |
+
"learning_rate": 3.529411764705883e-05,
|
| 351 |
+
"loss": 0.7183,
|
| 352 |
+
"step": 22
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 3.142857142857143,
|
| 356 |
+
"eval_accuracy": 0.5,
|
| 357 |
+
"eval_loss": 0.7155613899230957,
|
| 358 |
+
"eval_runtime": 1.5506,
|
| 359 |
+
"eval_samples_per_second": 85.127,
|
| 360 |
+
"eval_steps_per_second": 2.58,
|
| 361 |
+
"step": 22
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 3.2857142857142856,
|
| 365 |
+
"grad_norm": 2.861602306365967,
|
| 366 |
+
"learning_rate": 3.455882352941177e-05,
|
| 367 |
+
"loss": 0.714,
|
| 368 |
+
"step": 23
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.2857142857142856,
|
| 372 |
+
"eval_accuracy": 0.5303030303030303,
|
| 373 |
+
"eval_loss": 0.7245516777038574,
|
| 374 |
+
"eval_runtime": 1.5005,
|
| 375 |
+
"eval_samples_per_second": 87.969,
|
| 376 |
+
"eval_steps_per_second": 2.666,
|
| 377 |
+
"step": 23
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.4285714285714284,
|
| 381 |
+
"grad_norm": 5.409416675567627,
|
| 382 |
+
"learning_rate": 3.382352941176471e-05,
|
| 383 |
+
"loss": 0.7123,
|
| 384 |
+
"step": 24
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.4285714285714284,
|
| 388 |
+
"eval_accuracy": 0.48484848484848486,
|
| 389 |
+
"eval_loss": 0.7311227321624756,
|
| 390 |
+
"eval_runtime": 1.5492,
|
| 391 |
+
"eval_samples_per_second": 85.203,
|
| 392 |
+
"eval_steps_per_second": 2.582,
|
| 393 |
+
"step": 24
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.571428571428571,
|
| 397 |
+
"grad_norm": 5.741272926330566,
|
| 398 |
+
"learning_rate": 3.308823529411765e-05,
|
| 399 |
+
"loss": 0.7952,
|
| 400 |
+
"step": 25
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.571428571428571,
|
| 404 |
+
"eval_accuracy": 0.4696969696969697,
|
| 405 |
+
"eval_loss": 0.7317812442779541,
|
| 406 |
+
"eval_runtime": 1.4986,
|
| 407 |
+
"eval_samples_per_second": 88.082,
|
| 408 |
+
"eval_steps_per_second": 2.669,
|
| 409 |
+
"step": 25
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 3.7142857142857144,
|
| 413 |
+
"grad_norm": 4.539316177368164,
|
| 414 |
+
"learning_rate": 3.235294117647059e-05,
|
| 415 |
+
"loss": 0.6719,
|
| 416 |
+
"step": 26
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.7142857142857144,
|
| 420 |
+
"eval_accuracy": 0.44696969696969696,
|
| 421 |
+
"eval_loss": 0.7320696711540222,
|
| 422 |
+
"eval_runtime": 1.5498,
|
| 423 |
+
"eval_samples_per_second": 85.173,
|
| 424 |
+
"eval_steps_per_second": 2.581,
|
| 425 |
+
"step": 26
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.857142857142857,
|
| 429 |
+
"grad_norm": 5.660553932189941,
|
| 430 |
+
"learning_rate": 3.161764705882353e-05,
|
| 431 |
+
"loss": 0.6752,
|
| 432 |
+
"step": 27
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.857142857142857,
|
| 436 |
+
"eval_accuracy": 0.4318181818181818,
|
| 437 |
+
"eval_loss": 0.7303592562675476,
|
| 438 |
+
"eval_runtime": 1.4988,
|
| 439 |
+
"eval_samples_per_second": 88.068,
|
| 440 |
+
"eval_steps_per_second": 2.669,
|
| 441 |
+
"step": 27
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.0,
|
| 445 |
+
"grad_norm": 5.854210376739502,
|
| 446 |
+
"learning_rate": 3.0882352941176475e-05,
|
| 447 |
+
"loss": 0.7359,
|
| 448 |
+
"step": 28
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 4.0,
|
| 452 |
+
"eval_accuracy": 0.4621212121212121,
|
| 453 |
+
"eval_loss": 0.7259455323219299,
|
| 454 |
+
"eval_runtime": 1.5005,
|
| 455 |
+
"eval_samples_per_second": 87.973,
|
| 456 |
+
"eval_steps_per_second": 2.666,
|
| 457 |
+
"step": 28
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 4.142857142857143,
|
| 461 |
+
"grad_norm": 5.565073490142822,
|
| 462 |
+
"learning_rate": 3.0147058823529413e-05,
|
| 463 |
+
"loss": 0.7201,
|
| 464 |
+
"step": 29
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.142857142857143,
|
| 468 |
+
"eval_accuracy": 0.4696969696969697,
|
| 469 |
+
"eval_loss": 0.7197902798652649,
|
| 470 |
+
"eval_runtime": 1.4968,
|
| 471 |
+
"eval_samples_per_second": 88.189,
|
| 472 |
+
"eval_steps_per_second": 2.672,
|
| 473 |
+
"step": 29
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.285714285714286,
|
| 477 |
+
"grad_norm": 7.555918216705322,
|
| 478 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 479 |
+
"loss": 0.7135,
|
| 480 |
+
"step": 30
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 4.285714285714286,
|
| 484 |
+
"eval_accuracy": 0.5227272727272727,
|
| 485 |
+
"eval_loss": 0.7117217183113098,
|
| 486 |
+
"eval_runtime": 1.5427,
|
| 487 |
+
"eval_samples_per_second": 85.563,
|
| 488 |
+
"eval_steps_per_second": 2.593,
|
| 489 |
+
"step": 30
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 4.428571428571429,
|
| 493 |
+
"grad_norm": 3.8518428802490234,
|
| 494 |
+
"learning_rate": 2.8676470588235295e-05,
|
| 495 |
+
"loss": 0.6927,
|
| 496 |
+
"step": 31
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 4.428571428571429,
|
| 500 |
+
"eval_accuracy": 0.5303030303030303,
|
| 501 |
+
"eval_loss": 0.7075935006141663,
|
| 502 |
+
"eval_runtime": 1.4971,
|
| 503 |
+
"eval_samples_per_second": 88.171,
|
| 504 |
+
"eval_steps_per_second": 2.672,
|
| 505 |
+
"step": 31
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 4.571428571428571,
|
| 509 |
+
"grad_norm": 2.8224422931671143,
|
| 510 |
+
"learning_rate": 2.7941176470588236e-05,
|
| 511 |
+
"loss": 0.7018,
|
| 512 |
+
"step": 32
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.571428571428571,
|
| 516 |
+
"eval_accuracy": 0.5,
|
| 517 |
+
"eval_loss": 0.700927734375,
|
| 518 |
+
"eval_runtime": 1.5484,
|
| 519 |
+
"eval_samples_per_second": 85.247,
|
| 520 |
+
"eval_steps_per_second": 2.583,
|
| 521 |
+
"step": 32
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 4.714285714285714,
|
| 525 |
+
"grad_norm": 2.890439033508301,
|
| 526 |
+
"learning_rate": 2.7205882352941174e-05,
|
| 527 |
+
"loss": 0.7398,
|
| 528 |
+
"step": 33
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 4.714285714285714,
|
| 532 |
+
"eval_accuracy": 0.5454545454545454,
|
| 533 |
+
"eval_loss": 0.695911705493927,
|
| 534 |
+
"eval_runtime": 1.5466,
|
| 535 |
+
"eval_samples_per_second": 85.349,
|
| 536 |
+
"eval_steps_per_second": 2.586,
|
| 537 |
+
"step": 33
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.857142857142857,
|
| 541 |
+
"grad_norm": 2.9305408000946045,
|
| 542 |
+
"learning_rate": 2.647058823529412e-05,
|
| 543 |
+
"loss": 0.7487,
|
| 544 |
+
"step": 34
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 4.857142857142857,
|
| 548 |
+
"eval_accuracy": 0.5378787878787878,
|
| 549 |
+
"eval_loss": 0.6937810778617859,
|
| 550 |
+
"eval_runtime": 1.5486,
|
| 551 |
+
"eval_samples_per_second": 85.237,
|
| 552 |
+
"eval_steps_per_second": 2.583,
|
| 553 |
+
"step": 34
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 5.0,
|
| 557 |
+
"grad_norm": 3.190406084060669,
|
| 558 |
+
"learning_rate": 2.5735294117647057e-05,
|
| 559 |
+
"loss": 0.7183,
|
| 560 |
+
"step": 35
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 5.0,
|
| 564 |
+
"eval_accuracy": 0.5378787878787878,
|
| 565 |
+
"eval_loss": 0.6898541450500488,
|
| 566 |
+
"eval_runtime": 1.5451,
|
| 567 |
+
"eval_samples_per_second": 85.433,
|
| 568 |
+
"eval_steps_per_second": 2.589,
|
| 569 |
+
"step": 35
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.142857142857143,
|
| 573 |
+
"grad_norm": 4.026767730712891,
|
| 574 |
+
"learning_rate": 2.5e-05,
|
| 575 |
+
"loss": 0.7524,
|
| 576 |
+
"step": 36
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 5.142857142857143,
|
| 580 |
+
"eval_accuracy": 0.5454545454545454,
|
| 581 |
+
"eval_loss": 0.6862215995788574,
|
| 582 |
+
"eval_runtime": 1.5452,
|
| 583 |
+
"eval_samples_per_second": 85.425,
|
| 584 |
+
"eval_steps_per_second": 2.589,
|
| 585 |
+
"step": 36
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 5.285714285714286,
|
| 589 |
+
"grad_norm": 7.148804187774658,
|
| 590 |
+
"learning_rate": 2.4264705882352942e-05,
|
| 591 |
+
"loss": 0.731,
|
| 592 |
+
"step": 37
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 5.285714285714286,
|
| 596 |
+
"eval_accuracy": 0.5606060606060606,
|
| 597 |
+
"eval_loss": 0.6843928098678589,
|
| 598 |
+
"eval_runtime": 1.5499,
|
| 599 |
+
"eval_samples_per_second": 85.166,
|
| 600 |
+
"eval_steps_per_second": 2.581,
|
| 601 |
+
"step": 37
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 5.428571428571429,
|
| 605 |
+
"grad_norm": 6.0132737159729,
|
| 606 |
+
"learning_rate": 2.3529411764705884e-05,
|
| 607 |
+
"loss": 0.7534,
|
| 608 |
+
"step": 38
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 5.428571428571429,
|
| 612 |
+
"eval_accuracy": 0.553030303030303,
|
| 613 |
+
"eval_loss": 0.6832978129386902,
|
| 614 |
+
"eval_runtime": 1.5495,
|
| 615 |
+
"eval_samples_per_second": 85.19,
|
| 616 |
+
"eval_steps_per_second": 2.582,
|
| 617 |
+
"step": 38
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.571428571428571,
|
| 621 |
+
"grad_norm": 2.2362067699432373,
|
| 622 |
+
"learning_rate": 2.2794117647058825e-05,
|
| 623 |
+
"loss": 0.7339,
|
| 624 |
+
"step": 39
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.571428571428571,
|
| 628 |
+
"eval_accuracy": 0.5454545454545454,
|
| 629 |
+
"eval_loss": 0.6838245987892151,
|
| 630 |
+
"eval_runtime": 1.5476,
|
| 631 |
+
"eval_samples_per_second": 85.292,
|
| 632 |
+
"eval_steps_per_second": 2.585,
|
| 633 |
+
"step": 39
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 5.714285714285714,
|
| 637 |
+
"grad_norm": 3.735261917114258,
|
| 638 |
+
"learning_rate": 2.2058823529411766e-05,
|
| 639 |
+
"loss": 0.6537,
|
| 640 |
+
"step": 40
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 5.714285714285714,
|
| 644 |
+
"eval_accuracy": 0.553030303030303,
|
| 645 |
+
"eval_loss": 0.6850881576538086,
|
| 646 |
+
"eval_runtime": 1.5467,
|
| 647 |
+
"eval_samples_per_second": 85.344,
|
| 648 |
+
"eval_steps_per_second": 2.586,
|
| 649 |
+
"step": 40
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 5.857142857142857,
|
| 653 |
+
"grad_norm": 5.130250453948975,
|
| 654 |
+
"learning_rate": 2.1323529411764707e-05,
|
| 655 |
+
"loss": 0.7286,
|
| 656 |
+
"step": 41
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 5.857142857142857,
|
| 660 |
+
"eval_accuracy": 0.5454545454545454,
|
| 661 |
+
"eval_loss": 0.6860766410827637,
|
| 662 |
+
"eval_runtime": 1.5496,
|
| 663 |
+
"eval_samples_per_second": 85.186,
|
| 664 |
+
"eval_steps_per_second": 2.581,
|
| 665 |
+
"step": 41
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 6.0,
|
| 669 |
+
"grad_norm": 2.0442426204681396,
|
| 670 |
+
"learning_rate": 2.058823529411765e-05,
|
| 671 |
+
"loss": 0.7069,
|
| 672 |
+
"step": 42
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 6.0,
|
| 676 |
+
"eval_accuracy": 0.5378787878787878,
|
| 677 |
+
"eval_loss": 0.6856178641319275,
|
| 678 |
+
"eval_runtime": 1.55,
|
| 679 |
+
"eval_samples_per_second": 85.163,
|
| 680 |
+
"eval_steps_per_second": 2.581,
|
| 681 |
+
"step": 42
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.142857142857143,
|
| 685 |
+
"grad_norm": 2.5700104236602783,
|
| 686 |
+
"learning_rate": 1.9852941176470586e-05,
|
| 687 |
+
"loss": 0.724,
|
| 688 |
+
"step": 43
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 6.142857142857143,
|
| 692 |
+
"eval_accuracy": 0.5378787878787878,
|
| 693 |
+
"eval_loss": 0.684641420841217,
|
| 694 |
+
"eval_runtime": 1.548,
|
| 695 |
+
"eval_samples_per_second": 85.27,
|
| 696 |
+
"eval_steps_per_second": 2.584,
|
| 697 |
+
"step": 43
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 6.285714285714286,
|
| 701 |
+
"grad_norm": 7.043388366699219,
|
| 702 |
+
"learning_rate": 1.9117647058823528e-05,
|
| 703 |
+
"loss": 0.7109,
|
| 704 |
+
"step": 44
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 6.285714285714286,
|
| 708 |
+
"eval_accuracy": 0.5378787878787878,
|
| 709 |
+
"eval_loss": 0.6849846243858337,
|
| 710 |
+
"eval_runtime": 1.5478,
|
| 711 |
+
"eval_samples_per_second": 85.281,
|
| 712 |
+
"eval_steps_per_second": 2.584,
|
| 713 |
+
"step": 44
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 6.428571428571429,
|
| 717 |
+
"grad_norm": 3.666529655456543,
|
| 718 |
+
"learning_rate": 1.8382352941176472e-05,
|
| 719 |
+
"loss": 0.6973,
|
| 720 |
+
"step": 45
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 6.428571428571429,
|
| 724 |
+
"eval_accuracy": 0.5303030303030303,
|
| 725 |
+
"eval_loss": 0.6853426694869995,
|
| 726 |
+
"eval_runtime": 1.5469,
|
| 727 |
+
"eval_samples_per_second": 85.333,
|
| 728 |
+
"eval_steps_per_second": 2.586,
|
| 729 |
+
"step": 45
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 6.571428571428571,
|
| 733 |
+
"grad_norm": 3.5915279388427734,
|
| 734 |
+
"learning_rate": 1.7647058823529414e-05,
|
| 735 |
+
"loss": 0.701,
|
| 736 |
+
"step": 46
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 6.571428571428571,
|
| 740 |
+
"eval_accuracy": 0.5227272727272727,
|
| 741 |
+
"eval_loss": 0.6859287023544312,
|
| 742 |
+
"eval_runtime": 1.5453,
|
| 743 |
+
"eval_samples_per_second": 85.419,
|
| 744 |
+
"eval_steps_per_second": 2.588,
|
| 745 |
+
"step": 46
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 6.714285714285714,
|
| 749 |
+
"grad_norm": 6.7808003425598145,
|
| 750 |
+
"learning_rate": 1.6911764705882355e-05,
|
| 751 |
+
"loss": 0.7755,
|
| 752 |
+
"step": 47
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 6.714285714285714,
|
| 756 |
+
"eval_accuracy": 0.5378787878787878,
|
| 757 |
+
"eval_loss": 0.6857155561447144,
|
| 758 |
+
"eval_runtime": 1.5467,
|
| 759 |
+
"eval_samples_per_second": 85.341,
|
| 760 |
+
"eval_steps_per_second": 2.586,
|
| 761 |
+
"step": 47
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 6.857142857142857,
|
| 765 |
+
"grad_norm": 5.13129997253418,
|
| 766 |
+
"learning_rate": 1.6176470588235296e-05,
|
| 767 |
+
"loss": 0.7192,
|
| 768 |
+
"step": 48
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 6.857142857142857,
|
| 772 |
+
"eval_accuracy": 0.5303030303030303,
|
| 773 |
+
"eval_loss": 0.6857806444168091,
|
| 774 |
+
"eval_runtime": 1.5503,
|
| 775 |
+
"eval_samples_per_second": 85.146,
|
| 776 |
+
"eval_steps_per_second": 2.58,
|
| 777 |
+
"step": 48
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 7.0,
|
| 781 |
+
"grad_norm": 2.5239486694335938,
|
| 782 |
+
"learning_rate": 1.5441176470588237e-05,
|
| 783 |
+
"loss": 0.7459,
|
| 784 |
+
"step": 49
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 7.0,
|
| 788 |
+
"eval_accuracy": 0.5303030303030303,
|
| 789 |
+
"eval_loss": 0.68532794713974,
|
| 790 |
+
"eval_runtime": 1.5455,
|
| 791 |
+
"eval_samples_per_second": 85.407,
|
| 792 |
+
"eval_steps_per_second": 2.588,
|
| 793 |
+
"step": 49
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 7.142857142857143,
|
| 797 |
+
"grad_norm": 5.412455081939697,
|
| 798 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 799 |
+
"loss": 0.7348,
|
| 800 |
+
"step": 50
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 7.142857142857143,
|
| 804 |
+
"eval_accuracy": 0.5227272727272727,
|
| 805 |
+
"eval_loss": 0.6866211295127869,
|
| 806 |
+
"eval_runtime": 1.5453,
|
| 807 |
+
"eval_samples_per_second": 85.421,
|
| 808 |
+
"eval_steps_per_second": 2.589,
|
| 809 |
+
"step": 50
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 7.285714285714286,
|
| 813 |
+
"grad_norm": 2.2723119258880615,
|
| 814 |
+
"learning_rate": 1.3970588235294118e-05,
|
| 815 |
+
"loss": 0.7152,
|
| 816 |
+
"step": 51
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 7.285714285714286,
|
| 820 |
+
"eval_accuracy": 0.5681818181818182,
|
| 821 |
+
"eval_loss": 0.687363862991333,
|
| 822 |
+
"eval_runtime": 1.5415,
|
| 823 |
+
"eval_samples_per_second": 85.631,
|
| 824 |
+
"eval_steps_per_second": 2.595,
|
| 825 |
+
"step": 51
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 7.428571428571429,
|
| 829 |
+
"grad_norm": 2.08304762840271,
|
| 830 |
+
"learning_rate": 1.323529411764706e-05,
|
| 831 |
+
"loss": 0.6919,
|
| 832 |
+
"step": 52
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 7.428571428571429,
|
| 836 |
+
"eval_accuracy": 0.5681818181818182,
|
| 837 |
+
"eval_loss": 0.6890033483505249,
|
| 838 |
+
"eval_runtime": 1.5478,
|
| 839 |
+
"eval_samples_per_second": 85.284,
|
| 840 |
+
"eval_steps_per_second": 2.584,
|
| 841 |
+
"step": 52
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 7.571428571428571,
|
| 845 |
+
"grad_norm": 8.980510711669922,
|
| 846 |
+
"learning_rate": 1.25e-05,
|
| 847 |
+
"loss": 0.7328,
|
| 848 |
+
"step": 53
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 7.571428571428571,
|
| 852 |
+
"eval_accuracy": 0.5681818181818182,
|
| 853 |
+
"eval_loss": 0.6898555755615234,
|
| 854 |
+
"eval_runtime": 1.5482,
|
| 855 |
+
"eval_samples_per_second": 85.263,
|
| 856 |
+
"eval_steps_per_second": 2.584,
|
| 857 |
+
"step": 53
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 7.714285714285714,
|
| 861 |
+
"grad_norm": 3.777273416519165,
|
| 862 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 863 |
+
"loss": 0.6631,
|
| 864 |
+
"step": 54
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 7.714285714285714,
|
| 868 |
+
"eval_accuracy": 0.5681818181818182,
|
| 869 |
+
"eval_loss": 0.6898496150970459,
|
| 870 |
+
"eval_runtime": 1.5483,
|
| 871 |
+
"eval_samples_per_second": 85.252,
|
| 872 |
+
"eval_steps_per_second": 2.583,
|
| 873 |
+
"step": 54
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 7.857142857142857,
|
| 877 |
+
"grad_norm": 5.7015204429626465,
|
| 878 |
+
"learning_rate": 1.1029411764705883e-05,
|
| 879 |
+
"loss": 0.7114,
|
| 880 |
+
"step": 55
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 7.857142857142857,
|
| 884 |
+
"eval_accuracy": 0.5606060606060606,
|
| 885 |
+
"eval_loss": 0.6892370581626892,
|
| 886 |
+
"eval_runtime": 1.5489,
|
| 887 |
+
"eval_samples_per_second": 85.22,
|
| 888 |
+
"eval_steps_per_second": 2.582,
|
| 889 |
+
"step": 55
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 8.0,
|
| 893 |
+
"grad_norm": 2.6641385555267334,
|
| 894 |
+
"learning_rate": 1.0294117647058824e-05,
|
| 895 |
+
"loss": 0.7448,
|
| 896 |
+
"step": 56
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 8.0,
|
| 900 |
+
"eval_accuracy": 0.5606060606060606,
|
| 901 |
+
"eval_loss": 0.6905569434165955,
|
| 902 |
+
"eval_runtime": 1.5448,
|
| 903 |
+
"eval_samples_per_second": 85.448,
|
| 904 |
+
"eval_steps_per_second": 2.589,
|
| 905 |
+
"step": 56
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 8.142857142857142,
|
| 909 |
+
"grad_norm": 2.0213890075683594,
|
| 910 |
+
"learning_rate": 9.558823529411764e-06,
|
| 911 |
+
"loss": 0.7065,
|
| 912 |
+
"step": 57
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 8.142857142857142,
|
| 916 |
+
"eval_accuracy": 0.553030303030303,
|
| 917 |
+
"eval_loss": 0.6913914680480957,
|
| 918 |
+
"eval_runtime": 1.5496,
|
| 919 |
+
"eval_samples_per_second": 85.183,
|
| 920 |
+
"eval_steps_per_second": 2.581,
|
| 921 |
+
"step": 57
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 8.285714285714286,
|
| 925 |
+
"grad_norm": 2.5657827854156494,
|
| 926 |
+
"learning_rate": 8.823529411764707e-06,
|
| 927 |
+
"loss": 0.697,
|
| 928 |
+
"step": 58
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 8.285714285714286,
|
| 932 |
+
"eval_accuracy": 0.5606060606060606,
|
| 933 |
+
"eval_loss": 0.691057026386261,
|
| 934 |
+
"eval_runtime": 1.545,
|
| 935 |
+
"eval_samples_per_second": 85.438,
|
| 936 |
+
"eval_steps_per_second": 2.589,
|
| 937 |
+
"step": 58
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 8.428571428571429,
|
| 941 |
+
"grad_norm": 2.7576677799224854,
|
| 942 |
+
"learning_rate": 8.088235294117648e-06,
|
| 943 |
+
"loss": 0.7197,
|
| 944 |
+
"step": 59
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 8.428571428571429,
|
| 948 |
+
"eval_accuracy": 0.5378787878787878,
|
| 949 |
+
"eval_loss": 0.6916370987892151,
|
| 950 |
+
"eval_runtime": 1.5467,
|
| 951 |
+
"eval_samples_per_second": 85.343,
|
| 952 |
+
"eval_steps_per_second": 2.586,
|
| 953 |
+
"step": 59
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 8.571428571428571,
|
| 957 |
+
"grad_norm": 4.963264465332031,
|
| 958 |
+
"learning_rate": 7.3529411764705884e-06,
|
| 959 |
+
"loss": 0.7097,
|
| 960 |
+
"step": 60
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 8.571428571428571,
|
| 964 |
+
"eval_accuracy": 0.5606060606060606,
|
| 965 |
+
"eval_loss": 0.6910924911499023,
|
| 966 |
+
"eval_runtime": 1.5475,
|
| 967 |
+
"eval_samples_per_second": 85.297,
|
| 968 |
+
"eval_steps_per_second": 2.585,
|
| 969 |
+
"step": 60
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 8.714285714285714,
|
| 973 |
+
"grad_norm": 10.05405044555664,
|
| 974 |
+
"learning_rate": 6.61764705882353e-06,
|
| 975 |
+
"loss": 0.687,
|
| 976 |
+
"step": 61
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 8.714285714285714,
|
| 980 |
+
"eval_accuracy": 0.553030303030303,
|
| 981 |
+
"eval_loss": 0.690488874912262,
|
| 982 |
+
"eval_runtime": 1.5501,
|
| 983 |
+
"eval_samples_per_second": 85.156,
|
| 984 |
+
"eval_steps_per_second": 2.58,
|
| 985 |
+
"step": 61
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 8.857142857142858,
|
| 989 |
+
"grad_norm": 5.774103164672852,
|
| 990 |
+
"learning_rate": 5.882352941176471e-06,
|
| 991 |
+
"loss": 0.7323,
|
| 992 |
+
"step": 62
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 8.857142857142858,
|
| 996 |
+
"eval_accuracy": 0.5303030303030303,
|
| 997 |
+
"eval_loss": 0.6909504532814026,
|
| 998 |
+
"eval_runtime": 1.5471,
|
| 999 |
+
"eval_samples_per_second": 85.323,
|
| 1000 |
+
"eval_steps_per_second": 2.586,
|
| 1001 |
+
"step": 62
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 9.0,
|
| 1005 |
+
"grad_norm": 7.126034736633301,
|
| 1006 |
+
"learning_rate": 5.147058823529412e-06,
|
| 1007 |
+
"loss": 0.721,
|
| 1008 |
+
"step": 63
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 9.0,
|
| 1012 |
+
"eval_accuracy": 0.5378787878787878,
|
| 1013 |
+
"eval_loss": 0.6910215616226196,
|
| 1014 |
+
"eval_runtime": 1.5426,
|
| 1015 |
+
"eval_samples_per_second": 85.569,
|
| 1016 |
+
"eval_steps_per_second": 2.593,
|
| 1017 |
+
"step": 63
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 9.142857142857142,
|
| 1021 |
+
"grad_norm": 4.496044635772705,
|
| 1022 |
+
"learning_rate": 4.411764705882353e-06,
|
| 1023 |
+
"loss": 0.7411,
|
| 1024 |
+
"step": 64
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 9.142857142857142,
|
| 1028 |
+
"eval_accuracy": 0.5454545454545454,
|
| 1029 |
+
"eval_loss": 0.6925870180130005,
|
| 1030 |
+
"eval_runtime": 1.5463,
|
| 1031 |
+
"eval_samples_per_second": 85.367,
|
| 1032 |
+
"eval_steps_per_second": 2.587,
|
| 1033 |
+
"step": 64
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 9.285714285714286,
|
| 1037 |
+
"grad_norm": 5.705209732055664,
|
| 1038 |
+
"learning_rate": 3.6764705882352942e-06,
|
| 1039 |
+
"loss": 0.7041,
|
| 1040 |
+
"step": 65
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 9.285714285714286,
|
| 1044 |
+
"eval_accuracy": 0.553030303030303,
|
| 1045 |
+
"eval_loss": 0.6924833655357361,
|
| 1046 |
+
"eval_runtime": 1.5448,
|
| 1047 |
+
"eval_samples_per_second": 85.45,
|
| 1048 |
+
"eval_steps_per_second": 2.589,
|
| 1049 |
+
"step": 65
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 9.428571428571429,
|
| 1053 |
+
"grad_norm": 3.551724910736084,
|
| 1054 |
+
"learning_rate": 2.9411764705882355e-06,
|
| 1055 |
+
"loss": 0.7559,
|
| 1056 |
+
"step": 66
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 9.428571428571429,
|
| 1060 |
+
"eval_accuracy": 0.5454545454545454,
|
| 1061 |
+
"eval_loss": 0.6926906108856201,
|
| 1062 |
+
"eval_runtime": 1.5456,
|
| 1063 |
+
"eval_samples_per_second": 85.403,
|
| 1064 |
+
"eval_steps_per_second": 2.588,
|
| 1065 |
+
"step": 66
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 9.571428571428571,
|
| 1069 |
+
"grad_norm": 1.5494858026504517,
|
| 1070 |
+
"learning_rate": 2.2058823529411767e-06,
|
| 1071 |
+
"loss": 0.6951,
|
| 1072 |
+
"step": 67
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 9.571428571428571,
|
| 1076 |
+
"eval_accuracy": 0.5378787878787878,
|
| 1077 |
+
"eval_loss": 0.6926224231719971,
|
| 1078 |
+
"eval_runtime": 1.5442,
|
| 1079 |
+
"eval_samples_per_second": 85.483,
|
| 1080 |
+
"eval_steps_per_second": 2.59,
|
| 1081 |
+
"step": 67
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 9.714285714285714,
|
| 1085 |
+
"grad_norm": 6.727674961090088,
|
| 1086 |
+
"learning_rate": 1.4705882352941177e-06,
|
| 1087 |
+
"loss": 0.7175,
|
| 1088 |
+
"step": 68
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 9.714285714285714,
|
| 1092 |
+
"eval_accuracy": 0.5303030303030303,
|
| 1093 |
+
"eval_loss": 0.692868173122406,
|
| 1094 |
+
"eval_runtime": 1.5499,
|
| 1095 |
+
"eval_samples_per_second": 85.165,
|
| 1096 |
+
"eval_steps_per_second": 2.581,
|
| 1097 |
+
"step": 68
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 9.857142857142858,
|
| 1101 |
+
"grad_norm": 2.2420670986175537,
|
| 1102 |
+
"learning_rate": 7.352941176470589e-07,
|
| 1103 |
+
"loss": 0.6852,
|
| 1104 |
+
"step": 69
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 9.857142857142858,
|
| 1108 |
+
"eval_accuracy": 0.5454545454545454,
|
| 1109 |
+
"eval_loss": 0.6923591494560242,
|
| 1110 |
+
"eval_runtime": 1.5004,
|
| 1111 |
+
"eval_samples_per_second": 87.976,
|
| 1112 |
+
"eval_steps_per_second": 2.666,
|
| 1113 |
+
"step": 69
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 10.0,
|
| 1117 |
+
"grad_norm": 4.505035400390625,
|
| 1118 |
+
"learning_rate": 0.0,
|
| 1119 |
+
"loss": 0.6894,
|
| 1120 |
+
"step": 70
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 10.0,
|
| 1124 |
+
"eval_accuracy": 0.553030303030303,
|
| 1125 |
+
"eval_loss": 0.6922733187675476,
|
| 1126 |
+
"eval_runtime": 1.4985,
|
| 1127 |
+
"eval_samples_per_second": 88.086,
|
| 1128 |
+
"eval_steps_per_second": 2.669,
|
| 1129 |
+
"step": 70
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 10.0,
|
| 1133 |
+
"step": 70,
|
| 1134 |
+
"total_flos": 62972060631040.0,
|
| 1135 |
+
"train_loss": 0.7597047252314432,
|
| 1136 |
+
"train_runtime": 351.9683,
|
| 1137 |
+
"train_samples_per_second": 14.945,
|
| 1138 |
+
"train_steps_per_second": 0.199
|
| 1139 |
+
}
|
| 1140 |
+
],
|
| 1141 |
+
"logging_steps": 1,
|
| 1142 |
+
"max_steps": 70,
|
| 1143 |
+
"num_input_tokens_seen": 0,
|
| 1144 |
+
"num_train_epochs": 10,
|
| 1145 |
+
"save_steps": 500,
|
| 1146 |
+
"total_flos": 62972060631040.0,
|
| 1147 |
+
"train_batch_size": 10,
|
| 1148 |
+
"trial_name": null,
|
| 1149 |
+
"trial_params": null
|
| 1150 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37266b6d08508ed507c9a38582ba531a0bd0e5101eaa5e5b80d12ff76bff84ba
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|