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-axg-sequence_classification.json +1470 -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:bf8b2f603972f6cd85e86e5c0bbd9fa8b5e07cf1bc66ecda369e86c04da848d9
|
| 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-axg-sequence_classification.json
ADDED
|
@@ -0,0 +1,1470 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 90,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1111111111111111,
|
| 13 |
+
"grad_norm": 34.7608757019043,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 1.2054,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1111111111111111,
|
| 20 |
+
"eval_accuracy": 0.5277777777777778,
|
| 21 |
+
"eval_loss": 1.0094876289367676,
|
| 22 |
+
"eval_runtime": 0.7089,
|
| 23 |
+
"eval_samples_per_second": 101.565,
|
| 24 |
+
"eval_steps_per_second": 7.053,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.2222222222222222,
|
| 29 |
+
"grad_norm": 30.633609771728516,
|
| 30 |
+
"learning_rate": 5e-05,
|
| 31 |
+
"loss": 1.1567,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.2222222222222222,
|
| 36 |
+
"eval_accuracy": 0.5277777777777778,
|
| 37 |
+
"eval_loss": 0.9987521767616272,
|
| 38 |
+
"eval_runtime": 0.603,
|
| 39 |
+
"eval_samples_per_second": 119.406,
|
| 40 |
+
"eval_steps_per_second": 8.292,
|
| 41 |
+
"step": 2
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.3333333333333333,
|
| 45 |
+
"grad_norm": 25.385608673095703,
|
| 46 |
+
"learning_rate": 4.943181818181818e-05,
|
| 47 |
+
"loss": 1.0806,
|
| 48 |
+
"step": 3
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.3333333333333333,
|
| 52 |
+
"eval_accuracy": 0.5277777777777778,
|
| 53 |
+
"eval_loss": 0.9628159999847412,
|
| 54 |
+
"eval_runtime": 0.7075,
|
| 55 |
+
"eval_samples_per_second": 101.767,
|
| 56 |
+
"eval_steps_per_second": 7.067,
|
| 57 |
+
"step": 3
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.4444444444444444,
|
| 61 |
+
"grad_norm": 22.26402473449707,
|
| 62 |
+
"learning_rate": 4.886363636363637e-05,
|
| 63 |
+
"loss": 0.9883,
|
| 64 |
+
"step": 4
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.4444444444444444,
|
| 68 |
+
"eval_accuracy": 0.5277777777777778,
|
| 69 |
+
"eval_loss": 0.9259067177772522,
|
| 70 |
+
"eval_runtime": 0.7031,
|
| 71 |
+
"eval_samples_per_second": 102.402,
|
| 72 |
+
"eval_steps_per_second": 7.111,
|
| 73 |
+
"step": 4
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.5555555555555556,
|
| 77 |
+
"grad_norm": 26.522153854370117,
|
| 78 |
+
"learning_rate": 4.829545454545455e-05,
|
| 79 |
+
"loss": 0.9736,
|
| 80 |
+
"step": 5
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.5555555555555556,
|
| 84 |
+
"eval_accuracy": 0.4722222222222222,
|
| 85 |
+
"eval_loss": 0.8975830078125,
|
| 86 |
+
"eval_runtime": 0.7036,
|
| 87 |
+
"eval_samples_per_second": 102.336,
|
| 88 |
+
"eval_steps_per_second": 7.107,
|
| 89 |
+
"step": 5
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.6666666666666666,
|
| 93 |
+
"grad_norm": 18.14297866821289,
|
| 94 |
+
"learning_rate": 4.772727272727273e-05,
|
| 95 |
+
"loss": 0.8267,
|
| 96 |
+
"step": 6
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.6666666666666666,
|
| 100 |
+
"eval_accuracy": 0.4583333333333333,
|
| 101 |
+
"eval_loss": 0.8745185136795044,
|
| 102 |
+
"eval_runtime": 0.6043,
|
| 103 |
+
"eval_samples_per_second": 119.149,
|
| 104 |
+
"eval_steps_per_second": 8.274,
|
| 105 |
+
"step": 6
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.7777777777777778,
|
| 109 |
+
"grad_norm": 10.767016410827637,
|
| 110 |
+
"learning_rate": 4.715909090909091e-05,
|
| 111 |
+
"loss": 0.8047,
|
| 112 |
+
"step": 7
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.7777777777777778,
|
| 116 |
+
"eval_accuracy": 0.4166666666666667,
|
| 117 |
+
"eval_loss": 0.8637288212776184,
|
| 118 |
+
"eval_runtime": 0.7076,
|
| 119 |
+
"eval_samples_per_second": 101.757,
|
| 120 |
+
"eval_steps_per_second": 7.066,
|
| 121 |
+
"step": 7
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8888888888888888,
|
| 125 |
+
"grad_norm": 9.212442398071289,
|
| 126 |
+
"learning_rate": 4.659090909090909e-05,
|
| 127 |
+
"loss": 0.6807,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8888888888888888,
|
| 132 |
+
"eval_accuracy": 0.4027777777777778,
|
| 133 |
+
"eval_loss": 0.8712022304534912,
|
| 134 |
+
"eval_runtime": 0.7061,
|
| 135 |
+
"eval_samples_per_second": 101.97,
|
| 136 |
+
"eval_steps_per_second": 7.081,
|
| 137 |
+
"step": 8
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.0,
|
| 141 |
+
"grad_norm": 10.467320442199707,
|
| 142 |
+
"learning_rate": 4.602272727272727e-05,
|
| 143 |
+
"loss": 0.7425,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.0,
|
| 148 |
+
"eval_accuracy": 0.3611111111111111,
|
| 149 |
+
"eval_loss": 0.8966064453125,
|
| 150 |
+
"eval_runtime": 0.7054,
|
| 151 |
+
"eval_samples_per_second": 102.068,
|
| 152 |
+
"eval_steps_per_second": 7.088,
|
| 153 |
+
"step": 9
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.1111111111111112,
|
| 157 |
+
"grad_norm": 8.758502960205078,
|
| 158 |
+
"learning_rate": 4.545454545454546e-05,
|
| 159 |
+
"loss": 0.7941,
|
| 160 |
+
"step": 10
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.1111111111111112,
|
| 164 |
+
"eval_accuracy": 0.3611111111111111,
|
| 165 |
+
"eval_loss": 0.896728515625,
|
| 166 |
+
"eval_runtime": 0.7073,
|
| 167 |
+
"eval_samples_per_second": 101.79,
|
| 168 |
+
"eval_steps_per_second": 7.069,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.2222222222222223,
|
| 173 |
+
"grad_norm": 2.704101800918579,
|
| 174 |
+
"learning_rate": 4.488636363636364e-05,
|
| 175 |
+
"loss": 0.6092,
|
| 176 |
+
"step": 11
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.2222222222222223,
|
| 180 |
+
"eval_accuracy": 0.3333333333333333,
|
| 181 |
+
"eval_loss": 0.8883192539215088,
|
| 182 |
+
"eval_runtime": 0.603,
|
| 183 |
+
"eval_samples_per_second": 119.401,
|
| 184 |
+
"eval_steps_per_second": 8.292,
|
| 185 |
+
"step": 11
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.3333333333333333,
|
| 189 |
+
"grad_norm": 3.9579689502716064,
|
| 190 |
+
"learning_rate": 4.431818181818182e-05,
|
| 191 |
+
"loss": 0.7372,
|
| 192 |
+
"step": 12
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.3333333333333333,
|
| 196 |
+
"eval_accuracy": 0.3333333333333333,
|
| 197 |
+
"eval_loss": 0.8713921308517456,
|
| 198 |
+
"eval_runtime": 0.6557,
|
| 199 |
+
"eval_samples_per_second": 109.8,
|
| 200 |
+
"eval_steps_per_second": 7.625,
|
| 201 |
+
"step": 12
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.4444444444444444,
|
| 205 |
+
"grad_norm": 4.962625980377197,
|
| 206 |
+
"learning_rate": 4.375e-05,
|
| 207 |
+
"loss": 0.6553,
|
| 208 |
+
"step": 13
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.4444444444444444,
|
| 212 |
+
"eval_accuracy": 0.3194444444444444,
|
| 213 |
+
"eval_loss": 0.8686930537223816,
|
| 214 |
+
"eval_runtime": 0.7054,
|
| 215 |
+
"eval_samples_per_second": 102.073,
|
| 216 |
+
"eval_steps_per_second": 7.088,
|
| 217 |
+
"step": 13
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.5555555555555556,
|
| 221 |
+
"grad_norm": 2.9537837505340576,
|
| 222 |
+
"learning_rate": 4.318181818181819e-05,
|
| 223 |
+
"loss": 0.7266,
|
| 224 |
+
"step": 14
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.5555555555555556,
|
| 228 |
+
"eval_accuracy": 0.2777777777777778,
|
| 229 |
+
"eval_loss": 0.8620063066482544,
|
| 230 |
+
"eval_runtime": 0.7075,
|
| 231 |
+
"eval_samples_per_second": 101.766,
|
| 232 |
+
"eval_steps_per_second": 7.067,
|
| 233 |
+
"step": 14
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.6666666666666665,
|
| 237 |
+
"grad_norm": 4.937398910522461,
|
| 238 |
+
"learning_rate": 4.261363636363637e-05,
|
| 239 |
+
"loss": 0.7462,
|
| 240 |
+
"step": 15
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.6666666666666665,
|
| 244 |
+
"eval_accuracy": 0.3333333333333333,
|
| 245 |
+
"eval_loss": 0.8434787392616272,
|
| 246 |
+
"eval_runtime": 0.7043,
|
| 247 |
+
"eval_samples_per_second": 102.225,
|
| 248 |
+
"eval_steps_per_second": 7.099,
|
| 249 |
+
"step": 15
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.7777777777777777,
|
| 253 |
+
"grad_norm": 8.647956848144531,
|
| 254 |
+
"learning_rate": 4.204545454545455e-05,
|
| 255 |
+
"loss": 0.66,
|
| 256 |
+
"step": 16
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.7777777777777777,
|
| 260 |
+
"eval_accuracy": 0.375,
|
| 261 |
+
"eval_loss": 0.8198378086090088,
|
| 262 |
+
"eval_runtime": 0.7049,
|
| 263 |
+
"eval_samples_per_second": 102.141,
|
| 264 |
+
"eval_steps_per_second": 7.093,
|
| 265 |
+
"step": 16
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.8888888888888888,
|
| 269 |
+
"grad_norm": 6.325115203857422,
|
| 270 |
+
"learning_rate": 4.1477272727272734e-05,
|
| 271 |
+
"loss": 0.6908,
|
| 272 |
+
"step": 17
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.8888888888888888,
|
| 276 |
+
"eval_accuracy": 0.4444444444444444,
|
| 277 |
+
"eval_loss": 0.8034396767616272,
|
| 278 |
+
"eval_runtime": 0.6506,
|
| 279 |
+
"eval_samples_per_second": 110.674,
|
| 280 |
+
"eval_steps_per_second": 7.686,
|
| 281 |
+
"step": 17
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.0,
|
| 285 |
+
"grad_norm": 2.925394058227539,
|
| 286 |
+
"learning_rate": 4.0909090909090915e-05,
|
| 287 |
+
"loss": 0.6993,
|
| 288 |
+
"step": 18
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.0,
|
| 292 |
+
"eval_accuracy": 0.5277777777777778,
|
| 293 |
+
"eval_loss": 0.7982177734375,
|
| 294 |
+
"eval_runtime": 0.7049,
|
| 295 |
+
"eval_samples_per_second": 102.145,
|
| 296 |
+
"eval_steps_per_second": 7.093,
|
| 297 |
+
"step": 18
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.111111111111111,
|
| 301 |
+
"grad_norm": 4.028661251068115,
|
| 302 |
+
"learning_rate": 4.034090909090909e-05,
|
| 303 |
+
"loss": 0.7788,
|
| 304 |
+
"step": 19
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.111111111111111,
|
| 308 |
+
"eval_accuracy": 0.5277777777777778,
|
| 309 |
+
"eval_loss": 0.787353515625,
|
| 310 |
+
"eval_runtime": 0.7038,
|
| 311 |
+
"eval_samples_per_second": 102.296,
|
| 312 |
+
"eval_steps_per_second": 7.104,
|
| 313 |
+
"step": 19
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.2222222222222223,
|
| 317 |
+
"grad_norm": 3.346914529800415,
|
| 318 |
+
"learning_rate": 3.9772727272727275e-05,
|
| 319 |
+
"loss": 0.6594,
|
| 320 |
+
"step": 20
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.2222222222222223,
|
| 324 |
+
"eval_accuracy": 0.5138888888888888,
|
| 325 |
+
"eval_loss": 0.7767741084098816,
|
| 326 |
+
"eval_runtime": 0.7031,
|
| 327 |
+
"eval_samples_per_second": 102.403,
|
| 328 |
+
"eval_steps_per_second": 7.111,
|
| 329 |
+
"step": 20
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.3333333333333335,
|
| 333 |
+
"grad_norm": 5.400989532470703,
|
| 334 |
+
"learning_rate": 3.9204545454545456e-05,
|
| 335 |
+
"loss": 0.7303,
|
| 336 |
+
"step": 21
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.3333333333333335,
|
| 340 |
+
"eval_accuracy": 0.5,
|
| 341 |
+
"eval_loss": 0.7682834267616272,
|
| 342 |
+
"eval_runtime": 0.6498,
|
| 343 |
+
"eval_samples_per_second": 110.797,
|
| 344 |
+
"eval_steps_per_second": 7.694,
|
| 345 |
+
"step": 21
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.4444444444444446,
|
| 349 |
+
"grad_norm": 2.919682025909424,
|
| 350 |
+
"learning_rate": 3.8636363636363636e-05,
|
| 351 |
+
"loss": 0.6688,
|
| 352 |
+
"step": 22
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.4444444444444446,
|
| 356 |
+
"eval_accuracy": 0.4861111111111111,
|
| 357 |
+
"eval_loss": 0.7653401494026184,
|
| 358 |
+
"eval_runtime": 0.551,
|
| 359 |
+
"eval_samples_per_second": 130.66,
|
| 360 |
+
"eval_steps_per_second": 9.074,
|
| 361 |
+
"step": 22
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.5555555555555554,
|
| 365 |
+
"grad_norm": 9.212122917175293,
|
| 366 |
+
"learning_rate": 3.8068181818181816e-05,
|
| 367 |
+
"loss": 0.7337,
|
| 368 |
+
"step": 23
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.5555555555555554,
|
| 372 |
+
"eval_accuracy": 0.5,
|
| 373 |
+
"eval_loss": 0.7591145634651184,
|
| 374 |
+
"eval_runtime": 0.7017,
|
| 375 |
+
"eval_samples_per_second": 102.602,
|
| 376 |
+
"eval_steps_per_second": 7.125,
|
| 377 |
+
"step": 23
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.6666666666666665,
|
| 381 |
+
"grad_norm": 8.884961128234863,
|
| 382 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 383 |
+
"loss": 0.6648,
|
| 384 |
+
"step": 24
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.6666666666666665,
|
| 388 |
+
"eval_accuracy": 0.5,
|
| 389 |
+
"eval_loss": 0.7524074912071228,
|
| 390 |
+
"eval_runtime": 0.7032,
|
| 391 |
+
"eval_samples_per_second": 102.392,
|
| 392 |
+
"eval_steps_per_second": 7.111,
|
| 393 |
+
"step": 24
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.7777777777777777,
|
| 397 |
+
"grad_norm": 5.935830116271973,
|
| 398 |
+
"learning_rate": 3.6931818181818184e-05,
|
| 399 |
+
"loss": 0.6589,
|
| 400 |
+
"step": 25
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.7777777777777777,
|
| 404 |
+
"eval_accuracy": 0.5138888888888888,
|
| 405 |
+
"eval_loss": 0.7492743730545044,
|
| 406 |
+
"eval_runtime": 0.6514,
|
| 407 |
+
"eval_samples_per_second": 110.527,
|
| 408 |
+
"eval_steps_per_second": 7.675,
|
| 409 |
+
"step": 25
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.888888888888889,
|
| 413 |
+
"grad_norm": 7.1309027671813965,
|
| 414 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 415 |
+
"loss": 0.8163,
|
| 416 |
+
"step": 26
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.888888888888889,
|
| 420 |
+
"eval_accuracy": 0.5416666666666666,
|
| 421 |
+
"eval_loss": 0.7473212480545044,
|
| 422 |
+
"eval_runtime": 0.706,
|
| 423 |
+
"eval_samples_per_second": 101.99,
|
| 424 |
+
"eval_steps_per_second": 7.083,
|
| 425 |
+
"step": 26
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.0,
|
| 429 |
+
"grad_norm": 5.935413837432861,
|
| 430 |
+
"learning_rate": 3.579545454545455e-05,
|
| 431 |
+
"loss": 0.6456,
|
| 432 |
+
"step": 27
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.0,
|
| 436 |
+
"eval_accuracy": 0.5694444444444444,
|
| 437 |
+
"eval_loss": 0.74639892578125,
|
| 438 |
+
"eval_runtime": 0.6008,
|
| 439 |
+
"eval_samples_per_second": 119.848,
|
| 440 |
+
"eval_steps_per_second": 8.323,
|
| 441 |
+
"step": 27
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.111111111111111,
|
| 445 |
+
"grad_norm": 4.931116104125977,
|
| 446 |
+
"learning_rate": 3.522727272727273e-05,
|
| 447 |
+
"loss": 0.7576,
|
| 448 |
+
"step": 28
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 3.111111111111111,
|
| 452 |
+
"eval_accuracy": 0.5555555555555556,
|
| 453 |
+
"eval_loss": 0.7495456337928772,
|
| 454 |
+
"eval_runtime": 0.6526,
|
| 455 |
+
"eval_samples_per_second": 110.329,
|
| 456 |
+
"eval_steps_per_second": 7.662,
|
| 457 |
+
"step": 28
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 3.2222222222222223,
|
| 461 |
+
"grad_norm": 8.242729187011719,
|
| 462 |
+
"learning_rate": 3.465909090909091e-05,
|
| 463 |
+
"loss": 0.6763,
|
| 464 |
+
"step": 29
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.2222222222222223,
|
| 468 |
+
"eval_accuracy": 0.5555555555555556,
|
| 469 |
+
"eval_loss": 0.7501423954963684,
|
| 470 |
+
"eval_runtime": 0.7058,
|
| 471 |
+
"eval_samples_per_second": 102.009,
|
| 472 |
+
"eval_steps_per_second": 7.084,
|
| 473 |
+
"step": 29
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.3333333333333335,
|
| 477 |
+
"grad_norm": 4.411537170410156,
|
| 478 |
+
"learning_rate": 3.409090909090909e-05,
|
| 479 |
+
"loss": 0.7565,
|
| 480 |
+
"step": 30
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 3.3333333333333335,
|
| 484 |
+
"eval_accuracy": 0.5555555555555556,
|
| 485 |
+
"eval_loss": 0.7513563632965088,
|
| 486 |
+
"eval_runtime": 0.7022,
|
| 487 |
+
"eval_samples_per_second": 102.536,
|
| 488 |
+
"eval_steps_per_second": 7.121,
|
| 489 |
+
"step": 30
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.4444444444444446,
|
| 493 |
+
"grad_norm": 5.082301139831543,
|
| 494 |
+
"learning_rate": 3.352272727272727e-05,
|
| 495 |
+
"loss": 0.7888,
|
| 496 |
+
"step": 31
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 3.4444444444444446,
|
| 500 |
+
"eval_accuracy": 0.5277777777777778,
|
| 501 |
+
"eval_loss": 0.7555338740348816,
|
| 502 |
+
"eval_runtime": 0.7031,
|
| 503 |
+
"eval_samples_per_second": 102.41,
|
| 504 |
+
"eval_steps_per_second": 7.112,
|
| 505 |
+
"step": 31
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 3.5555555555555554,
|
| 509 |
+
"grad_norm": 3.5483062267303467,
|
| 510 |
+
"learning_rate": 3.295454545454545e-05,
|
| 511 |
+
"loss": 0.6769,
|
| 512 |
+
"step": 32
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.5555555555555554,
|
| 516 |
+
"eval_accuracy": 0.5277777777777778,
|
| 517 |
+
"eval_loss": 0.7550930380821228,
|
| 518 |
+
"eval_runtime": 0.6042,
|
| 519 |
+
"eval_samples_per_second": 119.164,
|
| 520 |
+
"eval_steps_per_second": 8.275,
|
| 521 |
+
"step": 32
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 3.6666666666666665,
|
| 525 |
+
"grad_norm": 3.9409377574920654,
|
| 526 |
+
"learning_rate": 3.238636363636364e-05,
|
| 527 |
+
"loss": 0.718,
|
| 528 |
+
"step": 33
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 3.6666666666666665,
|
| 532 |
+
"eval_accuracy": 0.5277777777777778,
|
| 533 |
+
"eval_loss": 0.7593722939491272,
|
| 534 |
+
"eval_runtime": 0.7024,
|
| 535 |
+
"eval_samples_per_second": 102.508,
|
| 536 |
+
"eval_steps_per_second": 7.119,
|
| 537 |
+
"step": 33
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 3.7777777777777777,
|
| 541 |
+
"grad_norm": 11.279867172241211,
|
| 542 |
+
"learning_rate": 3.181818181818182e-05,
|
| 543 |
+
"loss": 0.6424,
|
| 544 |
+
"step": 34
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 3.7777777777777777,
|
| 548 |
+
"eval_accuracy": 0.5138888888888888,
|
| 549 |
+
"eval_loss": 0.7629123330116272,
|
| 550 |
+
"eval_runtime": 0.7053,
|
| 551 |
+
"eval_samples_per_second": 102.077,
|
| 552 |
+
"eval_steps_per_second": 7.089,
|
| 553 |
+
"step": 34
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.888888888888889,
|
| 557 |
+
"grad_norm": 8.519107818603516,
|
| 558 |
+
"learning_rate": 3.125e-05,
|
| 559 |
+
"loss": 0.6471,
|
| 560 |
+
"step": 35
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.888888888888889,
|
| 564 |
+
"eval_accuracy": 0.4861111111111111,
|
| 565 |
+
"eval_loss": 0.7659505009651184,
|
| 566 |
+
"eval_runtime": 0.703,
|
| 567 |
+
"eval_samples_per_second": 102.418,
|
| 568 |
+
"eval_steps_per_second": 7.112,
|
| 569 |
+
"step": 35
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 4.0,
|
| 573 |
+
"grad_norm": 6.580870628356934,
|
| 574 |
+
"learning_rate": 3.068181818181818e-05,
|
| 575 |
+
"loss": 0.727,
|
| 576 |
+
"step": 36
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 4.0,
|
| 580 |
+
"eval_accuracy": 0.4027777777777778,
|
| 581 |
+
"eval_loss": 0.7695041298866272,
|
| 582 |
+
"eval_runtime": 0.6543,
|
| 583 |
+
"eval_samples_per_second": 110.049,
|
| 584 |
+
"eval_steps_per_second": 7.642,
|
| 585 |
+
"step": 36
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 4.111111111111111,
|
| 589 |
+
"grad_norm": 11.691934585571289,
|
| 590 |
+
"learning_rate": 3.0113636363636365e-05,
|
| 591 |
+
"loss": 0.73,
|
| 592 |
+
"step": 37
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 4.111111111111111,
|
| 596 |
+
"eval_accuracy": 0.4027777777777778,
|
| 597 |
+
"eval_loss": 0.7756076455116272,
|
| 598 |
+
"eval_runtime": 0.7028,
|
| 599 |
+
"eval_samples_per_second": 102.442,
|
| 600 |
+
"eval_steps_per_second": 7.114,
|
| 601 |
+
"step": 37
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 4.222222222222222,
|
| 605 |
+
"grad_norm": 13.515392303466797,
|
| 606 |
+
"learning_rate": 2.954545454545455e-05,
|
| 607 |
+
"loss": 0.687,
|
| 608 |
+
"step": 38
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 4.222222222222222,
|
| 612 |
+
"eval_accuracy": 0.4722222222222222,
|
| 613 |
+
"eval_loss": 0.7799343466758728,
|
| 614 |
+
"eval_runtime": 0.705,
|
| 615 |
+
"eval_samples_per_second": 102.128,
|
| 616 |
+
"eval_steps_per_second": 7.092,
|
| 617 |
+
"step": 38
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 4.333333333333333,
|
| 621 |
+
"grad_norm": 3.4968955516815186,
|
| 622 |
+
"learning_rate": 2.8977272727272732e-05,
|
| 623 |
+
"loss": 0.6573,
|
| 624 |
+
"step": 39
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 4.333333333333333,
|
| 628 |
+
"eval_accuracy": 0.4583333333333333,
|
| 629 |
+
"eval_loss": 0.7805582880973816,
|
| 630 |
+
"eval_runtime": 0.7046,
|
| 631 |
+
"eval_samples_per_second": 102.181,
|
| 632 |
+
"eval_steps_per_second": 7.096,
|
| 633 |
+
"step": 39
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 4.444444444444445,
|
| 637 |
+
"grad_norm": 6.2186713218688965,
|
| 638 |
+
"learning_rate": 2.8409090909090912e-05,
|
| 639 |
+
"loss": 0.6691,
|
| 640 |
+
"step": 40
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 4.444444444444445,
|
| 644 |
+
"eval_accuracy": 0.4861111111111111,
|
| 645 |
+
"eval_loss": 0.7847764492034912,
|
| 646 |
+
"eval_runtime": 0.7058,
|
| 647 |
+
"eval_samples_per_second": 102.009,
|
| 648 |
+
"eval_steps_per_second": 7.084,
|
| 649 |
+
"step": 40
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 4.555555555555555,
|
| 653 |
+
"grad_norm": 9.075811386108398,
|
| 654 |
+
"learning_rate": 2.784090909090909e-05,
|
| 655 |
+
"loss": 0.8023,
|
| 656 |
+
"step": 41
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 4.555555555555555,
|
| 660 |
+
"eval_accuracy": 0.4583333333333333,
|
| 661 |
+
"eval_loss": 0.78857421875,
|
| 662 |
+
"eval_runtime": 0.7051,
|
| 663 |
+
"eval_samples_per_second": 102.113,
|
| 664 |
+
"eval_steps_per_second": 7.091,
|
| 665 |
+
"step": 41
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 4.666666666666667,
|
| 669 |
+
"grad_norm": 5.013810157775879,
|
| 670 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 671 |
+
"loss": 0.6703,
|
| 672 |
+
"step": 42
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 4.666666666666667,
|
| 676 |
+
"eval_accuracy": 0.4861111111111111,
|
| 677 |
+
"eval_loss": 0.7918837070465088,
|
| 678 |
+
"eval_runtime": 0.655,
|
| 679 |
+
"eval_samples_per_second": 109.915,
|
| 680 |
+
"eval_steps_per_second": 7.633,
|
| 681 |
+
"step": 42
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 4.777777777777778,
|
| 685 |
+
"grad_norm": 5.304051876068115,
|
| 686 |
+
"learning_rate": 2.6704545454545453e-05,
|
| 687 |
+
"loss": 0.7019,
|
| 688 |
+
"step": 43
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 4.777777777777778,
|
| 692 |
+
"eval_accuracy": 0.4722222222222222,
|
| 693 |
+
"eval_loss": 0.7928195595741272,
|
| 694 |
+
"eval_runtime": 0.6557,
|
| 695 |
+
"eval_samples_per_second": 109.8,
|
| 696 |
+
"eval_steps_per_second": 7.625,
|
| 697 |
+
"step": 43
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 4.888888888888889,
|
| 701 |
+
"grad_norm": 7.697951316833496,
|
| 702 |
+
"learning_rate": 2.6136363636363637e-05,
|
| 703 |
+
"loss": 0.6973,
|
| 704 |
+
"step": 44
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.888888888888889,
|
| 708 |
+
"eval_accuracy": 0.4861111111111111,
|
| 709 |
+
"eval_loss": 0.8020155429840088,
|
| 710 |
+
"eval_runtime": 0.6545,
|
| 711 |
+
"eval_samples_per_second": 110.008,
|
| 712 |
+
"eval_steps_per_second": 7.639,
|
| 713 |
+
"step": 44
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 5.0,
|
| 717 |
+
"grad_norm": 18.014299392700195,
|
| 718 |
+
"learning_rate": 2.5568181818181817e-05,
|
| 719 |
+
"loss": 0.7859,
|
| 720 |
+
"step": 45
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 5.0,
|
| 724 |
+
"eval_accuracy": 0.4166666666666667,
|
| 725 |
+
"eval_loss": 0.8017985224723816,
|
| 726 |
+
"eval_runtime": 0.702,
|
| 727 |
+
"eval_samples_per_second": 102.565,
|
| 728 |
+
"eval_steps_per_second": 7.123,
|
| 729 |
+
"step": 45
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 5.111111111111111,
|
| 733 |
+
"grad_norm": 5.591033458709717,
|
| 734 |
+
"learning_rate": 2.5e-05,
|
| 735 |
+
"loss": 0.6987,
|
| 736 |
+
"step": 46
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 5.111111111111111,
|
| 740 |
+
"eval_accuracy": 0.4166666666666667,
|
| 741 |
+
"eval_loss": 0.8059489130973816,
|
| 742 |
+
"eval_runtime": 0.7047,
|
| 743 |
+
"eval_samples_per_second": 102.172,
|
| 744 |
+
"eval_steps_per_second": 7.095,
|
| 745 |
+
"step": 46
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 5.222222222222222,
|
| 749 |
+
"grad_norm": 4.745278835296631,
|
| 750 |
+
"learning_rate": 2.4431818181818185e-05,
|
| 751 |
+
"loss": 0.6566,
|
| 752 |
+
"step": 47
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 5.222222222222222,
|
| 756 |
+
"eval_accuracy": 0.4305555555555556,
|
| 757 |
+
"eval_loss": 0.807861328125,
|
| 758 |
+
"eval_runtime": 0.6555,
|
| 759 |
+
"eval_samples_per_second": 109.837,
|
| 760 |
+
"eval_steps_per_second": 7.628,
|
| 761 |
+
"step": 47
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 5.333333333333333,
|
| 765 |
+
"grad_norm": 7.4073486328125,
|
| 766 |
+
"learning_rate": 2.3863636363636365e-05,
|
| 767 |
+
"loss": 0.7671,
|
| 768 |
+
"step": 48
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 5.333333333333333,
|
| 772 |
+
"eval_accuracy": 0.4166666666666667,
|
| 773 |
+
"eval_loss": 0.8123643398284912,
|
| 774 |
+
"eval_runtime": 0.7034,
|
| 775 |
+
"eval_samples_per_second": 102.354,
|
| 776 |
+
"eval_steps_per_second": 7.108,
|
| 777 |
+
"step": 48
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 5.444444444444445,
|
| 781 |
+
"grad_norm": 7.266972541809082,
|
| 782 |
+
"learning_rate": 2.3295454545454546e-05,
|
| 783 |
+
"loss": 0.7223,
|
| 784 |
+
"step": 49
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 5.444444444444445,
|
| 788 |
+
"eval_accuracy": 0.4166666666666667,
|
| 789 |
+
"eval_loss": 0.8111029863357544,
|
| 790 |
+
"eval_runtime": 0.7066,
|
| 791 |
+
"eval_samples_per_second": 101.892,
|
| 792 |
+
"eval_steps_per_second": 7.076,
|
| 793 |
+
"step": 49
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 5.555555555555555,
|
| 797 |
+
"grad_norm": 3.803126573562622,
|
| 798 |
+
"learning_rate": 2.272727272727273e-05,
|
| 799 |
+
"loss": 0.637,
|
| 800 |
+
"step": 50
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 5.555555555555555,
|
| 804 |
+
"eval_accuracy": 0.4166666666666667,
|
| 805 |
+
"eval_loss": 0.8150363564491272,
|
| 806 |
+
"eval_runtime": 0.5565,
|
| 807 |
+
"eval_samples_per_second": 129.373,
|
| 808 |
+
"eval_steps_per_second": 8.984,
|
| 809 |
+
"step": 50
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 5.666666666666667,
|
| 813 |
+
"grad_norm": 6.748312950134277,
|
| 814 |
+
"learning_rate": 2.215909090909091e-05,
|
| 815 |
+
"loss": 0.6406,
|
| 816 |
+
"step": 51
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 5.666666666666667,
|
| 820 |
+
"eval_accuracy": 0.3888888888888889,
|
| 821 |
+
"eval_loss": 0.8139106035232544,
|
| 822 |
+
"eval_runtime": 0.6526,
|
| 823 |
+
"eval_samples_per_second": 110.328,
|
| 824 |
+
"eval_steps_per_second": 7.662,
|
| 825 |
+
"step": 51
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 5.777777777777778,
|
| 829 |
+
"grad_norm": 14.67806625366211,
|
| 830 |
+
"learning_rate": 2.1590909090909093e-05,
|
| 831 |
+
"loss": 0.7293,
|
| 832 |
+
"step": 52
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 5.777777777777778,
|
| 836 |
+
"eval_accuracy": 0.3888888888888889,
|
| 837 |
+
"eval_loss": 0.8112928867340088,
|
| 838 |
+
"eval_runtime": 0.5507,
|
| 839 |
+
"eval_samples_per_second": 130.733,
|
| 840 |
+
"eval_steps_per_second": 9.079,
|
| 841 |
+
"step": 52
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 5.888888888888889,
|
| 845 |
+
"grad_norm": 12.766432762145996,
|
| 846 |
+
"learning_rate": 2.1022727272727274e-05,
|
| 847 |
+
"loss": 0.6668,
|
| 848 |
+
"step": 53
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 5.888888888888889,
|
| 852 |
+
"eval_accuracy": 0.3888888888888889,
|
| 853 |
+
"eval_loss": 0.8097330927848816,
|
| 854 |
+
"eval_runtime": 0.6502,
|
| 855 |
+
"eval_samples_per_second": 110.73,
|
| 856 |
+
"eval_steps_per_second": 7.69,
|
| 857 |
+
"step": 53
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 6.0,
|
| 861 |
+
"grad_norm": 6.800503730773926,
|
| 862 |
+
"learning_rate": 2.0454545454545457e-05,
|
| 863 |
+
"loss": 0.69,
|
| 864 |
+
"step": 54
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 6.0,
|
| 868 |
+
"eval_accuracy": 0.3888888888888889,
|
| 869 |
+
"eval_loss": 0.8104926347732544,
|
| 870 |
+
"eval_runtime": 0.5514,
|
| 871 |
+
"eval_samples_per_second": 130.565,
|
| 872 |
+
"eval_steps_per_second": 9.067,
|
| 873 |
+
"step": 54
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 6.111111111111111,
|
| 877 |
+
"grad_norm": 3.1313846111297607,
|
| 878 |
+
"learning_rate": 1.9886363636363638e-05,
|
| 879 |
+
"loss": 0.6828,
|
| 880 |
+
"step": 55
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 6.111111111111111,
|
| 884 |
+
"eval_accuracy": 0.3888888888888889,
|
| 885 |
+
"eval_loss": 0.8099636435508728,
|
| 886 |
+
"eval_runtime": 0.5992,
|
| 887 |
+
"eval_samples_per_second": 120.168,
|
| 888 |
+
"eval_steps_per_second": 8.345,
|
| 889 |
+
"step": 55
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 6.222222222222222,
|
| 893 |
+
"grad_norm": 4.510275363922119,
|
| 894 |
+
"learning_rate": 1.9318181818181818e-05,
|
| 895 |
+
"loss": 0.6665,
|
| 896 |
+
"step": 56
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 6.222222222222222,
|
| 900 |
+
"eval_accuracy": 0.3888888888888889,
|
| 901 |
+
"eval_loss": 0.8113335371017456,
|
| 902 |
+
"eval_runtime": 0.5509,
|
| 903 |
+
"eval_samples_per_second": 130.706,
|
| 904 |
+
"eval_steps_per_second": 9.077,
|
| 905 |
+
"step": 56
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 6.333333333333333,
|
| 909 |
+
"grad_norm": 8.366003036499023,
|
| 910 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 911 |
+
"loss": 0.7423,
|
| 912 |
+
"step": 57
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 6.333333333333333,
|
| 916 |
+
"eval_accuracy": 0.3888888888888889,
|
| 917 |
+
"eval_loss": 0.8116319179534912,
|
| 918 |
+
"eval_runtime": 0.5995,
|
| 919 |
+
"eval_samples_per_second": 120.099,
|
| 920 |
+
"eval_steps_per_second": 8.34,
|
| 921 |
+
"step": 57
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 6.444444444444445,
|
| 925 |
+
"grad_norm": 2.654489517211914,
|
| 926 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 927 |
+
"loss": 0.7059,
|
| 928 |
+
"step": 58
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 6.444444444444445,
|
| 932 |
+
"eval_accuracy": 0.3888888888888889,
|
| 933 |
+
"eval_loss": 0.8082817792892456,
|
| 934 |
+
"eval_runtime": 0.5516,
|
| 935 |
+
"eval_samples_per_second": 130.519,
|
| 936 |
+
"eval_steps_per_second": 9.064,
|
| 937 |
+
"step": 58
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 6.555555555555555,
|
| 941 |
+
"grad_norm": 9.320557594299316,
|
| 942 |
+
"learning_rate": 1.7613636363636366e-05,
|
| 943 |
+
"loss": 0.7396,
|
| 944 |
+
"step": 59
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 6.555555555555555,
|
| 948 |
+
"eval_accuracy": 0.375,
|
| 949 |
+
"eval_loss": 0.8052436113357544,
|
| 950 |
+
"eval_runtime": 0.5998,
|
| 951 |
+
"eval_samples_per_second": 120.045,
|
| 952 |
+
"eval_steps_per_second": 8.336,
|
| 953 |
+
"step": 59
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 6.666666666666667,
|
| 957 |
+
"grad_norm": 7.24456787109375,
|
| 958 |
+
"learning_rate": 1.7045454545454546e-05,
|
| 959 |
+
"loss": 0.6561,
|
| 960 |
+
"step": 60
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 6.666666666666667,
|
| 964 |
+
"eval_accuracy": 0.375,
|
| 965 |
+
"eval_loss": 0.8018798828125,
|
| 966 |
+
"eval_runtime": 0.5995,
|
| 967 |
+
"eval_samples_per_second": 120.107,
|
| 968 |
+
"eval_steps_per_second": 8.341,
|
| 969 |
+
"step": 60
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 6.777777777777778,
|
| 973 |
+
"grad_norm": 7.286713123321533,
|
| 974 |
+
"learning_rate": 1.6477272727272726e-05,
|
| 975 |
+
"loss": 0.7355,
|
| 976 |
+
"step": 61
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 6.777777777777778,
|
| 980 |
+
"eval_accuracy": 0.375,
|
| 981 |
+
"eval_loss": 0.8011067509651184,
|
| 982 |
+
"eval_runtime": 0.6,
|
| 983 |
+
"eval_samples_per_second": 119.998,
|
| 984 |
+
"eval_steps_per_second": 8.333,
|
| 985 |
+
"step": 61
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 6.888888888888889,
|
| 989 |
+
"grad_norm": 4.26874303817749,
|
| 990 |
+
"learning_rate": 1.590909090909091e-05,
|
| 991 |
+
"loss": 0.7353,
|
| 992 |
+
"step": 62
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 6.888888888888889,
|
| 996 |
+
"eval_accuracy": 0.375,
|
| 997 |
+
"eval_loss": 0.7994384765625,
|
| 998 |
+
"eval_runtime": 0.5529,
|
| 999 |
+
"eval_samples_per_second": 130.221,
|
| 1000 |
+
"eval_steps_per_second": 9.043,
|
| 1001 |
+
"step": 62
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 7.0,
|
| 1005 |
+
"grad_norm": 3.4262943267822266,
|
| 1006 |
+
"learning_rate": 1.534090909090909e-05,
|
| 1007 |
+
"loss": 0.6377,
|
| 1008 |
+
"step": 63
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 7.0,
|
| 1012 |
+
"eval_accuracy": 0.375,
|
| 1013 |
+
"eval_loss": 0.7936333417892456,
|
| 1014 |
+
"eval_runtime": 0.5486,
|
| 1015 |
+
"eval_samples_per_second": 131.251,
|
| 1016 |
+
"eval_steps_per_second": 9.115,
|
| 1017 |
+
"step": 63
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 7.111111111111111,
|
| 1021 |
+
"grad_norm": 5.528657913208008,
|
| 1022 |
+
"learning_rate": 1.4772727272727274e-05,
|
| 1023 |
+
"loss": 0.6874,
|
| 1024 |
+
"step": 64
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 7.111111111111111,
|
| 1028 |
+
"eval_accuracy": 0.375,
|
| 1029 |
+
"eval_loss": 0.7888047695159912,
|
| 1030 |
+
"eval_runtime": 0.6014,
|
| 1031 |
+
"eval_samples_per_second": 119.712,
|
| 1032 |
+
"eval_steps_per_second": 8.313,
|
| 1033 |
+
"step": 64
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 7.222222222222222,
|
| 1037 |
+
"grad_norm": 5.771848678588867,
|
| 1038 |
+
"learning_rate": 1.4204545454545456e-05,
|
| 1039 |
+
"loss": 0.7112,
|
| 1040 |
+
"step": 65
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 7.222222222222222,
|
| 1044 |
+
"eval_accuracy": 0.3611111111111111,
|
| 1045 |
+
"eval_loss": 0.7859971523284912,
|
| 1046 |
+
"eval_runtime": 0.6005,
|
| 1047 |
+
"eval_samples_per_second": 119.903,
|
| 1048 |
+
"eval_steps_per_second": 8.327,
|
| 1049 |
+
"step": 65
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 7.333333333333333,
|
| 1053 |
+
"grad_norm": 8.485419273376465,
|
| 1054 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 1055 |
+
"loss": 0.6282,
|
| 1056 |
+
"step": 66
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 7.333333333333333,
|
| 1060 |
+
"eval_accuracy": 0.3611111111111111,
|
| 1061 |
+
"eval_loss": 0.7813856601715088,
|
| 1062 |
+
"eval_runtime": 0.6515,
|
| 1063 |
+
"eval_samples_per_second": 110.513,
|
| 1064 |
+
"eval_steps_per_second": 7.675,
|
| 1065 |
+
"step": 66
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 7.444444444444445,
|
| 1069 |
+
"grad_norm": 10.057698249816895,
|
| 1070 |
+
"learning_rate": 1.3068181818181819e-05,
|
| 1071 |
+
"loss": 0.6793,
|
| 1072 |
+
"step": 67
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 7.444444444444445,
|
| 1076 |
+
"eval_accuracy": 0.375,
|
| 1077 |
+
"eval_loss": 0.7774929404258728,
|
| 1078 |
+
"eval_runtime": 0.5496,
|
| 1079 |
+
"eval_samples_per_second": 131.003,
|
| 1080 |
+
"eval_steps_per_second": 9.097,
|
| 1081 |
+
"step": 67
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 7.555555555555555,
|
| 1085 |
+
"grad_norm": 9.190048217773438,
|
| 1086 |
+
"learning_rate": 1.25e-05,
|
| 1087 |
+
"loss": 0.6707,
|
| 1088 |
+
"step": 68
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 7.555555555555555,
|
| 1092 |
+
"eval_accuracy": 0.3888888888888889,
|
| 1093 |
+
"eval_loss": 0.7748887538909912,
|
| 1094 |
+
"eval_runtime": 0.5517,
|
| 1095 |
+
"eval_samples_per_second": 130.502,
|
| 1096 |
+
"eval_steps_per_second": 9.063,
|
| 1097 |
+
"step": 68
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 7.666666666666667,
|
| 1101 |
+
"grad_norm": 6.497270107269287,
|
| 1102 |
+
"learning_rate": 1.1931818181818183e-05,
|
| 1103 |
+
"loss": 0.6571,
|
| 1104 |
+
"step": 69
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 7.666666666666667,
|
| 1108 |
+
"eval_accuracy": 0.375,
|
| 1109 |
+
"eval_loss": 0.77294921875,
|
| 1110 |
+
"eval_runtime": 0.5507,
|
| 1111 |
+
"eval_samples_per_second": 130.752,
|
| 1112 |
+
"eval_steps_per_second": 9.08,
|
| 1113 |
+
"step": 69
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 7.777777777777778,
|
| 1117 |
+
"grad_norm": 5.636641025543213,
|
| 1118 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 1119 |
+
"loss": 0.6539,
|
| 1120 |
+
"step": 70
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 7.777777777777778,
|
| 1124 |
+
"eval_accuracy": 0.3611111111111111,
|
| 1125 |
+
"eval_loss": 0.7728678584098816,
|
| 1126 |
+
"eval_runtime": 0.5491,
|
| 1127 |
+
"eval_samples_per_second": 131.117,
|
| 1128 |
+
"eval_steps_per_second": 9.105,
|
| 1129 |
+
"step": 70
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 7.888888888888889,
|
| 1133 |
+
"grad_norm": 4.822576522827148,
|
| 1134 |
+
"learning_rate": 1.0795454545454547e-05,
|
| 1135 |
+
"loss": 0.6953,
|
| 1136 |
+
"step": 71
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 7.888888888888889,
|
| 1140 |
+
"eval_accuracy": 0.3472222222222222,
|
| 1141 |
+
"eval_loss": 0.7734103798866272,
|
| 1142 |
+
"eval_runtime": 0.5482,
|
| 1143 |
+
"eval_samples_per_second": 131.348,
|
| 1144 |
+
"eval_steps_per_second": 9.121,
|
| 1145 |
+
"step": 71
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 8.0,
|
| 1149 |
+
"grad_norm": 7.65333366394043,
|
| 1150 |
+
"learning_rate": 1.0227272727272729e-05,
|
| 1151 |
+
"loss": 0.7214,
|
| 1152 |
+
"step": 72
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 8.0,
|
| 1156 |
+
"eval_accuracy": 0.3611111111111111,
|
| 1157 |
+
"eval_loss": 0.7741156816482544,
|
| 1158 |
+
"eval_runtime": 0.6017,
|
| 1159 |
+
"eval_samples_per_second": 119.662,
|
| 1160 |
+
"eval_steps_per_second": 8.31,
|
| 1161 |
+
"step": 72
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 8.11111111111111,
|
| 1165 |
+
"grad_norm": 8.882245063781738,
|
| 1166 |
+
"learning_rate": 9.659090909090909e-06,
|
| 1167 |
+
"loss": 0.722,
|
| 1168 |
+
"step": 73
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 8.11111111111111,
|
| 1172 |
+
"eval_accuracy": 0.3472222222222222,
|
| 1173 |
+
"eval_loss": 0.7755805253982544,
|
| 1174 |
+
"eval_runtime": 0.5489,
|
| 1175 |
+
"eval_samples_per_second": 131.162,
|
| 1176 |
+
"eval_steps_per_second": 9.108,
|
| 1177 |
+
"step": 73
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 8.222222222222221,
|
| 1181 |
+
"grad_norm": 3.2345800399780273,
|
| 1182 |
+
"learning_rate": 9.090909090909091e-06,
|
| 1183 |
+
"loss": 0.6578,
|
| 1184 |
+
"step": 74
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 8.222222222222221,
|
| 1188 |
+
"eval_accuracy": 0.3472222222222222,
|
| 1189 |
+
"eval_loss": 0.771728515625,
|
| 1190 |
+
"eval_runtime": 0.6516,
|
| 1191 |
+
"eval_samples_per_second": 110.506,
|
| 1192 |
+
"eval_steps_per_second": 7.674,
|
| 1193 |
+
"step": 74
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 8.333333333333334,
|
| 1197 |
+
"grad_norm": 4.6726484298706055,
|
| 1198 |
+
"learning_rate": 8.522727272727273e-06,
|
| 1199 |
+
"loss": 0.7094,
|
| 1200 |
+
"step": 75
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 8.333333333333334,
|
| 1204 |
+
"eval_accuracy": 0.3472222222222222,
|
| 1205 |
+
"eval_loss": 0.7747802734375,
|
| 1206 |
+
"eval_runtime": 0.5499,
|
| 1207 |
+
"eval_samples_per_second": 130.927,
|
| 1208 |
+
"eval_steps_per_second": 9.092,
|
| 1209 |
+
"step": 75
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 8.444444444444445,
|
| 1213 |
+
"grad_norm": 16.0637264251709,
|
| 1214 |
+
"learning_rate": 7.954545454545455e-06,
|
| 1215 |
+
"loss": 0.7181,
|
| 1216 |
+
"step": 76
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 8.444444444444445,
|
| 1220 |
+
"eval_accuracy": 0.375,
|
| 1221 |
+
"eval_loss": 0.7764350175857544,
|
| 1222 |
+
"eval_runtime": 0.7006,
|
| 1223 |
+
"eval_samples_per_second": 102.77,
|
| 1224 |
+
"eval_steps_per_second": 7.137,
|
| 1225 |
+
"step": 76
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 8.555555555555555,
|
| 1229 |
+
"grad_norm": 4.427946090698242,
|
| 1230 |
+
"learning_rate": 7.386363636363637e-06,
|
| 1231 |
+
"loss": 0.6544,
|
| 1232 |
+
"step": 77
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 8.555555555555555,
|
| 1236 |
+
"eval_accuracy": 0.3472222222222222,
|
| 1237 |
+
"eval_loss": 0.7750922441482544,
|
| 1238 |
+
"eval_runtime": 0.5503,
|
| 1239 |
+
"eval_samples_per_second": 130.846,
|
| 1240 |
+
"eval_steps_per_second": 9.086,
|
| 1241 |
+
"step": 77
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 8.666666666666666,
|
| 1245 |
+
"grad_norm": 3.1340301036834717,
|
| 1246 |
+
"learning_rate": 6.818181818181818e-06,
|
| 1247 |
+
"loss": 0.6482,
|
| 1248 |
+
"step": 78
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 8.666666666666666,
|
| 1252 |
+
"eval_accuracy": 0.3472222222222222,
|
| 1253 |
+
"eval_loss": 0.7764485478401184,
|
| 1254 |
+
"eval_runtime": 0.6071,
|
| 1255 |
+
"eval_samples_per_second": 118.588,
|
| 1256 |
+
"eval_steps_per_second": 8.235,
|
| 1257 |
+
"step": 78
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 8.777777777777779,
|
| 1261 |
+
"grad_norm": 14.458281517028809,
|
| 1262 |
+
"learning_rate": 6.25e-06,
|
| 1263 |
+
"loss": 0.7313,
|
| 1264 |
+
"step": 79
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 8.777777777777779,
|
| 1268 |
+
"eval_accuracy": 0.3472222222222222,
|
| 1269 |
+
"eval_loss": 0.7769097089767456,
|
| 1270 |
+
"eval_runtime": 0.6033,
|
| 1271 |
+
"eval_samples_per_second": 119.344,
|
| 1272 |
+
"eval_steps_per_second": 8.288,
|
| 1273 |
+
"step": 79
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 8.88888888888889,
|
| 1277 |
+
"grad_norm": 10.602180480957031,
|
| 1278 |
+
"learning_rate": 5.681818181818182e-06,
|
| 1279 |
+
"loss": 0.7158,
|
| 1280 |
+
"step": 80
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 8.88888888888889,
|
| 1284 |
+
"eval_accuracy": 0.3611111111111111,
|
| 1285 |
+
"eval_loss": 0.7765977382659912,
|
| 1286 |
+
"eval_runtime": 0.7058,
|
| 1287 |
+
"eval_samples_per_second": 102.018,
|
| 1288 |
+
"eval_steps_per_second": 7.085,
|
| 1289 |
+
"step": 80
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 9.0,
|
| 1293 |
+
"grad_norm": 8.127225875854492,
|
| 1294 |
+
"learning_rate": 5.113636363636364e-06,
|
| 1295 |
+
"loss": 0.6447,
|
| 1296 |
+
"step": 81
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 9.0,
|
| 1300 |
+
"eval_accuracy": 0.3472222222222222,
|
| 1301 |
+
"eval_loss": 0.7755669355392456,
|
| 1302 |
+
"eval_runtime": 0.6543,
|
| 1303 |
+
"eval_samples_per_second": 110.049,
|
| 1304 |
+
"eval_steps_per_second": 7.642,
|
| 1305 |
+
"step": 81
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 9.11111111111111,
|
| 1309 |
+
"grad_norm": 6.457716464996338,
|
| 1310 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 1311 |
+
"loss": 0.6601,
|
| 1312 |
+
"step": 82
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 9.11111111111111,
|
| 1316 |
+
"eval_accuracy": 0.3333333333333333,
|
| 1317 |
+
"eval_loss": 0.7762587070465088,
|
| 1318 |
+
"eval_runtime": 0.6069,
|
| 1319 |
+
"eval_samples_per_second": 118.636,
|
| 1320 |
+
"eval_steps_per_second": 8.239,
|
| 1321 |
+
"step": 82
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 9.222222222222221,
|
| 1325 |
+
"grad_norm": 3.813633918762207,
|
| 1326 |
+
"learning_rate": 3.9772727272727275e-06,
|
| 1327 |
+
"loss": 0.7732,
|
| 1328 |
+
"step": 83
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 9.222222222222221,
|
| 1332 |
+
"eval_accuracy": 0.3888888888888889,
|
| 1333 |
+
"eval_loss": 0.7770453691482544,
|
| 1334 |
+
"eval_runtime": 0.7076,
|
| 1335 |
+
"eval_samples_per_second": 101.748,
|
| 1336 |
+
"eval_steps_per_second": 7.066,
|
| 1337 |
+
"step": 83
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 9.333333333333334,
|
| 1341 |
+
"grad_norm": 10.45854377746582,
|
| 1342 |
+
"learning_rate": 3.409090909090909e-06,
|
| 1343 |
+
"loss": 0.6657,
|
| 1344 |
+
"step": 84
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 9.333333333333334,
|
| 1348 |
+
"eval_accuracy": 0.3888888888888889,
|
| 1349 |
+
"eval_loss": 0.7784559726715088,
|
| 1350 |
+
"eval_runtime": 0.7109,
|
| 1351 |
+
"eval_samples_per_second": 101.287,
|
| 1352 |
+
"eval_steps_per_second": 7.034,
|
| 1353 |
+
"step": 84
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 9.444444444444445,
|
| 1357 |
+
"grad_norm": 4.11740255355835,
|
| 1358 |
+
"learning_rate": 2.840909090909091e-06,
|
| 1359 |
+
"loss": 0.716,
|
| 1360 |
+
"step": 85
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 9.444444444444445,
|
| 1364 |
+
"eval_accuracy": 0.3888888888888889,
|
| 1365 |
+
"eval_loss": 0.7778727412223816,
|
| 1366 |
+
"eval_runtime": 0.5543,
|
| 1367 |
+
"eval_samples_per_second": 129.897,
|
| 1368 |
+
"eval_steps_per_second": 9.021,
|
| 1369 |
+
"step": 85
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 9.555555555555555,
|
| 1373 |
+
"grad_norm": 10.107967376708984,
|
| 1374 |
+
"learning_rate": 2.2727272727272728e-06,
|
| 1375 |
+
"loss": 0.7518,
|
| 1376 |
+
"step": 86
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 9.555555555555555,
|
| 1380 |
+
"eval_accuracy": 0.3888888888888889,
|
| 1381 |
+
"eval_loss": 0.7781982421875,
|
| 1382 |
+
"eval_runtime": 0.6493,
|
| 1383 |
+
"eval_samples_per_second": 110.892,
|
| 1384 |
+
"eval_steps_per_second": 7.701,
|
| 1385 |
+
"step": 86
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 9.666666666666666,
|
| 1389 |
+
"grad_norm": 6.475906848907471,
|
| 1390 |
+
"learning_rate": 1.7045454545454546e-06,
|
| 1391 |
+
"loss": 0.713,
|
| 1392 |
+
"step": 87
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 9.666666666666666,
|
| 1396 |
+
"eval_accuracy": 0.3888888888888889,
|
| 1397 |
+
"eval_loss": 0.7775471806526184,
|
| 1398 |
+
"eval_runtime": 0.5511,
|
| 1399 |
+
"eval_samples_per_second": 130.655,
|
| 1400 |
+
"eval_steps_per_second": 9.073,
|
| 1401 |
+
"step": 87
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 9.777777777777779,
|
| 1405 |
+
"grad_norm": 11.71182632446289,
|
| 1406 |
+
"learning_rate": 1.1363636363636364e-06,
|
| 1407 |
+
"loss": 0.6931,
|
| 1408 |
+
"step": 88
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 9.777777777777779,
|
| 1412 |
+
"eval_accuracy": 0.375,
|
| 1413 |
+
"eval_loss": 0.7794325351715088,
|
| 1414 |
+
"eval_runtime": 0.5536,
|
| 1415 |
+
"eval_samples_per_second": 130.057,
|
| 1416 |
+
"eval_steps_per_second": 9.032,
|
| 1417 |
+
"step": 88
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 9.88888888888889,
|
| 1421 |
+
"grad_norm": 8.962738037109375,
|
| 1422 |
+
"learning_rate": 5.681818181818182e-07,
|
| 1423 |
+
"loss": 0.7001,
|
| 1424 |
+
"step": 89
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 9.88888888888889,
|
| 1428 |
+
"eval_accuracy": 0.3888888888888889,
|
| 1429 |
+
"eval_loss": 0.7806532382965088,
|
| 1430 |
+
"eval_runtime": 0.6003,
|
| 1431 |
+
"eval_samples_per_second": 119.933,
|
| 1432 |
+
"eval_steps_per_second": 8.329,
|
| 1433 |
+
"step": 89
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 10.0,
|
| 1437 |
+
"grad_norm": 8.880528450012207,
|
| 1438 |
+
"learning_rate": 0.0,
|
| 1439 |
+
"loss": 0.6525,
|
| 1440 |
+
"step": 90
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 10.0,
|
| 1444 |
+
"eval_accuracy": 0.3888888888888889,
|
| 1445 |
+
"eval_loss": 0.7818332314491272,
|
| 1446 |
+
"eval_runtime": 0.6538,
|
| 1447 |
+
"eval_samples_per_second": 110.129,
|
| 1448 |
+
"eval_steps_per_second": 7.648,
|
| 1449 |
+
"step": 90
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 10.0,
|
| 1453 |
+
"step": 90,
|
| 1454 |
+
"total_flos": 13264513597440.0,
|
| 1455 |
+
"train_loss": 0.7229804992675781,
|
| 1456 |
+
"train_runtime": 239.59,
|
| 1457 |
+
"train_samples_per_second": 11.854,
|
| 1458 |
+
"train_steps_per_second": 0.376
|
| 1459 |
+
}
|
| 1460 |
+
],
|
| 1461 |
+
"logging_steps": 1,
|
| 1462 |
+
"max_steps": 90,
|
| 1463 |
+
"num_input_tokens_seen": 0,
|
| 1464 |
+
"num_train_epochs": 10,
|
| 1465 |
+
"save_steps": 500,
|
| 1466 |
+
"total_flos": 13264513597440.0,
|
| 1467 |
+
"train_batch_size": 4,
|
| 1468 |
+
"trial_name": null,
|
| 1469 |
+
"trial_params": null
|
| 1470 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e9990005b16fc0a36be93d38f8df0bc9aa0be7ce28edd70ead99fe2ce980025
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|