Task: SequenceClassification
Browse files- README.md +202 -0
- adapter_config.json +35 -0
- adapter_model.safetensors +3 -0
- merges.txt +0 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +30 -0
- trainer_state-opt-bnb8-QLORA-super_glue-wic-sequence_classification.json +1950 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: facebook/opt-6.7b
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "facebook/opt-6.7b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": [
|
| 18 |
+
"score"
|
| 19 |
+
],
|
| 20 |
+
"peft_type": "LORA",
|
| 21 |
+
"r": 8,
|
| 22 |
+
"rank_pattern": {},
|
| 23 |
+
"revision": null,
|
| 24 |
+
"target_modules": [
|
| 25 |
+
"q_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"fc2",
|
| 28 |
+
"out_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"fc1"
|
| 31 |
+
],
|
| 32 |
+
"task_type": "SEQ_CLS",
|
| 33 |
+
"use_dora": false,
|
| 34 |
+
"use_rslora": false
|
| 35 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a668d1baf516b5449a0212f3affe45868b581232297f30228fa1c838ebf8f509
|
| 3 |
+
size 75583208
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "</s>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"1": {
|
| 6 |
+
"content": "<pad>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"2": {
|
| 14 |
+
"content": "</s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"bos_token": "</s>",
|
| 23 |
+
"clean_up_tokenization_spaces": true,
|
| 24 |
+
"eos_token": "</s>",
|
| 25 |
+
"errors": "replace",
|
| 26 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 27 |
+
"pad_token": "</s>",
|
| 28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 29 |
+
"unk_token": "</s>"
|
| 30 |
+
}
|
trainer_state-opt-bnb8-QLORA-super_glue-wic-sequence_classification.json
ADDED
|
@@ -0,0 +1,1950 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.6,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 120,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"grad_norm": 15.745562553405762,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 0.8605,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"eval_accuracy": 0.484,
|
| 21 |
+
"eval_loss": 0.8637617230415344,
|
| 22 |
+
"eval_runtime": 2.5683,
|
| 23 |
+
"eval_samples_per_second": 97.341,
|
| 24 |
+
"eval_steps_per_second": 2.726,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.16,
|
| 29 |
+
"grad_norm": 19.96647834777832,
|
| 30 |
+
"learning_rate": 5e-05,
|
| 31 |
+
"loss": 0.9163,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.16,
|
| 36 |
+
"eval_accuracy": 0.488,
|
| 37 |
+
"eval_loss": 0.810189425945282,
|
| 38 |
+
"eval_runtime": 2.552,
|
| 39 |
+
"eval_samples_per_second": 97.963,
|
| 40 |
+
"eval_steps_per_second": 2.743,
|
| 41 |
+
"step": 2
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.24,
|
| 45 |
+
"grad_norm": 19.000354766845703,
|
| 46 |
+
"learning_rate": 4.957627118644068e-05,
|
| 47 |
+
"loss": 0.8681,
|
| 48 |
+
"step": 3
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.24,
|
| 52 |
+
"eval_accuracy": 0.516,
|
| 53 |
+
"eval_loss": 0.7167539000511169,
|
| 54 |
+
"eval_runtime": 2.5526,
|
| 55 |
+
"eval_samples_per_second": 97.938,
|
| 56 |
+
"eval_steps_per_second": 2.742,
|
| 57 |
+
"step": 3
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.32,
|
| 61 |
+
"grad_norm": 4.575774669647217,
|
| 62 |
+
"learning_rate": 4.915254237288136e-05,
|
| 63 |
+
"loss": 0.6484,
|
| 64 |
+
"step": 4
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.32,
|
| 68 |
+
"eval_accuracy": 0.52,
|
| 69 |
+
"eval_loss": 0.7121953368186951,
|
| 70 |
+
"eval_runtime": 2.5001,
|
| 71 |
+
"eval_samples_per_second": 99.994,
|
| 72 |
+
"eval_steps_per_second": 2.8,
|
| 73 |
+
"step": 4
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.4,
|
| 77 |
+
"grad_norm": 2.526747703552246,
|
| 78 |
+
"learning_rate": 4.8728813559322034e-05,
|
| 79 |
+
"loss": 0.7006,
|
| 80 |
+
"step": 5
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.4,
|
| 84 |
+
"eval_accuracy": 0.516,
|
| 85 |
+
"eval_loss": 0.7209541201591492,
|
| 86 |
+
"eval_runtime": 2.5542,
|
| 87 |
+
"eval_samples_per_second": 97.879,
|
| 88 |
+
"eval_steps_per_second": 2.741,
|
| 89 |
+
"step": 5
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.48,
|
| 93 |
+
"grad_norm": 2.2623257637023926,
|
| 94 |
+
"learning_rate": 4.8305084745762714e-05,
|
| 95 |
+
"loss": 0.6587,
|
| 96 |
+
"step": 6
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.48,
|
| 100 |
+
"eval_accuracy": 0.516,
|
| 101 |
+
"eval_loss": 0.737973153591156,
|
| 102 |
+
"eval_runtime": 2.553,
|
| 103 |
+
"eval_samples_per_second": 97.925,
|
| 104 |
+
"eval_steps_per_second": 2.742,
|
| 105 |
+
"step": 6
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.56,
|
| 109 |
+
"grad_norm": 6.5833001136779785,
|
| 110 |
+
"learning_rate": 4.788135593220339e-05,
|
| 111 |
+
"loss": 0.6634,
|
| 112 |
+
"step": 7
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.56,
|
| 116 |
+
"eval_accuracy": 0.516,
|
| 117 |
+
"eval_loss": 0.7435795664787292,
|
| 118 |
+
"eval_runtime": 2.5637,
|
| 119 |
+
"eval_samples_per_second": 97.517,
|
| 120 |
+
"eval_steps_per_second": 2.73,
|
| 121 |
+
"step": 7
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.64,
|
| 125 |
+
"grad_norm": 11.965208053588867,
|
| 126 |
+
"learning_rate": 4.745762711864407e-05,
|
| 127 |
+
"loss": 0.7901,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.64,
|
| 132 |
+
"eval_accuracy": 0.516,
|
| 133 |
+
"eval_loss": 0.7358012795448303,
|
| 134 |
+
"eval_runtime": 2.5517,
|
| 135 |
+
"eval_samples_per_second": 97.974,
|
| 136 |
+
"eval_steps_per_second": 2.743,
|
| 137 |
+
"step": 8
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.72,
|
| 141 |
+
"grad_norm": 11.749293327331543,
|
| 142 |
+
"learning_rate": 4.703389830508475e-05,
|
| 143 |
+
"loss": 0.7845,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.72,
|
| 148 |
+
"eval_accuracy": 0.512,
|
| 149 |
+
"eval_loss": 0.7179194092750549,
|
| 150 |
+
"eval_runtime": 2.5585,
|
| 151 |
+
"eval_samples_per_second": 97.713,
|
| 152 |
+
"eval_steps_per_second": 2.736,
|
| 153 |
+
"step": 9
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.8,
|
| 157 |
+
"grad_norm": 7.4664130210876465,
|
| 158 |
+
"learning_rate": 4.6610169491525425e-05,
|
| 159 |
+
"loss": 0.9122,
|
| 160 |
+
"step": 10
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.8,
|
| 164 |
+
"eval_accuracy": 0.484,
|
| 165 |
+
"eval_loss": 0.6973310708999634,
|
| 166 |
+
"eval_runtime": 2.5527,
|
| 167 |
+
"eval_samples_per_second": 97.934,
|
| 168 |
+
"eval_steps_per_second": 2.742,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.88,
|
| 173 |
+
"grad_norm": 5.599862098693848,
|
| 174 |
+
"learning_rate": 4.6186440677966104e-05,
|
| 175 |
+
"loss": 0.7581,
|
| 176 |
+
"step": 11
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.88,
|
| 180 |
+
"eval_accuracy": 0.512,
|
| 181 |
+
"eval_loss": 0.6890488266944885,
|
| 182 |
+
"eval_runtime": 2.5516,
|
| 183 |
+
"eval_samples_per_second": 97.976,
|
| 184 |
+
"eval_steps_per_second": 2.743,
|
| 185 |
+
"step": 11
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.96,
|
| 189 |
+
"grad_norm": 5.2170634269714355,
|
| 190 |
+
"learning_rate": 4.5762711864406784e-05,
|
| 191 |
+
"loss": 0.6821,
|
| 192 |
+
"step": 12
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.96,
|
| 196 |
+
"eval_accuracy": 0.512,
|
| 197 |
+
"eval_loss": 0.6933399438858032,
|
| 198 |
+
"eval_runtime": 2.5513,
|
| 199 |
+
"eval_samples_per_second": 97.991,
|
| 200 |
+
"eval_steps_per_second": 2.744,
|
| 201 |
+
"step": 12
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.04,
|
| 205 |
+
"grad_norm": 5.609626293182373,
|
| 206 |
+
"learning_rate": 4.533898305084746e-05,
|
| 207 |
+
"loss": 0.6992,
|
| 208 |
+
"step": 13
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.04,
|
| 212 |
+
"eval_accuracy": 0.512,
|
| 213 |
+
"eval_loss": 0.7035390734672546,
|
| 214 |
+
"eval_runtime": 2.5496,
|
| 215 |
+
"eval_samples_per_second": 98.056,
|
| 216 |
+
"eval_steps_per_second": 2.746,
|
| 217 |
+
"step": 13
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.12,
|
| 221 |
+
"grad_norm": 7.854551792144775,
|
| 222 |
+
"learning_rate": 4.491525423728814e-05,
|
| 223 |
+
"loss": 0.7384,
|
| 224 |
+
"step": 14
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.12,
|
| 228 |
+
"eval_accuracy": 0.516,
|
| 229 |
+
"eval_loss": 0.710085928440094,
|
| 230 |
+
"eval_runtime": 2.5489,
|
| 231 |
+
"eval_samples_per_second": 98.08,
|
| 232 |
+
"eval_steps_per_second": 2.746,
|
| 233 |
+
"step": 14
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.2,
|
| 237 |
+
"grad_norm": 5.026305198669434,
|
| 238 |
+
"learning_rate": 4.4491525423728816e-05,
|
| 239 |
+
"loss": 0.7223,
|
| 240 |
+
"step": 15
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.2,
|
| 244 |
+
"eval_accuracy": 0.508,
|
| 245 |
+
"eval_loss": 0.7157421708106995,
|
| 246 |
+
"eval_runtime": 2.5501,
|
| 247 |
+
"eval_samples_per_second": 98.036,
|
| 248 |
+
"eval_steps_per_second": 2.745,
|
| 249 |
+
"step": 15
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.28,
|
| 253 |
+
"grad_norm": 13.441658973693848,
|
| 254 |
+
"learning_rate": 4.4067796610169495e-05,
|
| 255 |
+
"loss": 0.7687,
|
| 256 |
+
"step": 16
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.28,
|
| 260 |
+
"eval_accuracy": 0.508,
|
| 261 |
+
"eval_loss": 0.7153124809265137,
|
| 262 |
+
"eval_runtime": 2.5486,
|
| 263 |
+
"eval_samples_per_second": 98.095,
|
| 264 |
+
"eval_steps_per_second": 2.747,
|
| 265 |
+
"step": 16
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.3599999999999999,
|
| 269 |
+
"grad_norm": 7.546152591705322,
|
| 270 |
+
"learning_rate": 4.3644067796610175e-05,
|
| 271 |
+
"loss": 0.7453,
|
| 272 |
+
"step": 17
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.3599999999999999,
|
| 276 |
+
"eval_accuracy": 0.512,
|
| 277 |
+
"eval_loss": 0.7087851762771606,
|
| 278 |
+
"eval_runtime": 2.5485,
|
| 279 |
+
"eval_samples_per_second": 98.095,
|
| 280 |
+
"eval_steps_per_second": 2.747,
|
| 281 |
+
"step": 17
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.44,
|
| 285 |
+
"grad_norm": 3.2455766201019287,
|
| 286 |
+
"learning_rate": 4.3220338983050854e-05,
|
| 287 |
+
"loss": 0.7231,
|
| 288 |
+
"step": 18
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.44,
|
| 292 |
+
"eval_accuracy": 0.512,
|
| 293 |
+
"eval_loss": 0.6991875171661377,
|
| 294 |
+
"eval_runtime": 2.5539,
|
| 295 |
+
"eval_samples_per_second": 97.889,
|
| 296 |
+
"eval_steps_per_second": 2.741,
|
| 297 |
+
"step": 18
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.52,
|
| 301 |
+
"grad_norm": 8.115966796875,
|
| 302 |
+
"learning_rate": 4.279661016949153e-05,
|
| 303 |
+
"loss": 0.7162,
|
| 304 |
+
"step": 19
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.52,
|
| 308 |
+
"eval_accuracy": 0.516,
|
| 309 |
+
"eval_loss": 0.6926875114440918,
|
| 310 |
+
"eval_runtime": 2.548,
|
| 311 |
+
"eval_samples_per_second": 98.118,
|
| 312 |
+
"eval_steps_per_second": 2.747,
|
| 313 |
+
"step": 19
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.6,
|
| 317 |
+
"grad_norm": 2.57649564743042,
|
| 318 |
+
"learning_rate": 4.2372881355932206e-05,
|
| 319 |
+
"loss": 0.6927,
|
| 320 |
+
"step": 20
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.6,
|
| 324 |
+
"eval_accuracy": 0.516,
|
| 325 |
+
"eval_loss": 0.688406229019165,
|
| 326 |
+
"eval_runtime": 2.5496,
|
| 327 |
+
"eval_samples_per_second": 98.054,
|
| 328 |
+
"eval_steps_per_second": 2.746,
|
| 329 |
+
"step": 20
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.6800000000000002,
|
| 333 |
+
"grad_norm": 2.991580009460449,
|
| 334 |
+
"learning_rate": 4.1949152542372886e-05,
|
| 335 |
+
"loss": 0.7097,
|
| 336 |
+
"step": 21
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.6800000000000002,
|
| 340 |
+
"eval_accuracy": 0.536,
|
| 341 |
+
"eval_loss": 0.6855859160423279,
|
| 342 |
+
"eval_runtime": 2.5522,
|
| 343 |
+
"eval_samples_per_second": 97.953,
|
| 344 |
+
"eval_steps_per_second": 2.743,
|
| 345 |
+
"step": 21
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.76,
|
| 349 |
+
"grad_norm": 2.709691286087036,
|
| 350 |
+
"learning_rate": 4.152542372881356e-05,
|
| 351 |
+
"loss": 0.6887,
|
| 352 |
+
"step": 22
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.76,
|
| 356 |
+
"eval_accuracy": 0.504,
|
| 357 |
+
"eval_loss": 0.6868593692779541,
|
| 358 |
+
"eval_runtime": 2.5523,
|
| 359 |
+
"eval_samples_per_second": 97.95,
|
| 360 |
+
"eval_steps_per_second": 2.743,
|
| 361 |
+
"step": 22
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.8399999999999999,
|
| 365 |
+
"grad_norm": 5.620818138122559,
|
| 366 |
+
"learning_rate": 4.110169491525424e-05,
|
| 367 |
+
"loss": 0.6656,
|
| 368 |
+
"step": 23
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.8399999999999999,
|
| 372 |
+
"eval_accuracy": 0.48,
|
| 373 |
+
"eval_loss": 0.6900019645690918,
|
| 374 |
+
"eval_runtime": 2.5504,
|
| 375 |
+
"eval_samples_per_second": 98.023,
|
| 376 |
+
"eval_steps_per_second": 2.745,
|
| 377 |
+
"step": 23
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.92,
|
| 381 |
+
"grad_norm": 12.563273429870605,
|
| 382 |
+
"learning_rate": 4.067796610169492e-05,
|
| 383 |
+
"loss": 0.7211,
|
| 384 |
+
"step": 24
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.92,
|
| 388 |
+
"eval_accuracy": 0.5,
|
| 389 |
+
"eval_loss": 0.6927011609077454,
|
| 390 |
+
"eval_runtime": 2.5512,
|
| 391 |
+
"eval_samples_per_second": 97.994,
|
| 392 |
+
"eval_steps_per_second": 2.744,
|
| 393 |
+
"step": 24
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.0,
|
| 397 |
+
"grad_norm": 3.7670013904571533,
|
| 398 |
+
"learning_rate": 4.025423728813559e-05,
|
| 399 |
+
"loss": 0.7575,
|
| 400 |
+
"step": 25
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.0,
|
| 404 |
+
"eval_accuracy": 0.496,
|
| 405 |
+
"eval_loss": 0.6926933526992798,
|
| 406 |
+
"eval_runtime": 2.5561,
|
| 407 |
+
"eval_samples_per_second": 97.805,
|
| 408 |
+
"eval_steps_per_second": 2.739,
|
| 409 |
+
"step": 25
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.08,
|
| 413 |
+
"grad_norm": 4.824467658996582,
|
| 414 |
+
"learning_rate": 3.983050847457627e-05,
|
| 415 |
+
"loss": 0.7596,
|
| 416 |
+
"step": 26
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.08,
|
| 420 |
+
"eval_accuracy": 0.532,
|
| 421 |
+
"eval_loss": 0.6877753734588623,
|
| 422 |
+
"eval_runtime": 2.5044,
|
| 423 |
+
"eval_samples_per_second": 99.823,
|
| 424 |
+
"eval_steps_per_second": 2.795,
|
| 425 |
+
"step": 26
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.16,
|
| 429 |
+
"grad_norm": 1.8508061170578003,
|
| 430 |
+
"learning_rate": 3.940677966101695e-05,
|
| 431 |
+
"loss": 0.7391,
|
| 432 |
+
"step": 27
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.16,
|
| 436 |
+
"eval_accuracy": 0.5,
|
| 437 |
+
"eval_loss": 0.6870742440223694,
|
| 438 |
+
"eval_runtime": 2.5639,
|
| 439 |
+
"eval_samples_per_second": 97.509,
|
| 440 |
+
"eval_steps_per_second": 2.73,
|
| 441 |
+
"step": 27
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.24,
|
| 445 |
+
"grad_norm": 3.564190149307251,
|
| 446 |
+
"learning_rate": 3.898305084745763e-05,
|
| 447 |
+
"loss": 0.6948,
|
| 448 |
+
"step": 28
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.24,
|
| 452 |
+
"eval_accuracy": 0.524,
|
| 453 |
+
"eval_loss": 0.6858359575271606,
|
| 454 |
+
"eval_runtime": 2.5544,
|
| 455 |
+
"eval_samples_per_second": 97.87,
|
| 456 |
+
"eval_steps_per_second": 2.74,
|
| 457 |
+
"step": 28
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.32,
|
| 461 |
+
"grad_norm": 5.474400997161865,
|
| 462 |
+
"learning_rate": 3.855932203389831e-05,
|
| 463 |
+
"loss": 0.7572,
|
| 464 |
+
"step": 29
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.32,
|
| 468 |
+
"eval_accuracy": 0.528,
|
| 469 |
+
"eval_loss": 0.6866718530654907,
|
| 470 |
+
"eval_runtime": 2.5557,
|
| 471 |
+
"eval_samples_per_second": 97.821,
|
| 472 |
+
"eval_steps_per_second": 2.739,
|
| 473 |
+
"step": 29
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.4,
|
| 477 |
+
"grad_norm": 2.450674533843994,
|
| 478 |
+
"learning_rate": 3.813559322033898e-05,
|
| 479 |
+
"loss": 0.6643,
|
| 480 |
+
"step": 30
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.4,
|
| 484 |
+
"eval_accuracy": 0.52,
|
| 485 |
+
"eval_loss": 0.6864023208618164,
|
| 486 |
+
"eval_runtime": 2.5543,
|
| 487 |
+
"eval_samples_per_second": 97.875,
|
| 488 |
+
"eval_steps_per_second": 2.741,
|
| 489 |
+
"step": 30
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.48,
|
| 493 |
+
"grad_norm": 3.568068265914917,
|
| 494 |
+
"learning_rate": 3.771186440677966e-05,
|
| 495 |
+
"loss": 0.7332,
|
| 496 |
+
"step": 31
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.48,
|
| 500 |
+
"eval_accuracy": 0.512,
|
| 501 |
+
"eval_loss": 0.6899687647819519,
|
| 502 |
+
"eval_runtime": 2.5505,
|
| 503 |
+
"eval_samples_per_second": 98.019,
|
| 504 |
+
"eval_steps_per_second": 2.745,
|
| 505 |
+
"step": 31
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.56,
|
| 509 |
+
"grad_norm": 2.2910633087158203,
|
| 510 |
+
"learning_rate": 3.728813559322034e-05,
|
| 511 |
+
"loss": 0.7119,
|
| 512 |
+
"step": 32
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.56,
|
| 516 |
+
"eval_accuracy": 0.508,
|
| 517 |
+
"eval_loss": 0.6921640634536743,
|
| 518 |
+
"eval_runtime": 2.5545,
|
| 519 |
+
"eval_samples_per_second": 97.865,
|
| 520 |
+
"eval_steps_per_second": 2.74,
|
| 521 |
+
"step": 32
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.64,
|
| 525 |
+
"grad_norm": 2.090604066848755,
|
| 526 |
+
"learning_rate": 3.686440677966102e-05,
|
| 527 |
+
"loss": 0.7247,
|
| 528 |
+
"step": 33
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.64,
|
| 532 |
+
"eval_accuracy": 0.512,
|
| 533 |
+
"eval_loss": 0.6914921998977661,
|
| 534 |
+
"eval_runtime": 2.5526,
|
| 535 |
+
"eval_samples_per_second": 97.939,
|
| 536 |
+
"eval_steps_per_second": 2.742,
|
| 537 |
+
"step": 33
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.7199999999999998,
|
| 541 |
+
"grad_norm": 6.273575782775879,
|
| 542 |
+
"learning_rate": 3.644067796610169e-05,
|
| 543 |
+
"loss": 0.7364,
|
| 544 |
+
"step": 34
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.7199999999999998,
|
| 548 |
+
"eval_accuracy": 0.508,
|
| 549 |
+
"eval_loss": 0.6918437480926514,
|
| 550 |
+
"eval_runtime": 2.5551,
|
| 551 |
+
"eval_samples_per_second": 97.843,
|
| 552 |
+
"eval_steps_per_second": 2.74,
|
| 553 |
+
"step": 34
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.8,
|
| 557 |
+
"grad_norm": 6.723451614379883,
|
| 558 |
+
"learning_rate": 3.601694915254237e-05,
|
| 559 |
+
"loss": 0.6936,
|
| 560 |
+
"step": 35
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.8,
|
| 564 |
+
"eval_accuracy": 0.512,
|
| 565 |
+
"eval_loss": 0.6923359632492065,
|
| 566 |
+
"eval_runtime": 2.5513,
|
| 567 |
+
"eval_samples_per_second": 97.991,
|
| 568 |
+
"eval_steps_per_second": 2.744,
|
| 569 |
+
"step": 35
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.88,
|
| 573 |
+
"grad_norm": 10.801304817199707,
|
| 574 |
+
"learning_rate": 3.559322033898305e-05,
|
| 575 |
+
"loss": 0.6749,
|
| 576 |
+
"step": 36
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.88,
|
| 580 |
+
"eval_accuracy": 0.516,
|
| 581 |
+
"eval_loss": 0.6919687390327454,
|
| 582 |
+
"eval_runtime": 2.5553,
|
| 583 |
+
"eval_samples_per_second": 97.836,
|
| 584 |
+
"eval_steps_per_second": 2.739,
|
| 585 |
+
"step": 36
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.96,
|
| 589 |
+
"grad_norm": 7.005471229553223,
|
| 590 |
+
"learning_rate": 3.516949152542373e-05,
|
| 591 |
+
"loss": 0.7283,
|
| 592 |
+
"step": 37
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.96,
|
| 596 |
+
"eval_accuracy": 0.528,
|
| 597 |
+
"eval_loss": 0.690359354019165,
|
| 598 |
+
"eval_runtime": 2.5563,
|
| 599 |
+
"eval_samples_per_second": 97.799,
|
| 600 |
+
"eval_steps_per_second": 2.738,
|
| 601 |
+
"step": 37
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 3.04,
|
| 605 |
+
"grad_norm": 3.912996530532837,
|
| 606 |
+
"learning_rate": 3.474576271186441e-05,
|
| 607 |
+
"loss": 0.6633,
|
| 608 |
+
"step": 38
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.04,
|
| 612 |
+
"eval_accuracy": 0.524,
|
| 613 |
+
"eval_loss": 0.6878437399864197,
|
| 614 |
+
"eval_runtime": 2.5515,
|
| 615 |
+
"eval_samples_per_second": 97.982,
|
| 616 |
+
"eval_steps_per_second": 2.743,
|
| 617 |
+
"step": 38
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.12,
|
| 621 |
+
"grad_norm": 3.429208278656006,
|
| 622 |
+
"learning_rate": 3.432203389830508e-05,
|
| 623 |
+
"loss": 0.705,
|
| 624 |
+
"step": 39
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.12,
|
| 628 |
+
"eval_accuracy": 0.52,
|
| 629 |
+
"eval_loss": 0.6873710751533508,
|
| 630 |
+
"eval_runtime": 2.5571,
|
| 631 |
+
"eval_samples_per_second": 97.766,
|
| 632 |
+
"eval_steps_per_second": 2.737,
|
| 633 |
+
"step": 39
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.2,
|
| 637 |
+
"grad_norm": 3.2059762477874756,
|
| 638 |
+
"learning_rate": 3.389830508474576e-05,
|
| 639 |
+
"loss": 0.6913,
|
| 640 |
+
"step": 40
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.2,
|
| 644 |
+
"eval_accuracy": 0.516,
|
| 645 |
+
"eval_loss": 0.689160168170929,
|
| 646 |
+
"eval_runtime": 2.5594,
|
| 647 |
+
"eval_samples_per_second": 97.681,
|
| 648 |
+
"eval_steps_per_second": 2.735,
|
| 649 |
+
"step": 40
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 3.2800000000000002,
|
| 653 |
+
"grad_norm": 1.8953251838684082,
|
| 654 |
+
"learning_rate": 3.347457627118644e-05,
|
| 655 |
+
"loss": 0.6501,
|
| 656 |
+
"step": 41
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.2800000000000002,
|
| 660 |
+
"eval_accuracy": 0.52,
|
| 661 |
+
"eval_loss": 0.6878241896629333,
|
| 662 |
+
"eval_runtime": 2.5561,
|
| 663 |
+
"eval_samples_per_second": 97.806,
|
| 664 |
+
"eval_steps_per_second": 2.739,
|
| 665 |
+
"step": 41
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 3.36,
|
| 669 |
+
"grad_norm": 3.3232831954956055,
|
| 670 |
+
"learning_rate": 3.305084745762712e-05,
|
| 671 |
+
"loss": 0.7278,
|
| 672 |
+
"step": 42
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 3.36,
|
| 676 |
+
"eval_accuracy": 0.52,
|
| 677 |
+
"eval_loss": 0.6906406283378601,
|
| 678 |
+
"eval_runtime": 2.5543,
|
| 679 |
+
"eval_samples_per_second": 97.873,
|
| 680 |
+
"eval_steps_per_second": 2.74,
|
| 681 |
+
"step": 42
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.44,
|
| 685 |
+
"grad_norm": 7.255284309387207,
|
| 686 |
+
"learning_rate": 3.26271186440678e-05,
|
| 687 |
+
"loss": 0.6755,
|
| 688 |
+
"step": 43
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.44,
|
| 692 |
+
"eval_accuracy": 0.52,
|
| 693 |
+
"eval_loss": 0.6893867254257202,
|
| 694 |
+
"eval_runtime": 2.5555,
|
| 695 |
+
"eval_samples_per_second": 97.827,
|
| 696 |
+
"eval_steps_per_second": 2.739,
|
| 697 |
+
"step": 43
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 3.52,
|
| 701 |
+
"grad_norm": 5.801779270172119,
|
| 702 |
+
"learning_rate": 3.2203389830508473e-05,
|
| 703 |
+
"loss": 0.7261,
|
| 704 |
+
"step": 44
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.52,
|
| 708 |
+
"eval_accuracy": 0.52,
|
| 709 |
+
"eval_loss": 0.689304769039154,
|
| 710 |
+
"eval_runtime": 2.5009,
|
| 711 |
+
"eval_samples_per_second": 99.965,
|
| 712 |
+
"eval_steps_per_second": 2.799,
|
| 713 |
+
"step": 44
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 3.6,
|
| 717 |
+
"grad_norm": 6.175045967102051,
|
| 718 |
+
"learning_rate": 3.177966101694915e-05,
|
| 719 |
+
"loss": 0.6614,
|
| 720 |
+
"step": 45
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 3.6,
|
| 724 |
+
"eval_accuracy": 0.52,
|
| 725 |
+
"eval_loss": 0.6881933808326721,
|
| 726 |
+
"eval_runtime": 2.5565,
|
| 727 |
+
"eval_samples_per_second": 97.788,
|
| 728 |
+
"eval_steps_per_second": 2.738,
|
| 729 |
+
"step": 45
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.68,
|
| 733 |
+
"grad_norm": 7.691817760467529,
|
| 734 |
+
"learning_rate": 3.135593220338983e-05,
|
| 735 |
+
"loss": 0.7862,
|
| 736 |
+
"step": 46
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 3.68,
|
| 740 |
+
"eval_accuracy": 0.52,
|
| 741 |
+
"eval_loss": 0.6858007907867432,
|
| 742 |
+
"eval_runtime": 2.556,
|
| 743 |
+
"eval_samples_per_second": 97.808,
|
| 744 |
+
"eval_steps_per_second": 2.739,
|
| 745 |
+
"step": 46
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 3.76,
|
| 749 |
+
"grad_norm": 7.117946624755859,
|
| 750 |
+
"learning_rate": 3.093220338983051e-05,
|
| 751 |
+
"loss": 0.6939,
|
| 752 |
+
"step": 47
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.76,
|
| 756 |
+
"eval_accuracy": 0.52,
|
| 757 |
+
"eval_loss": 0.6848788857460022,
|
| 758 |
+
"eval_runtime": 2.5617,
|
| 759 |
+
"eval_samples_per_second": 97.593,
|
| 760 |
+
"eval_steps_per_second": 2.733,
|
| 761 |
+
"step": 47
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 3.84,
|
| 765 |
+
"grad_norm": 3.879883289337158,
|
| 766 |
+
"learning_rate": 3.050847457627119e-05,
|
| 767 |
+
"loss": 0.6851,
|
| 768 |
+
"step": 48
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 3.84,
|
| 772 |
+
"eval_accuracy": 0.52,
|
| 773 |
+
"eval_loss": 0.6833086013793945,
|
| 774 |
+
"eval_runtime": 2.5485,
|
| 775 |
+
"eval_samples_per_second": 98.095,
|
| 776 |
+
"eval_steps_per_second": 2.747,
|
| 777 |
+
"step": 48
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.92,
|
| 781 |
+
"grad_norm": 7.152946949005127,
|
| 782 |
+
"learning_rate": 3.0084745762711864e-05,
|
| 783 |
+
"loss": 0.7251,
|
| 784 |
+
"step": 49
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 3.92,
|
| 788 |
+
"eval_accuracy": 0.508,
|
| 789 |
+
"eval_loss": 0.6816601753234863,
|
| 790 |
+
"eval_runtime": 2.5514,
|
| 791 |
+
"eval_samples_per_second": 97.984,
|
| 792 |
+
"eval_steps_per_second": 2.744,
|
| 793 |
+
"step": 49
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 4.0,
|
| 797 |
+
"grad_norm": 1.905958890914917,
|
| 798 |
+
"learning_rate": 2.9661016949152544e-05,
|
| 799 |
+
"loss": 0.7008,
|
| 800 |
+
"step": 50
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 4.0,
|
| 804 |
+
"eval_accuracy": 0.508,
|
| 805 |
+
"eval_loss": 0.6813437342643738,
|
| 806 |
+
"eval_runtime": 2.5476,
|
| 807 |
+
"eval_samples_per_second": 98.131,
|
| 808 |
+
"eval_steps_per_second": 2.748,
|
| 809 |
+
"step": 50
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 4.08,
|
| 813 |
+
"grad_norm": 3.4690747261047363,
|
| 814 |
+
"learning_rate": 2.9237288135593223e-05,
|
| 815 |
+
"loss": 0.7161,
|
| 816 |
+
"step": 51
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 4.08,
|
| 820 |
+
"eval_accuracy": 0.52,
|
| 821 |
+
"eval_loss": 0.6803905963897705,
|
| 822 |
+
"eval_runtime": 2.552,
|
| 823 |
+
"eval_samples_per_second": 97.961,
|
| 824 |
+
"eval_steps_per_second": 2.743,
|
| 825 |
+
"step": 51
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 4.16,
|
| 829 |
+
"grad_norm": 4.801358699798584,
|
| 830 |
+
"learning_rate": 2.88135593220339e-05,
|
| 831 |
+
"loss": 0.6932,
|
| 832 |
+
"step": 52
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 4.16,
|
| 836 |
+
"eval_accuracy": 0.512,
|
| 837 |
+
"eval_loss": 0.6818437576293945,
|
| 838 |
+
"eval_runtime": 2.5499,
|
| 839 |
+
"eval_samples_per_second": 98.043,
|
| 840 |
+
"eval_steps_per_second": 2.745,
|
| 841 |
+
"step": 52
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 4.24,
|
| 845 |
+
"grad_norm": 11.071053504943848,
|
| 846 |
+
"learning_rate": 2.838983050847458e-05,
|
| 847 |
+
"loss": 0.6743,
|
| 848 |
+
"step": 53
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 4.24,
|
| 852 |
+
"eval_accuracy": 0.5,
|
| 853 |
+
"eval_loss": 0.6845312714576721,
|
| 854 |
+
"eval_runtime": 2.552,
|
| 855 |
+
"eval_samples_per_second": 97.962,
|
| 856 |
+
"eval_steps_per_second": 2.743,
|
| 857 |
+
"step": 53
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 4.32,
|
| 861 |
+
"grad_norm": 2.7743890285491943,
|
| 862 |
+
"learning_rate": 2.7966101694915255e-05,
|
| 863 |
+
"loss": 0.7102,
|
| 864 |
+
"step": 54
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 4.32,
|
| 868 |
+
"eval_accuracy": 0.5,
|
| 869 |
+
"eval_loss": 0.6837421655654907,
|
| 870 |
+
"eval_runtime": 2.5501,
|
| 871 |
+
"eval_samples_per_second": 98.035,
|
| 872 |
+
"eval_steps_per_second": 2.745,
|
| 873 |
+
"step": 54
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 4.4,
|
| 877 |
+
"grad_norm": 4.514011859893799,
|
| 878 |
+
"learning_rate": 2.754237288135593e-05,
|
| 879 |
+
"loss": 0.7169,
|
| 880 |
+
"step": 55
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 4.4,
|
| 884 |
+
"eval_accuracy": 0.532,
|
| 885 |
+
"eval_loss": 0.6851328015327454,
|
| 886 |
+
"eval_runtime": 2.4999,
|
| 887 |
+
"eval_samples_per_second": 100.005,
|
| 888 |
+
"eval_steps_per_second": 2.8,
|
| 889 |
+
"step": 55
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 4.48,
|
| 893 |
+
"grad_norm": 4.223740100860596,
|
| 894 |
+
"learning_rate": 2.711864406779661e-05,
|
| 895 |
+
"loss": 0.735,
|
| 896 |
+
"step": 56
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 4.48,
|
| 900 |
+
"eval_accuracy": 0.54,
|
| 901 |
+
"eval_loss": 0.6856874823570251,
|
| 902 |
+
"eval_runtime": 2.501,
|
| 903 |
+
"eval_samples_per_second": 99.959,
|
| 904 |
+
"eval_steps_per_second": 2.799,
|
| 905 |
+
"step": 56
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 4.5600000000000005,
|
| 909 |
+
"grad_norm": 8.217570304870605,
|
| 910 |
+
"learning_rate": 2.669491525423729e-05,
|
| 911 |
+
"loss": 0.7155,
|
| 912 |
+
"step": 57
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 4.5600000000000005,
|
| 916 |
+
"eval_accuracy": 0.56,
|
| 917 |
+
"eval_loss": 0.686718761920929,
|
| 918 |
+
"eval_runtime": 2.455,
|
| 919 |
+
"eval_samples_per_second": 101.832,
|
| 920 |
+
"eval_steps_per_second": 2.851,
|
| 921 |
+
"step": 57
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 4.64,
|
| 925 |
+
"grad_norm": 7.043219089508057,
|
| 926 |
+
"learning_rate": 2.627118644067797e-05,
|
| 927 |
+
"loss": 0.696,
|
| 928 |
+
"step": 58
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 4.64,
|
| 932 |
+
"eval_accuracy": 0.536,
|
| 933 |
+
"eval_loss": 0.6860937476158142,
|
| 934 |
+
"eval_runtime": 2.5524,
|
| 935 |
+
"eval_samples_per_second": 97.946,
|
| 936 |
+
"eval_steps_per_second": 2.742,
|
| 937 |
+
"step": 58
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 4.72,
|
| 941 |
+
"grad_norm": 5.340857982635498,
|
| 942 |
+
"learning_rate": 2.5847457627118642e-05,
|
| 943 |
+
"loss": 0.715,
|
| 944 |
+
"step": 59
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 4.72,
|
| 948 |
+
"eval_accuracy": 0.572,
|
| 949 |
+
"eval_loss": 0.6860234141349792,
|
| 950 |
+
"eval_runtime": 2.5519,
|
| 951 |
+
"eval_samples_per_second": 97.968,
|
| 952 |
+
"eval_steps_per_second": 2.743,
|
| 953 |
+
"step": 59
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 4.8,
|
| 957 |
+
"grad_norm": 3.935725212097168,
|
| 958 |
+
"learning_rate": 2.5423728813559322e-05,
|
| 959 |
+
"loss": 0.6934,
|
| 960 |
+
"step": 60
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 4.8,
|
| 964 |
+
"eval_accuracy": 0.532,
|
| 965 |
+
"eval_loss": 0.6857656240463257,
|
| 966 |
+
"eval_runtime": 2.5599,
|
| 967 |
+
"eval_samples_per_second": 97.659,
|
| 968 |
+
"eval_steps_per_second": 2.734,
|
| 969 |
+
"step": 60
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 4.88,
|
| 973 |
+
"grad_norm": 5.759483814239502,
|
| 974 |
+
"learning_rate": 2.5e-05,
|
| 975 |
+
"loss": 0.6659,
|
| 976 |
+
"step": 61
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 4.88,
|
| 980 |
+
"eval_accuracy": 0.54,
|
| 981 |
+
"eval_loss": 0.6850937604904175,
|
| 982 |
+
"eval_runtime": 2.556,
|
| 983 |
+
"eval_samples_per_second": 97.809,
|
| 984 |
+
"eval_steps_per_second": 2.739,
|
| 985 |
+
"step": 61
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 4.96,
|
| 989 |
+
"grad_norm": 9.154269218444824,
|
| 990 |
+
"learning_rate": 2.457627118644068e-05,
|
| 991 |
+
"loss": 0.7122,
|
| 992 |
+
"step": 62
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 4.96,
|
| 996 |
+
"eval_accuracy": 0.54,
|
| 997 |
+
"eval_loss": 0.683843731880188,
|
| 998 |
+
"eval_runtime": 2.5171,
|
| 999 |
+
"eval_samples_per_second": 99.322,
|
| 1000 |
+
"eval_steps_per_second": 2.781,
|
| 1001 |
+
"step": 62
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 5.04,
|
| 1005 |
+
"grad_norm": 3.8628180027008057,
|
| 1006 |
+
"learning_rate": 2.4152542372881357e-05,
|
| 1007 |
+
"loss": 0.685,
|
| 1008 |
+
"step": 63
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 5.04,
|
| 1012 |
+
"eval_accuracy": 0.536,
|
| 1013 |
+
"eval_loss": 0.6826719045639038,
|
| 1014 |
+
"eval_runtime": 2.5523,
|
| 1015 |
+
"eval_samples_per_second": 97.95,
|
| 1016 |
+
"eval_steps_per_second": 2.743,
|
| 1017 |
+
"step": 63
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 5.12,
|
| 1021 |
+
"grad_norm": 3.074619770050049,
|
| 1022 |
+
"learning_rate": 2.3728813559322036e-05,
|
| 1023 |
+
"loss": 0.6702,
|
| 1024 |
+
"step": 64
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 5.12,
|
| 1028 |
+
"eval_accuracy": 0.54,
|
| 1029 |
+
"eval_loss": 0.6835703253746033,
|
| 1030 |
+
"eval_runtime": 2.5526,
|
| 1031 |
+
"eval_samples_per_second": 97.94,
|
| 1032 |
+
"eval_steps_per_second": 2.742,
|
| 1033 |
+
"step": 64
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 5.2,
|
| 1037 |
+
"grad_norm": 3.274127721786499,
|
| 1038 |
+
"learning_rate": 2.3305084745762712e-05,
|
| 1039 |
+
"loss": 0.7247,
|
| 1040 |
+
"step": 65
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 5.2,
|
| 1044 |
+
"eval_accuracy": 0.532,
|
| 1045 |
+
"eval_loss": 0.6832265853881836,
|
| 1046 |
+
"eval_runtime": 2.5575,
|
| 1047 |
+
"eval_samples_per_second": 97.752,
|
| 1048 |
+
"eval_steps_per_second": 2.737,
|
| 1049 |
+
"step": 65
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 5.28,
|
| 1053 |
+
"grad_norm": 3.9896106719970703,
|
| 1054 |
+
"learning_rate": 2.2881355932203392e-05,
|
| 1055 |
+
"loss": 0.7237,
|
| 1056 |
+
"step": 66
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 5.28,
|
| 1060 |
+
"eval_accuracy": 0.52,
|
| 1061 |
+
"eval_loss": 0.683218777179718,
|
| 1062 |
+
"eval_runtime": 2.5521,
|
| 1063 |
+
"eval_samples_per_second": 97.959,
|
| 1064 |
+
"eval_steps_per_second": 2.743,
|
| 1065 |
+
"step": 66
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 5.36,
|
| 1069 |
+
"grad_norm": 4.6198410987854,
|
| 1070 |
+
"learning_rate": 2.245762711864407e-05,
|
| 1071 |
+
"loss": 0.6874,
|
| 1072 |
+
"step": 67
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 5.36,
|
| 1076 |
+
"eval_accuracy": 0.52,
|
| 1077 |
+
"eval_loss": 0.6817265748977661,
|
| 1078 |
+
"eval_runtime": 2.5508,
|
| 1079 |
+
"eval_samples_per_second": 98.007,
|
| 1080 |
+
"eval_steps_per_second": 2.744,
|
| 1081 |
+
"step": 67
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 5.44,
|
| 1085 |
+
"grad_norm": 2.7638332843780518,
|
| 1086 |
+
"learning_rate": 2.2033898305084748e-05,
|
| 1087 |
+
"loss": 0.6759,
|
| 1088 |
+
"step": 68
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 5.44,
|
| 1092 |
+
"eval_accuracy": 0.524,
|
| 1093 |
+
"eval_loss": 0.6810156106948853,
|
| 1094 |
+
"eval_runtime": 2.5592,
|
| 1095 |
+
"eval_samples_per_second": 97.689,
|
| 1096 |
+
"eval_steps_per_second": 2.735,
|
| 1097 |
+
"step": 68
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 5.52,
|
| 1101 |
+
"grad_norm": 5.45823860168457,
|
| 1102 |
+
"learning_rate": 2.1610169491525427e-05,
|
| 1103 |
+
"loss": 0.6508,
|
| 1104 |
+
"step": 69
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 5.52,
|
| 1108 |
+
"eval_accuracy": 0.524,
|
| 1109 |
+
"eval_loss": 0.6822657585144043,
|
| 1110 |
+
"eval_runtime": 2.5549,
|
| 1111 |
+
"eval_samples_per_second": 97.85,
|
| 1112 |
+
"eval_steps_per_second": 2.74,
|
| 1113 |
+
"step": 69
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 5.6,
|
| 1117 |
+
"grad_norm": 1.344992756843567,
|
| 1118 |
+
"learning_rate": 2.1186440677966103e-05,
|
| 1119 |
+
"loss": 0.65,
|
| 1120 |
+
"step": 70
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 5.6,
|
| 1124 |
+
"eval_accuracy": 0.524,
|
| 1125 |
+
"eval_loss": 0.6806054711341858,
|
| 1126 |
+
"eval_runtime": 2.5531,
|
| 1127 |
+
"eval_samples_per_second": 97.92,
|
| 1128 |
+
"eval_steps_per_second": 2.742,
|
| 1129 |
+
"step": 70
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 5.68,
|
| 1133 |
+
"grad_norm": 3.803818941116333,
|
| 1134 |
+
"learning_rate": 2.076271186440678e-05,
|
| 1135 |
+
"loss": 0.6818,
|
| 1136 |
+
"step": 71
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 5.68,
|
| 1140 |
+
"eval_accuracy": 0.524,
|
| 1141 |
+
"eval_loss": 0.6822031140327454,
|
| 1142 |
+
"eval_runtime": 2.5599,
|
| 1143 |
+
"eval_samples_per_second": 97.661,
|
| 1144 |
+
"eval_steps_per_second": 2.734,
|
| 1145 |
+
"step": 71
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 5.76,
|
| 1149 |
+
"grad_norm": 3.8192968368530273,
|
| 1150 |
+
"learning_rate": 2.033898305084746e-05,
|
| 1151 |
+
"loss": 0.6384,
|
| 1152 |
+
"step": 72
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 5.76,
|
| 1156 |
+
"eval_accuracy": 0.524,
|
| 1157 |
+
"eval_loss": 0.6826953887939453,
|
| 1158 |
+
"eval_runtime": 2.5524,
|
| 1159 |
+
"eval_samples_per_second": 97.945,
|
| 1160 |
+
"eval_steps_per_second": 2.742,
|
| 1161 |
+
"step": 72
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 5.84,
|
| 1165 |
+
"grad_norm": 2.2677340507507324,
|
| 1166 |
+
"learning_rate": 1.9915254237288135e-05,
|
| 1167 |
+
"loss": 0.6847,
|
| 1168 |
+
"step": 73
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 5.84,
|
| 1172 |
+
"eval_accuracy": 0.516,
|
| 1173 |
+
"eval_loss": 0.6820663809776306,
|
| 1174 |
+
"eval_runtime": 2.5706,
|
| 1175 |
+
"eval_samples_per_second": 97.253,
|
| 1176 |
+
"eval_steps_per_second": 2.723,
|
| 1177 |
+
"step": 73
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 5.92,
|
| 1181 |
+
"grad_norm": 10.372380256652832,
|
| 1182 |
+
"learning_rate": 1.9491525423728814e-05,
|
| 1183 |
+
"loss": 0.7528,
|
| 1184 |
+
"step": 74
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 5.92,
|
| 1188 |
+
"eval_accuracy": 0.516,
|
| 1189 |
+
"eval_loss": 0.683914065361023,
|
| 1190 |
+
"eval_runtime": 2.5522,
|
| 1191 |
+
"eval_samples_per_second": 97.953,
|
| 1192 |
+
"eval_steps_per_second": 2.743,
|
| 1193 |
+
"step": 74
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 6.0,
|
| 1197 |
+
"grad_norm": 2.46616268157959,
|
| 1198 |
+
"learning_rate": 1.906779661016949e-05,
|
| 1199 |
+
"loss": 0.6733,
|
| 1200 |
+
"step": 75
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 6.0,
|
| 1204 |
+
"eval_accuracy": 0.516,
|
| 1205 |
+
"eval_loss": 0.6828632950782776,
|
| 1206 |
+
"eval_runtime": 2.5571,
|
| 1207 |
+
"eval_samples_per_second": 97.766,
|
| 1208 |
+
"eval_steps_per_second": 2.737,
|
| 1209 |
+
"step": 75
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 6.08,
|
| 1213 |
+
"grad_norm": 4.386812686920166,
|
| 1214 |
+
"learning_rate": 1.864406779661017e-05,
|
| 1215 |
+
"loss": 0.6642,
|
| 1216 |
+
"step": 76
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 6.08,
|
| 1220 |
+
"eval_accuracy": 0.512,
|
| 1221 |
+
"eval_loss": 0.6845312714576721,
|
| 1222 |
+
"eval_runtime": 2.5496,
|
| 1223 |
+
"eval_samples_per_second": 98.055,
|
| 1224 |
+
"eval_steps_per_second": 2.746,
|
| 1225 |
+
"step": 76
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 6.16,
|
| 1229 |
+
"grad_norm": 2.428257703781128,
|
| 1230 |
+
"learning_rate": 1.8220338983050846e-05,
|
| 1231 |
+
"loss": 0.669,
|
| 1232 |
+
"step": 77
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 6.16,
|
| 1236 |
+
"eval_accuracy": 0.516,
|
| 1237 |
+
"eval_loss": 0.6866054534912109,
|
| 1238 |
+
"eval_runtime": 2.5556,
|
| 1239 |
+
"eval_samples_per_second": 97.825,
|
| 1240 |
+
"eval_steps_per_second": 2.739,
|
| 1241 |
+
"step": 77
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 6.24,
|
| 1245 |
+
"grad_norm": 3.2233493328094482,
|
| 1246 |
+
"learning_rate": 1.7796610169491526e-05,
|
| 1247 |
+
"loss": 0.6525,
|
| 1248 |
+
"step": 78
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 6.24,
|
| 1252 |
+
"eval_accuracy": 0.52,
|
| 1253 |
+
"eval_loss": 0.6888242363929749,
|
| 1254 |
+
"eval_runtime": 2.5518,
|
| 1255 |
+
"eval_samples_per_second": 97.969,
|
| 1256 |
+
"eval_steps_per_second": 2.743,
|
| 1257 |
+
"step": 78
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 6.32,
|
| 1261 |
+
"grad_norm": 4.684359550476074,
|
| 1262 |
+
"learning_rate": 1.7372881355932205e-05,
|
| 1263 |
+
"loss": 0.6827,
|
| 1264 |
+
"step": 79
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 6.32,
|
| 1268 |
+
"eval_accuracy": 0.52,
|
| 1269 |
+
"eval_loss": 0.6881914138793945,
|
| 1270 |
+
"eval_runtime": 2.5526,
|
| 1271 |
+
"eval_samples_per_second": 97.938,
|
| 1272 |
+
"eval_steps_per_second": 2.742,
|
| 1273 |
+
"step": 79
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 6.4,
|
| 1277 |
+
"grad_norm": 6.635712623596191,
|
| 1278 |
+
"learning_rate": 1.694915254237288e-05,
|
| 1279 |
+
"loss": 0.7138,
|
| 1280 |
+
"step": 80
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 6.4,
|
| 1284 |
+
"eval_accuracy": 0.52,
|
| 1285 |
+
"eval_loss": 0.688589870929718,
|
| 1286 |
+
"eval_runtime": 2.5551,
|
| 1287 |
+
"eval_samples_per_second": 97.843,
|
| 1288 |
+
"eval_steps_per_second": 2.74,
|
| 1289 |
+
"step": 80
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 6.48,
|
| 1293 |
+
"grad_norm": 2.153329610824585,
|
| 1294 |
+
"learning_rate": 1.652542372881356e-05,
|
| 1295 |
+
"loss": 0.6533,
|
| 1296 |
+
"step": 81
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 6.48,
|
| 1300 |
+
"eval_accuracy": 0.52,
|
| 1301 |
+
"eval_loss": 0.6895253658294678,
|
| 1302 |
+
"eval_runtime": 2.5548,
|
| 1303 |
+
"eval_samples_per_second": 97.856,
|
| 1304 |
+
"eval_steps_per_second": 2.74,
|
| 1305 |
+
"step": 81
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 6.5600000000000005,
|
| 1309 |
+
"grad_norm": 8.309370994567871,
|
| 1310 |
+
"learning_rate": 1.6101694915254237e-05,
|
| 1311 |
+
"loss": 0.7126,
|
| 1312 |
+
"step": 82
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 6.5600000000000005,
|
| 1316 |
+
"eval_accuracy": 0.52,
|
| 1317 |
+
"eval_loss": 0.6872695088386536,
|
| 1318 |
+
"eval_runtime": 2.5551,
|
| 1319 |
+
"eval_samples_per_second": 97.844,
|
| 1320 |
+
"eval_steps_per_second": 2.74,
|
| 1321 |
+
"step": 82
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 6.64,
|
| 1325 |
+
"grad_norm": 7.506027698516846,
|
| 1326 |
+
"learning_rate": 1.5677966101694916e-05,
|
| 1327 |
+
"loss": 0.7333,
|
| 1328 |
+
"step": 83
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 6.64,
|
| 1332 |
+
"eval_accuracy": 0.52,
|
| 1333 |
+
"eval_loss": 0.6848945021629333,
|
| 1334 |
+
"eval_runtime": 2.5576,
|
| 1335 |
+
"eval_samples_per_second": 97.75,
|
| 1336 |
+
"eval_steps_per_second": 2.737,
|
| 1337 |
+
"step": 83
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 6.72,
|
| 1341 |
+
"grad_norm": 2.9009928703308105,
|
| 1342 |
+
"learning_rate": 1.5254237288135596e-05,
|
| 1343 |
+
"loss": 0.6469,
|
| 1344 |
+
"step": 84
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 6.72,
|
| 1348 |
+
"eval_accuracy": 0.52,
|
| 1349 |
+
"eval_loss": 0.6854609251022339,
|
| 1350 |
+
"eval_runtime": 2.5528,
|
| 1351 |
+
"eval_samples_per_second": 97.93,
|
| 1352 |
+
"eval_steps_per_second": 2.742,
|
| 1353 |
+
"step": 84
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 6.8,
|
| 1357 |
+
"grad_norm": 5.017767429351807,
|
| 1358 |
+
"learning_rate": 1.4830508474576272e-05,
|
| 1359 |
+
"loss": 0.7521,
|
| 1360 |
+
"step": 85
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 6.8,
|
| 1364 |
+
"eval_accuracy": 0.52,
|
| 1365 |
+
"eval_loss": 0.6840038895606995,
|
| 1366 |
+
"eval_runtime": 2.5591,
|
| 1367 |
+
"eval_samples_per_second": 97.691,
|
| 1368 |
+
"eval_steps_per_second": 2.735,
|
| 1369 |
+
"step": 85
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 6.88,
|
| 1373 |
+
"grad_norm": 2.006927013397217,
|
| 1374 |
+
"learning_rate": 1.440677966101695e-05,
|
| 1375 |
+
"loss": 0.6516,
|
| 1376 |
+
"step": 86
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 6.88,
|
| 1380 |
+
"eval_accuracy": 0.52,
|
| 1381 |
+
"eval_loss": 0.6825664043426514,
|
| 1382 |
+
"eval_runtime": 2.5642,
|
| 1383 |
+
"eval_samples_per_second": 97.496,
|
| 1384 |
+
"eval_steps_per_second": 2.73,
|
| 1385 |
+
"step": 86
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 6.96,
|
| 1389 |
+
"grad_norm": 5.504487037658691,
|
| 1390 |
+
"learning_rate": 1.3983050847457627e-05,
|
| 1391 |
+
"loss": 0.7072,
|
| 1392 |
+
"step": 87
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 6.96,
|
| 1396 |
+
"eval_accuracy": 0.516,
|
| 1397 |
+
"eval_loss": 0.6815390586853027,
|
| 1398 |
+
"eval_runtime": 2.5618,
|
| 1399 |
+
"eval_samples_per_second": 97.588,
|
| 1400 |
+
"eval_steps_per_second": 2.732,
|
| 1401 |
+
"step": 87
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 7.04,
|
| 1405 |
+
"grad_norm": 3.175321578979492,
|
| 1406 |
+
"learning_rate": 1.3559322033898305e-05,
|
| 1407 |
+
"loss": 0.6543,
|
| 1408 |
+
"step": 88
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 7.04,
|
| 1412 |
+
"eval_accuracy": 0.52,
|
| 1413 |
+
"eval_loss": 0.6796953082084656,
|
| 1414 |
+
"eval_runtime": 2.5612,
|
| 1415 |
+
"eval_samples_per_second": 97.61,
|
| 1416 |
+
"eval_steps_per_second": 2.733,
|
| 1417 |
+
"step": 88
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 7.12,
|
| 1421 |
+
"grad_norm": 9.99293327331543,
|
| 1422 |
+
"learning_rate": 1.3135593220338985e-05,
|
| 1423 |
+
"loss": 0.7078,
|
| 1424 |
+
"step": 89
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 7.12,
|
| 1428 |
+
"eval_accuracy": 0.524,
|
| 1429 |
+
"eval_loss": 0.6775000691413879,
|
| 1430 |
+
"eval_runtime": 2.5598,
|
| 1431 |
+
"eval_samples_per_second": 97.663,
|
| 1432 |
+
"eval_steps_per_second": 2.735,
|
| 1433 |
+
"step": 89
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 7.2,
|
| 1437 |
+
"grad_norm": 6.317586421966553,
|
| 1438 |
+
"learning_rate": 1.2711864406779661e-05,
|
| 1439 |
+
"loss": 0.7115,
|
| 1440 |
+
"step": 90
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 7.2,
|
| 1444 |
+
"eval_accuracy": 0.528,
|
| 1445 |
+
"eval_loss": 0.6765468716621399,
|
| 1446 |
+
"eval_runtime": 2.5596,
|
| 1447 |
+
"eval_samples_per_second": 97.67,
|
| 1448 |
+
"eval_steps_per_second": 2.735,
|
| 1449 |
+
"step": 90
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 7.28,
|
| 1453 |
+
"grad_norm": 6.010474681854248,
|
| 1454 |
+
"learning_rate": 1.228813559322034e-05,
|
| 1455 |
+
"loss": 0.6348,
|
| 1456 |
+
"step": 91
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 7.28,
|
| 1460 |
+
"eval_accuracy": 0.532,
|
| 1461 |
+
"eval_loss": 0.6753984093666077,
|
| 1462 |
+
"eval_runtime": 2.5578,
|
| 1463 |
+
"eval_samples_per_second": 97.741,
|
| 1464 |
+
"eval_steps_per_second": 2.737,
|
| 1465 |
+
"step": 91
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 7.36,
|
| 1469 |
+
"grad_norm": 1.554281234741211,
|
| 1470 |
+
"learning_rate": 1.1864406779661018e-05,
|
| 1471 |
+
"loss": 0.6907,
|
| 1472 |
+
"step": 92
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 7.36,
|
| 1476 |
+
"eval_accuracy": 0.552,
|
| 1477 |
+
"eval_loss": 0.6742578148841858,
|
| 1478 |
+
"eval_runtime": 2.5536,
|
| 1479 |
+
"eval_samples_per_second": 97.901,
|
| 1480 |
+
"eval_steps_per_second": 2.741,
|
| 1481 |
+
"step": 92
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 7.44,
|
| 1485 |
+
"grad_norm": 2.691506862640381,
|
| 1486 |
+
"learning_rate": 1.1440677966101696e-05,
|
| 1487 |
+
"loss": 0.6474,
|
| 1488 |
+
"step": 93
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 7.44,
|
| 1492 |
+
"eval_accuracy": 0.532,
|
| 1493 |
+
"eval_loss": 0.6753789186477661,
|
| 1494 |
+
"eval_runtime": 2.5576,
|
| 1495 |
+
"eval_samples_per_second": 97.747,
|
| 1496 |
+
"eval_steps_per_second": 2.737,
|
| 1497 |
+
"step": 93
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 7.52,
|
| 1501 |
+
"grad_norm": 3.9982895851135254,
|
| 1502 |
+
"learning_rate": 1.1016949152542374e-05,
|
| 1503 |
+
"loss": 0.6816,
|
| 1504 |
+
"step": 94
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 7.52,
|
| 1508 |
+
"eval_accuracy": 0.536,
|
| 1509 |
+
"eval_loss": 0.6741992235183716,
|
| 1510 |
+
"eval_runtime": 2.5538,
|
| 1511 |
+
"eval_samples_per_second": 97.894,
|
| 1512 |
+
"eval_steps_per_second": 2.741,
|
| 1513 |
+
"step": 94
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 7.6,
|
| 1517 |
+
"grad_norm": 4.3524274826049805,
|
| 1518 |
+
"learning_rate": 1.0593220338983052e-05,
|
| 1519 |
+
"loss": 0.6974,
|
| 1520 |
+
"step": 95
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 7.6,
|
| 1524 |
+
"eval_accuracy": 0.544,
|
| 1525 |
+
"eval_loss": 0.6741132736206055,
|
| 1526 |
+
"eval_runtime": 2.5546,
|
| 1527 |
+
"eval_samples_per_second": 97.862,
|
| 1528 |
+
"eval_steps_per_second": 2.74,
|
| 1529 |
+
"step": 95
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 7.68,
|
| 1533 |
+
"grad_norm": 2.858217477798462,
|
| 1534 |
+
"learning_rate": 1.016949152542373e-05,
|
| 1535 |
+
"loss": 0.7131,
|
| 1536 |
+
"step": 96
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 7.68,
|
| 1540 |
+
"eval_accuracy": 0.556,
|
| 1541 |
+
"eval_loss": 0.6736015677452087,
|
| 1542 |
+
"eval_runtime": 2.5522,
|
| 1543 |
+
"eval_samples_per_second": 97.955,
|
| 1544 |
+
"eval_steps_per_second": 2.743,
|
| 1545 |
+
"step": 96
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 7.76,
|
| 1549 |
+
"grad_norm": 5.655324459075928,
|
| 1550 |
+
"learning_rate": 9.745762711864407e-06,
|
| 1551 |
+
"loss": 0.639,
|
| 1552 |
+
"step": 97
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 7.76,
|
| 1556 |
+
"eval_accuracy": 0.56,
|
| 1557 |
+
"eval_loss": 0.6730742454528809,
|
| 1558 |
+
"eval_runtime": 2.559,
|
| 1559 |
+
"eval_samples_per_second": 97.694,
|
| 1560 |
+
"eval_steps_per_second": 2.735,
|
| 1561 |
+
"step": 97
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 7.84,
|
| 1565 |
+
"grad_norm": 11.034967422485352,
|
| 1566 |
+
"learning_rate": 9.322033898305085e-06,
|
| 1567 |
+
"loss": 0.6931,
|
| 1568 |
+
"step": 98
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 7.84,
|
| 1572 |
+
"eval_accuracy": 0.552,
|
| 1573 |
+
"eval_loss": 0.6729413866996765,
|
| 1574 |
+
"eval_runtime": 2.5511,
|
| 1575 |
+
"eval_samples_per_second": 97.998,
|
| 1576 |
+
"eval_steps_per_second": 2.744,
|
| 1577 |
+
"step": 98
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 7.92,
|
| 1581 |
+
"grad_norm": 4.288939476013184,
|
| 1582 |
+
"learning_rate": 8.898305084745763e-06,
|
| 1583 |
+
"loss": 0.7052,
|
| 1584 |
+
"step": 99
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 7.92,
|
| 1588 |
+
"eval_accuracy": 0.536,
|
| 1589 |
+
"eval_loss": 0.6727031469345093,
|
| 1590 |
+
"eval_runtime": 2.5507,
|
| 1591 |
+
"eval_samples_per_second": 98.012,
|
| 1592 |
+
"eval_steps_per_second": 2.744,
|
| 1593 |
+
"step": 99
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 8.0,
|
| 1597 |
+
"grad_norm": 7.271831035614014,
|
| 1598 |
+
"learning_rate": 8.47457627118644e-06,
|
| 1599 |
+
"loss": 0.6804,
|
| 1600 |
+
"step": 100
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 8.0,
|
| 1604 |
+
"eval_accuracy": 0.532,
|
| 1605 |
+
"eval_loss": 0.6717929840087891,
|
| 1606 |
+
"eval_runtime": 2.5062,
|
| 1607 |
+
"eval_samples_per_second": 99.751,
|
| 1608 |
+
"eval_steps_per_second": 2.793,
|
| 1609 |
+
"step": 100
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 8.08,
|
| 1613 |
+
"grad_norm": 3.726989269256592,
|
| 1614 |
+
"learning_rate": 8.050847457627118e-06,
|
| 1615 |
+
"loss": 0.6751,
|
| 1616 |
+
"step": 101
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 8.08,
|
| 1620 |
+
"eval_accuracy": 0.536,
|
| 1621 |
+
"eval_loss": 0.6729882955551147,
|
| 1622 |
+
"eval_runtime": 2.552,
|
| 1623 |
+
"eval_samples_per_second": 97.962,
|
| 1624 |
+
"eval_steps_per_second": 2.743,
|
| 1625 |
+
"step": 101
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 8.16,
|
| 1629 |
+
"grad_norm": 3.427084445953369,
|
| 1630 |
+
"learning_rate": 7.627118644067798e-06,
|
| 1631 |
+
"loss": 0.6867,
|
| 1632 |
+
"step": 102
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 8.16,
|
| 1636 |
+
"eval_accuracy": 0.536,
|
| 1637 |
+
"eval_loss": 0.6727109551429749,
|
| 1638 |
+
"eval_runtime": 2.5498,
|
| 1639 |
+
"eval_samples_per_second": 98.046,
|
| 1640 |
+
"eval_steps_per_second": 2.745,
|
| 1641 |
+
"step": 102
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 8.24,
|
| 1645 |
+
"grad_norm": 7.673038005828857,
|
| 1646 |
+
"learning_rate": 7.203389830508475e-06,
|
| 1647 |
+
"loss": 0.6712,
|
| 1648 |
+
"step": 103
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 8.24,
|
| 1652 |
+
"eval_accuracy": 0.548,
|
| 1653 |
+
"eval_loss": 0.6731953024864197,
|
| 1654 |
+
"eval_runtime": 2.564,
|
| 1655 |
+
"eval_samples_per_second": 97.503,
|
| 1656 |
+
"eval_steps_per_second": 2.73,
|
| 1657 |
+
"step": 103
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 8.32,
|
| 1661 |
+
"grad_norm": 4.261835098266602,
|
| 1662 |
+
"learning_rate": 6.779661016949153e-06,
|
| 1663 |
+
"loss": 0.7308,
|
| 1664 |
+
"step": 104
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 8.32,
|
| 1668 |
+
"eval_accuracy": 0.556,
|
| 1669 |
+
"eval_loss": 0.6727851629257202,
|
| 1670 |
+
"eval_runtime": 2.5486,
|
| 1671 |
+
"eval_samples_per_second": 98.091,
|
| 1672 |
+
"eval_steps_per_second": 2.747,
|
| 1673 |
+
"step": 104
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 8.4,
|
| 1677 |
+
"grad_norm": 4.702732086181641,
|
| 1678 |
+
"learning_rate": 6.3559322033898304e-06,
|
| 1679 |
+
"loss": 0.7019,
|
| 1680 |
+
"step": 105
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 8.4,
|
| 1684 |
+
"eval_accuracy": 0.532,
|
| 1685 |
+
"eval_loss": 0.6733944416046143,
|
| 1686 |
+
"eval_runtime": 2.5543,
|
| 1687 |
+
"eval_samples_per_second": 97.876,
|
| 1688 |
+
"eval_steps_per_second": 2.741,
|
| 1689 |
+
"step": 105
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 8.48,
|
| 1693 |
+
"grad_norm": 1.8300518989562988,
|
| 1694 |
+
"learning_rate": 5.932203389830509e-06,
|
| 1695 |
+
"loss": 0.6733,
|
| 1696 |
+
"step": 106
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 8.48,
|
| 1700 |
+
"eval_accuracy": 0.528,
|
| 1701 |
+
"eval_loss": 0.6754140853881836,
|
| 1702 |
+
"eval_runtime": 2.5508,
|
| 1703 |
+
"eval_samples_per_second": 98.009,
|
| 1704 |
+
"eval_steps_per_second": 2.744,
|
| 1705 |
+
"step": 106
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 8.56,
|
| 1709 |
+
"grad_norm": 4.873719692230225,
|
| 1710 |
+
"learning_rate": 5.508474576271187e-06,
|
| 1711 |
+
"loss": 0.6503,
|
| 1712 |
+
"step": 107
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 8.56,
|
| 1716 |
+
"eval_accuracy": 0.528,
|
| 1717 |
+
"eval_loss": 0.6744531393051147,
|
| 1718 |
+
"eval_runtime": 2.5498,
|
| 1719 |
+
"eval_samples_per_second": 98.045,
|
| 1720 |
+
"eval_steps_per_second": 2.745,
|
| 1721 |
+
"step": 107
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 8.64,
|
| 1725 |
+
"grad_norm": 2.1070873737335205,
|
| 1726 |
+
"learning_rate": 5.084745762711865e-06,
|
| 1727 |
+
"loss": 0.6976,
|
| 1728 |
+
"step": 108
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 8.64,
|
| 1732 |
+
"eval_accuracy": 0.52,
|
| 1733 |
+
"eval_loss": 0.6756640672683716,
|
| 1734 |
+
"eval_runtime": 2.5509,
|
| 1735 |
+
"eval_samples_per_second": 98.005,
|
| 1736 |
+
"eval_steps_per_second": 2.744,
|
| 1737 |
+
"step": 108
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 8.72,
|
| 1741 |
+
"grad_norm": 1.433050513267517,
|
| 1742 |
+
"learning_rate": 4.6610169491525425e-06,
|
| 1743 |
+
"loss": 0.6447,
|
| 1744 |
+
"step": 109
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 8.72,
|
| 1748 |
+
"eval_accuracy": 0.528,
|
| 1749 |
+
"eval_loss": 0.6764531135559082,
|
| 1750 |
+
"eval_runtime": 2.5599,
|
| 1751 |
+
"eval_samples_per_second": 97.66,
|
| 1752 |
+
"eval_steps_per_second": 2.734,
|
| 1753 |
+
"step": 109
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 8.8,
|
| 1757 |
+
"grad_norm": 2.937915086746216,
|
| 1758 |
+
"learning_rate": 4.23728813559322e-06,
|
| 1759 |
+
"loss": 0.6964,
|
| 1760 |
+
"step": 110
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 8.8,
|
| 1764 |
+
"eval_accuracy": 0.516,
|
| 1765 |
+
"eval_loss": 0.6768437623977661,
|
| 1766 |
+
"eval_runtime": 2.5495,
|
| 1767 |
+
"eval_samples_per_second": 98.058,
|
| 1768 |
+
"eval_steps_per_second": 2.746,
|
| 1769 |
+
"step": 110
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 8.88,
|
| 1773 |
+
"grad_norm": 1.9771907329559326,
|
| 1774 |
+
"learning_rate": 3.813559322033899e-06,
|
| 1775 |
+
"loss": 0.6625,
|
| 1776 |
+
"step": 111
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 8.88,
|
| 1780 |
+
"eval_accuracy": 0.52,
|
| 1781 |
+
"eval_loss": 0.677441418170929,
|
| 1782 |
+
"eval_runtime": 2.5474,
|
| 1783 |
+
"eval_samples_per_second": 98.139,
|
| 1784 |
+
"eval_steps_per_second": 2.748,
|
| 1785 |
+
"step": 111
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 8.96,
|
| 1789 |
+
"grad_norm": 8.43002986907959,
|
| 1790 |
+
"learning_rate": 3.3898305084745763e-06,
|
| 1791 |
+
"loss": 0.7092,
|
| 1792 |
+
"step": 112
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 8.96,
|
| 1796 |
+
"eval_accuracy": 0.52,
|
| 1797 |
+
"eval_loss": 0.6763046979904175,
|
| 1798 |
+
"eval_runtime": 2.5006,
|
| 1799 |
+
"eval_samples_per_second": 99.975,
|
| 1800 |
+
"eval_steps_per_second": 2.799,
|
| 1801 |
+
"step": 112
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 9.04,
|
| 1805 |
+
"grad_norm": 16.455059051513672,
|
| 1806 |
+
"learning_rate": 2.9661016949152545e-06,
|
| 1807 |
+
"loss": 0.6859,
|
| 1808 |
+
"step": 113
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 9.04,
|
| 1812 |
+
"eval_accuracy": 0.524,
|
| 1813 |
+
"eval_loss": 0.6773906350135803,
|
| 1814 |
+
"eval_runtime": 2.5491,
|
| 1815 |
+
"eval_samples_per_second": 98.075,
|
| 1816 |
+
"eval_steps_per_second": 2.746,
|
| 1817 |
+
"step": 113
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 9.12,
|
| 1821 |
+
"grad_norm": 3.359854221343994,
|
| 1822 |
+
"learning_rate": 2.5423728813559323e-06,
|
| 1823 |
+
"loss": 0.6657,
|
| 1824 |
+
"step": 114
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 9.12,
|
| 1828 |
+
"eval_accuracy": 0.524,
|
| 1829 |
+
"eval_loss": 0.6762812733650208,
|
| 1830 |
+
"eval_runtime": 2.5524,
|
| 1831 |
+
"eval_samples_per_second": 97.946,
|
| 1832 |
+
"eval_steps_per_second": 2.742,
|
| 1833 |
+
"step": 114
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 9.2,
|
| 1837 |
+
"grad_norm": 3.9168431758880615,
|
| 1838 |
+
"learning_rate": 2.11864406779661e-06,
|
| 1839 |
+
"loss": 0.6546,
|
| 1840 |
+
"step": 115
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 9.2,
|
| 1844 |
+
"eval_accuracy": 0.52,
|
| 1845 |
+
"eval_loss": 0.6755898594856262,
|
| 1846 |
+
"eval_runtime": 2.5568,
|
| 1847 |
+
"eval_samples_per_second": 97.78,
|
| 1848 |
+
"eval_steps_per_second": 2.738,
|
| 1849 |
+
"step": 115
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 9.28,
|
| 1853 |
+
"grad_norm": 3.361232280731201,
|
| 1854 |
+
"learning_rate": 1.6949152542372882e-06,
|
| 1855 |
+
"loss": 0.7128,
|
| 1856 |
+
"step": 116
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 9.28,
|
| 1860 |
+
"eval_accuracy": 0.516,
|
| 1861 |
+
"eval_loss": 0.6770547032356262,
|
| 1862 |
+
"eval_runtime": 2.5602,
|
| 1863 |
+
"eval_samples_per_second": 97.649,
|
| 1864 |
+
"eval_steps_per_second": 2.734,
|
| 1865 |
+
"step": 116
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 9.36,
|
| 1869 |
+
"grad_norm": 2.9631147384643555,
|
| 1870 |
+
"learning_rate": 1.2711864406779662e-06,
|
| 1871 |
+
"loss": 0.6779,
|
| 1872 |
+
"step": 117
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 9.36,
|
| 1876 |
+
"eval_accuracy": 0.528,
|
| 1877 |
+
"eval_loss": 0.6765038967132568,
|
| 1878 |
+
"eval_runtime": 2.5606,
|
| 1879 |
+
"eval_samples_per_second": 97.633,
|
| 1880 |
+
"eval_steps_per_second": 2.734,
|
| 1881 |
+
"step": 117
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 9.44,
|
| 1885 |
+
"grad_norm": 4.792584419250488,
|
| 1886 |
+
"learning_rate": 8.474576271186441e-07,
|
| 1887 |
+
"loss": 0.6241,
|
| 1888 |
+
"step": 118
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 9.44,
|
| 1892 |
+
"eval_accuracy": 0.516,
|
| 1893 |
+
"eval_loss": 0.6751171946525574,
|
| 1894 |
+
"eval_runtime": 2.5493,
|
| 1895 |
+
"eval_samples_per_second": 98.066,
|
| 1896 |
+
"eval_steps_per_second": 2.746,
|
| 1897 |
+
"step": 118
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 9.52,
|
| 1901 |
+
"grad_norm": 5.438122749328613,
|
| 1902 |
+
"learning_rate": 4.2372881355932204e-07,
|
| 1903 |
+
"loss": 0.6748,
|
| 1904 |
+
"step": 119
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 9.52,
|
| 1908 |
+
"eval_accuracy": 0.516,
|
| 1909 |
+
"eval_loss": 0.6753047108650208,
|
| 1910 |
+
"eval_runtime": 2.5608,
|
| 1911 |
+
"eval_samples_per_second": 97.624,
|
| 1912 |
+
"eval_steps_per_second": 2.733,
|
| 1913 |
+
"step": 119
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 9.6,
|
| 1917 |
+
"grad_norm": 2.0531022548675537,
|
| 1918 |
+
"learning_rate": 0.0,
|
| 1919 |
+
"loss": 0.6738,
|
| 1920 |
+
"step": 120
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 9.6,
|
| 1924 |
+
"eval_accuracy": 0.524,
|
| 1925 |
+
"eval_loss": 0.6763242483139038,
|
| 1926 |
+
"eval_runtime": 2.5002,
|
| 1927 |
+
"eval_samples_per_second": 99.994,
|
| 1928 |
+
"eval_steps_per_second": 2.8,
|
| 1929 |
+
"step": 120
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 9.6,
|
| 1933 |
+
"step": 120,
|
| 1934 |
+
"total_flos": 2.3370919602814976e+16,
|
| 1935 |
+
"train_loss": 0.7025685042142868,
|
| 1936 |
+
"train_runtime": 671.5636,
|
| 1937 |
+
"train_samples_per_second": 14.891,
|
| 1938 |
+
"train_steps_per_second": 0.179
|
| 1939 |
+
}
|
| 1940 |
+
],
|
| 1941 |
+
"logging_steps": 1,
|
| 1942 |
+
"max_steps": 120,
|
| 1943 |
+
"num_input_tokens_seen": 0,
|
| 1944 |
+
"num_train_epochs": 10,
|
| 1945 |
+
"save_steps": 500,
|
| 1946 |
+
"total_flos": 2.3370919602814976e+16,
|
| 1947 |
+
"train_batch_size": 10,
|
| 1948 |
+
"trial_name": null,
|
| 1949 |
+
"trial_params": null
|
| 1950 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a079eefb3b5d6e104eecf4326c396504c14a92fe24ff3e72ece9a34cdf6c9f3c
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|