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-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: 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:cbde5587246764041af7d190a0b0779e65f193ded1c66a602dc51e05a12a0f27
|
| 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-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": 9.880268096923828,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 0.8184,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"eval_accuracy": 0.484,
|
| 21 |
+
"eval_loss": 0.794564425945282,
|
| 22 |
+
"eval_runtime": 2.0232,
|
| 23 |
+
"eval_samples_per_second": 123.566,
|
| 24 |
+
"eval_steps_per_second": 3.46,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.16,
|
| 29 |
+
"grad_norm": 13.567129135131836,
|
| 30 |
+
"learning_rate": 5e-05,
|
| 31 |
+
"loss": 0.8494,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.16,
|
| 36 |
+
"eval_accuracy": 0.484,
|
| 37 |
+
"eval_loss": 0.7883964776992798,
|
| 38 |
+
"eval_runtime": 2.0183,
|
| 39 |
+
"eval_samples_per_second": 123.869,
|
| 40 |
+
"eval_steps_per_second": 3.468,
|
| 41 |
+
"step": 2
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.24,
|
| 45 |
+
"grad_norm": 15.441740989685059,
|
| 46 |
+
"learning_rate": 4.957627118644068e-05,
|
| 47 |
+
"loss": 0.8586,
|
| 48 |
+
"step": 3
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.24,
|
| 52 |
+
"eval_accuracy": 0.484,
|
| 53 |
+
"eval_loss": 0.763421893119812,
|
| 54 |
+
"eval_runtime": 2.0194,
|
| 55 |
+
"eval_samples_per_second": 123.8,
|
| 56 |
+
"eval_steps_per_second": 3.466,
|
| 57 |
+
"step": 3
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.32,
|
| 61 |
+
"grad_norm": 7.4458136558532715,
|
| 62 |
+
"learning_rate": 4.915254237288136e-05,
|
| 63 |
+
"loss": 0.7138,
|
| 64 |
+
"step": 4
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.32,
|
| 68 |
+
"eval_accuracy": 0.484,
|
| 69 |
+
"eval_loss": 0.7402032017707825,
|
| 70 |
+
"eval_runtime": 2.0299,
|
| 71 |
+
"eval_samples_per_second": 123.158,
|
| 72 |
+
"eval_steps_per_second": 3.448,
|
| 73 |
+
"step": 4
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.4,
|
| 77 |
+
"grad_norm": 8.256447792053223,
|
| 78 |
+
"learning_rate": 4.8728813559322034e-05,
|
| 79 |
+
"loss": 0.718,
|
| 80 |
+
"step": 5
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.4,
|
| 84 |
+
"eval_accuracy": 0.496,
|
| 85 |
+
"eval_loss": 0.71826171875,
|
| 86 |
+
"eval_runtime": 2.0247,
|
| 87 |
+
"eval_samples_per_second": 123.473,
|
| 88 |
+
"eval_steps_per_second": 3.457,
|
| 89 |
+
"step": 5
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.48,
|
| 93 |
+
"grad_norm": 9.767592430114746,
|
| 94 |
+
"learning_rate": 4.8305084745762714e-05,
|
| 95 |
+
"loss": 0.754,
|
| 96 |
+
"step": 6
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.48,
|
| 100 |
+
"eval_accuracy": 0.504,
|
| 101 |
+
"eval_loss": 0.6996328234672546,
|
| 102 |
+
"eval_runtime": 2.0186,
|
| 103 |
+
"eval_samples_per_second": 123.847,
|
| 104 |
+
"eval_steps_per_second": 3.468,
|
| 105 |
+
"step": 6
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.56,
|
| 109 |
+
"grad_norm": 5.398552417755127,
|
| 110 |
+
"learning_rate": 4.788135593220339e-05,
|
| 111 |
+
"loss": 0.712,
|
| 112 |
+
"step": 7
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.56,
|
| 116 |
+
"eval_accuracy": 0.528,
|
| 117 |
+
"eval_loss": 0.689703106880188,
|
| 118 |
+
"eval_runtime": 2.0279,
|
| 119 |
+
"eval_samples_per_second": 123.282,
|
| 120 |
+
"eval_steps_per_second": 3.452,
|
| 121 |
+
"step": 7
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.64,
|
| 125 |
+
"grad_norm": 3.870819330215454,
|
| 126 |
+
"learning_rate": 4.745762711864407e-05,
|
| 127 |
+
"loss": 0.7295,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.64,
|
| 132 |
+
"eval_accuracy": 0.492,
|
| 133 |
+
"eval_loss": 0.6884413957595825,
|
| 134 |
+
"eval_runtime": 2.03,
|
| 135 |
+
"eval_samples_per_second": 123.154,
|
| 136 |
+
"eval_steps_per_second": 3.448,
|
| 137 |
+
"step": 8
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.72,
|
| 141 |
+
"grad_norm": 5.142106533050537,
|
| 142 |
+
"learning_rate": 4.703389830508475e-05,
|
| 143 |
+
"loss": 0.7051,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.72,
|
| 148 |
+
"eval_accuracy": 0.504,
|
| 149 |
+
"eval_loss": 0.6892617344856262,
|
| 150 |
+
"eval_runtime": 1.9705,
|
| 151 |
+
"eval_samples_per_second": 126.874,
|
| 152 |
+
"eval_steps_per_second": 3.552,
|
| 153 |
+
"step": 9
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.8,
|
| 157 |
+
"grad_norm": 5.520991325378418,
|
| 158 |
+
"learning_rate": 4.6610169491525425e-05,
|
| 159 |
+
"loss": 0.8498,
|
| 160 |
+
"step": 10
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.8,
|
| 164 |
+
"eval_accuracy": 0.492,
|
| 165 |
+
"eval_loss": 0.6888476610183716,
|
| 166 |
+
"eval_runtime": 2.0284,
|
| 167 |
+
"eval_samples_per_second": 123.25,
|
| 168 |
+
"eval_steps_per_second": 3.451,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.88,
|
| 173 |
+
"grad_norm": 4.853059768676758,
|
| 174 |
+
"learning_rate": 4.6186440677966104e-05,
|
| 175 |
+
"loss": 0.7578,
|
| 176 |
+
"step": 11
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.88,
|
| 180 |
+
"eval_accuracy": 0.468,
|
| 181 |
+
"eval_loss": 0.6881210803985596,
|
| 182 |
+
"eval_runtime": 2.0199,
|
| 183 |
+
"eval_samples_per_second": 123.766,
|
| 184 |
+
"eval_steps_per_second": 3.465,
|
| 185 |
+
"step": 11
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.96,
|
| 189 |
+
"grad_norm": 6.042579650878906,
|
| 190 |
+
"learning_rate": 4.5762711864406784e-05,
|
| 191 |
+
"loss": 0.7002,
|
| 192 |
+
"step": 12
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.96,
|
| 196 |
+
"eval_accuracy": 0.524,
|
| 197 |
+
"eval_loss": 0.6887617111206055,
|
| 198 |
+
"eval_runtime": 2.0231,
|
| 199 |
+
"eval_samples_per_second": 123.57,
|
| 200 |
+
"eval_steps_per_second": 3.46,
|
| 201 |
+
"step": 12
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.04,
|
| 205 |
+
"grad_norm": 2.7558984756469727,
|
| 206 |
+
"learning_rate": 4.533898305084746e-05,
|
| 207 |
+
"loss": 0.6943,
|
| 208 |
+
"step": 13
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.04,
|
| 212 |
+
"eval_accuracy": 0.52,
|
| 213 |
+
"eval_loss": 0.6887617111206055,
|
| 214 |
+
"eval_runtime": 2.0283,
|
| 215 |
+
"eval_samples_per_second": 123.257,
|
| 216 |
+
"eval_steps_per_second": 3.451,
|
| 217 |
+
"step": 13
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.12,
|
| 221 |
+
"grad_norm": 4.205049991607666,
|
| 222 |
+
"learning_rate": 4.491525423728814e-05,
|
| 223 |
+
"loss": 0.7401,
|
| 224 |
+
"step": 14
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.12,
|
| 228 |
+
"eval_accuracy": 0.532,
|
| 229 |
+
"eval_loss": 0.6896406412124634,
|
| 230 |
+
"eval_runtime": 2.0318,
|
| 231 |
+
"eval_samples_per_second": 123.045,
|
| 232 |
+
"eval_steps_per_second": 3.445,
|
| 233 |
+
"step": 14
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.2,
|
| 237 |
+
"grad_norm": 2.5496792793273926,
|
| 238 |
+
"learning_rate": 4.4491525423728816e-05,
|
| 239 |
+
"loss": 0.73,
|
| 240 |
+
"step": 15
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.2,
|
| 244 |
+
"eval_accuracy": 0.52,
|
| 245 |
+
"eval_loss": 0.6907109618186951,
|
| 246 |
+
"eval_runtime": 2.0241,
|
| 247 |
+
"eval_samples_per_second": 123.512,
|
| 248 |
+
"eval_steps_per_second": 3.458,
|
| 249 |
+
"step": 15
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.28,
|
| 253 |
+
"grad_norm": 8.400224685668945,
|
| 254 |
+
"learning_rate": 4.4067796610169495e-05,
|
| 255 |
+
"loss": 0.6979,
|
| 256 |
+
"step": 16
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.28,
|
| 260 |
+
"eval_accuracy": 0.524,
|
| 261 |
+
"eval_loss": 0.6910077929496765,
|
| 262 |
+
"eval_runtime": 2.0229,
|
| 263 |
+
"eval_samples_per_second": 123.583,
|
| 264 |
+
"eval_steps_per_second": 3.46,
|
| 265 |
+
"step": 16
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.3599999999999999,
|
| 269 |
+
"grad_norm": 2.9197959899902344,
|
| 270 |
+
"learning_rate": 4.3644067796610175e-05,
|
| 271 |
+
"loss": 0.7125,
|
| 272 |
+
"step": 17
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.3599999999999999,
|
| 276 |
+
"eval_accuracy": 0.524,
|
| 277 |
+
"eval_loss": 0.6910234093666077,
|
| 278 |
+
"eval_runtime": 2.0278,
|
| 279 |
+
"eval_samples_per_second": 123.287,
|
| 280 |
+
"eval_steps_per_second": 3.452,
|
| 281 |
+
"step": 17
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.44,
|
| 285 |
+
"grad_norm": 2.210724115371704,
|
| 286 |
+
"learning_rate": 4.3220338983050854e-05,
|
| 287 |
+
"loss": 0.7068,
|
| 288 |
+
"step": 18
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.44,
|
| 292 |
+
"eval_accuracy": 0.524,
|
| 293 |
+
"eval_loss": 0.6906171441078186,
|
| 294 |
+
"eval_runtime": 2.0216,
|
| 295 |
+
"eval_samples_per_second": 123.667,
|
| 296 |
+
"eval_steps_per_second": 3.463,
|
| 297 |
+
"step": 18
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.52,
|
| 301 |
+
"grad_norm": 9.887163162231445,
|
| 302 |
+
"learning_rate": 4.279661016949153e-05,
|
| 303 |
+
"loss": 0.7026,
|
| 304 |
+
"step": 19
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.52,
|
| 308 |
+
"eval_accuracy": 0.52,
|
| 309 |
+
"eval_loss": 0.6904453039169312,
|
| 310 |
+
"eval_runtime": 2.0246,
|
| 311 |
+
"eval_samples_per_second": 123.482,
|
| 312 |
+
"eval_steps_per_second": 3.458,
|
| 313 |
+
"step": 19
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.6,
|
| 317 |
+
"grad_norm": 1.4493184089660645,
|
| 318 |
+
"learning_rate": 4.2372881355932206e-05,
|
| 319 |
+
"loss": 0.7118,
|
| 320 |
+
"step": 20
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.6,
|
| 324 |
+
"eval_accuracy": 0.52,
|
| 325 |
+
"eval_loss": 0.691031277179718,
|
| 326 |
+
"eval_runtime": 2.0269,
|
| 327 |
+
"eval_samples_per_second": 123.339,
|
| 328 |
+
"eval_steps_per_second": 3.453,
|
| 329 |
+
"step": 20
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.6800000000000002,
|
| 333 |
+
"grad_norm": 2.368281364440918,
|
| 334 |
+
"learning_rate": 4.1949152542372886e-05,
|
| 335 |
+
"loss": 0.7186,
|
| 336 |
+
"step": 21
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.6800000000000002,
|
| 340 |
+
"eval_accuracy": 0.52,
|
| 341 |
+
"eval_loss": 0.6909297108650208,
|
| 342 |
+
"eval_runtime": 2.021,
|
| 343 |
+
"eval_samples_per_second": 123.701,
|
| 344 |
+
"eval_steps_per_second": 3.464,
|
| 345 |
+
"step": 21
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.76,
|
| 349 |
+
"grad_norm": 1.8369947671890259,
|
| 350 |
+
"learning_rate": 4.152542372881356e-05,
|
| 351 |
+
"loss": 0.7003,
|
| 352 |
+
"step": 22
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.76,
|
| 356 |
+
"eval_accuracy": 0.52,
|
| 357 |
+
"eval_loss": 0.6904531121253967,
|
| 358 |
+
"eval_runtime": 2.0203,
|
| 359 |
+
"eval_samples_per_second": 123.741,
|
| 360 |
+
"eval_steps_per_second": 3.465,
|
| 361 |
+
"step": 22
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.8399999999999999,
|
| 365 |
+
"grad_norm": 3.725130796432495,
|
| 366 |
+
"learning_rate": 4.110169491525424e-05,
|
| 367 |
+
"loss": 0.6743,
|
| 368 |
+
"step": 23
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.8399999999999999,
|
| 372 |
+
"eval_accuracy": 0.52,
|
| 373 |
+
"eval_loss": 0.6904218792915344,
|
| 374 |
+
"eval_runtime": 2.0289,
|
| 375 |
+
"eval_samples_per_second": 123.217,
|
| 376 |
+
"eval_steps_per_second": 3.45,
|
| 377 |
+
"step": 23
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.92,
|
| 381 |
+
"grad_norm": 10.2611665725708,
|
| 382 |
+
"learning_rate": 4.067796610169492e-05,
|
| 383 |
+
"loss": 0.7153,
|
| 384 |
+
"step": 24
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.92,
|
| 388 |
+
"eval_accuracy": 0.524,
|
| 389 |
+
"eval_loss": 0.6903828382492065,
|
| 390 |
+
"eval_runtime": 2.0289,
|
| 391 |
+
"eval_samples_per_second": 123.222,
|
| 392 |
+
"eval_steps_per_second": 3.45,
|
| 393 |
+
"step": 24
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.0,
|
| 397 |
+
"grad_norm": 2.8820903301239014,
|
| 398 |
+
"learning_rate": 4.025423728813559e-05,
|
| 399 |
+
"loss": 0.7439,
|
| 400 |
+
"step": 25
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.0,
|
| 404 |
+
"eval_accuracy": 0.524,
|
| 405 |
+
"eval_loss": 0.6901171803474426,
|
| 406 |
+
"eval_runtime": 2.0222,
|
| 407 |
+
"eval_samples_per_second": 123.628,
|
| 408 |
+
"eval_steps_per_second": 3.462,
|
| 409 |
+
"step": 25
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.08,
|
| 413 |
+
"grad_norm": 3.839857816696167,
|
| 414 |
+
"learning_rate": 3.983050847457627e-05,
|
| 415 |
+
"loss": 0.7569,
|
| 416 |
+
"step": 26
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.08,
|
| 420 |
+
"eval_accuracy": 0.528,
|
| 421 |
+
"eval_loss": 0.690011739730835,
|
| 422 |
+
"eval_runtime": 2.0192,
|
| 423 |
+
"eval_samples_per_second": 123.81,
|
| 424 |
+
"eval_steps_per_second": 3.467,
|
| 425 |
+
"step": 26
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.16,
|
| 429 |
+
"grad_norm": 2.944941520690918,
|
| 430 |
+
"learning_rate": 3.940677966101695e-05,
|
| 431 |
+
"loss": 0.7443,
|
| 432 |
+
"step": 27
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.16,
|
| 436 |
+
"eval_accuracy": 0.528,
|
| 437 |
+
"eval_loss": 0.6898750066757202,
|
| 438 |
+
"eval_runtime": 2.0288,
|
| 439 |
+
"eval_samples_per_second": 123.224,
|
| 440 |
+
"eval_steps_per_second": 3.45,
|
| 441 |
+
"step": 27
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.24,
|
| 445 |
+
"grad_norm": 2.2883877754211426,
|
| 446 |
+
"learning_rate": 3.898305084745763e-05,
|
| 447 |
+
"loss": 0.7171,
|
| 448 |
+
"step": 28
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.24,
|
| 452 |
+
"eval_accuracy": 0.528,
|
| 453 |
+
"eval_loss": 0.6903359293937683,
|
| 454 |
+
"eval_runtime": 2.0189,
|
| 455 |
+
"eval_samples_per_second": 123.832,
|
| 456 |
+
"eval_steps_per_second": 3.467,
|
| 457 |
+
"step": 28
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.32,
|
| 461 |
+
"grad_norm": 5.3827691078186035,
|
| 462 |
+
"learning_rate": 3.855932203389831e-05,
|
| 463 |
+
"loss": 0.755,
|
| 464 |
+
"step": 29
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.32,
|
| 468 |
+
"eval_accuracy": 0.52,
|
| 469 |
+
"eval_loss": 0.6900156140327454,
|
| 470 |
+
"eval_runtime": 2.0291,
|
| 471 |
+
"eval_samples_per_second": 123.209,
|
| 472 |
+
"eval_steps_per_second": 3.45,
|
| 473 |
+
"step": 29
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.4,
|
| 477 |
+
"grad_norm": 2.5618762969970703,
|
| 478 |
+
"learning_rate": 3.813559322033898e-05,
|
| 479 |
+
"loss": 0.6827,
|
| 480 |
+
"step": 30
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.4,
|
| 484 |
+
"eval_accuracy": 0.524,
|
| 485 |
+
"eval_loss": 0.6895468831062317,
|
| 486 |
+
"eval_runtime": 2.0196,
|
| 487 |
+
"eval_samples_per_second": 123.787,
|
| 488 |
+
"eval_steps_per_second": 3.466,
|
| 489 |
+
"step": 30
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.48,
|
| 493 |
+
"grad_norm": 3.690232276916504,
|
| 494 |
+
"learning_rate": 3.771186440677966e-05,
|
| 495 |
+
"loss": 0.7392,
|
| 496 |
+
"step": 31
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.48,
|
| 500 |
+
"eval_accuracy": 0.52,
|
| 501 |
+
"eval_loss": 0.6898476481437683,
|
| 502 |
+
"eval_runtime": 2.0266,
|
| 503 |
+
"eval_samples_per_second": 123.361,
|
| 504 |
+
"eval_steps_per_second": 3.454,
|
| 505 |
+
"step": 31
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.56,
|
| 509 |
+
"grad_norm": 1.4257826805114746,
|
| 510 |
+
"learning_rate": 3.728813559322034e-05,
|
| 511 |
+
"loss": 0.7212,
|
| 512 |
+
"step": 32
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.56,
|
| 516 |
+
"eval_accuracy": 0.528,
|
| 517 |
+
"eval_loss": 0.6890624761581421,
|
| 518 |
+
"eval_runtime": 2.0204,
|
| 519 |
+
"eval_samples_per_second": 123.738,
|
| 520 |
+
"eval_steps_per_second": 3.465,
|
| 521 |
+
"step": 32
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.64,
|
| 525 |
+
"grad_norm": 1.9220340251922607,
|
| 526 |
+
"learning_rate": 3.686440677966102e-05,
|
| 527 |
+
"loss": 0.7333,
|
| 528 |
+
"step": 33
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.64,
|
| 532 |
+
"eval_accuracy": 0.528,
|
| 533 |
+
"eval_loss": 0.689382791519165,
|
| 534 |
+
"eval_runtime": 2.0254,
|
| 535 |
+
"eval_samples_per_second": 123.43,
|
| 536 |
+
"eval_steps_per_second": 3.456,
|
| 537 |
+
"step": 33
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.7199999999999998,
|
| 541 |
+
"grad_norm": 7.450087070465088,
|
| 542 |
+
"learning_rate": 3.644067796610169e-05,
|
| 543 |
+
"loss": 0.7509,
|
| 544 |
+
"step": 34
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.7199999999999998,
|
| 548 |
+
"eval_accuracy": 0.528,
|
| 549 |
+
"eval_loss": 0.689257800579071,
|
| 550 |
+
"eval_runtime": 2.0291,
|
| 551 |
+
"eval_samples_per_second": 123.206,
|
| 552 |
+
"eval_steps_per_second": 3.45,
|
| 553 |
+
"step": 34
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.8,
|
| 557 |
+
"grad_norm": 8.32366943359375,
|
| 558 |
+
"learning_rate": 3.601694915254237e-05,
|
| 559 |
+
"loss": 0.7312,
|
| 560 |
+
"step": 35
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.8,
|
| 564 |
+
"eval_accuracy": 0.528,
|
| 565 |
+
"eval_loss": 0.6896445155143738,
|
| 566 |
+
"eval_runtime": 2.0268,
|
| 567 |
+
"eval_samples_per_second": 123.345,
|
| 568 |
+
"eval_steps_per_second": 3.454,
|
| 569 |
+
"step": 35
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.88,
|
| 573 |
+
"grad_norm": 8.8251314163208,
|
| 574 |
+
"learning_rate": 3.559322033898305e-05,
|
| 575 |
+
"loss": 0.6624,
|
| 576 |
+
"step": 36
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.88,
|
| 580 |
+
"eval_accuracy": 0.528,
|
| 581 |
+
"eval_loss": 0.6905156373977661,
|
| 582 |
+
"eval_runtime": 2.0218,
|
| 583 |
+
"eval_samples_per_second": 123.651,
|
| 584 |
+
"eval_steps_per_second": 3.462,
|
| 585 |
+
"step": 36
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.96,
|
| 589 |
+
"grad_norm": 4.100712299346924,
|
| 590 |
+
"learning_rate": 3.516949152542373e-05,
|
| 591 |
+
"loss": 0.7233,
|
| 592 |
+
"step": 37
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.96,
|
| 596 |
+
"eval_accuracy": 0.52,
|
| 597 |
+
"eval_loss": 0.6898671984672546,
|
| 598 |
+
"eval_runtime": 2.0212,
|
| 599 |
+
"eval_samples_per_second": 123.69,
|
| 600 |
+
"eval_steps_per_second": 3.463,
|
| 601 |
+
"step": 37
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 3.04,
|
| 605 |
+
"grad_norm": 2.2732489109039307,
|
| 606 |
+
"learning_rate": 3.474576271186441e-05,
|
| 607 |
+
"loss": 0.6459,
|
| 608 |
+
"step": 38
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.04,
|
| 612 |
+
"eval_accuracy": 0.524,
|
| 613 |
+
"eval_loss": 0.6897343993186951,
|
| 614 |
+
"eval_runtime": 2.0299,
|
| 615 |
+
"eval_samples_per_second": 123.161,
|
| 616 |
+
"eval_steps_per_second": 3.449,
|
| 617 |
+
"step": 38
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.12,
|
| 621 |
+
"grad_norm": 4.981455326080322,
|
| 622 |
+
"learning_rate": 3.432203389830508e-05,
|
| 623 |
+
"loss": 0.7077,
|
| 624 |
+
"step": 39
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.12,
|
| 628 |
+
"eval_accuracy": 0.532,
|
| 629 |
+
"eval_loss": 0.6902265548706055,
|
| 630 |
+
"eval_runtime": 2.0257,
|
| 631 |
+
"eval_samples_per_second": 123.414,
|
| 632 |
+
"eval_steps_per_second": 3.456,
|
| 633 |
+
"step": 39
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.2,
|
| 637 |
+
"grad_norm": 4.601206302642822,
|
| 638 |
+
"learning_rate": 3.389830508474576e-05,
|
| 639 |
+
"loss": 0.7111,
|
| 640 |
+
"step": 40
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.2,
|
| 644 |
+
"eval_accuracy": 0.528,
|
| 645 |
+
"eval_loss": 0.6908008456230164,
|
| 646 |
+
"eval_runtime": 2.0209,
|
| 647 |
+
"eval_samples_per_second": 123.706,
|
| 648 |
+
"eval_steps_per_second": 3.464,
|
| 649 |
+
"step": 40
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 3.2800000000000002,
|
| 653 |
+
"grad_norm": 1.5413074493408203,
|
| 654 |
+
"learning_rate": 3.347457627118644e-05,
|
| 655 |
+
"loss": 0.6503,
|
| 656 |
+
"step": 41
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.2800000000000002,
|
| 660 |
+
"eval_accuracy": 0.524,
|
| 661 |
+
"eval_loss": 0.6919609308242798,
|
| 662 |
+
"eval_runtime": 2.0246,
|
| 663 |
+
"eval_samples_per_second": 123.478,
|
| 664 |
+
"eval_steps_per_second": 3.457,
|
| 665 |
+
"step": 41
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 3.36,
|
| 669 |
+
"grad_norm": 4.281999111175537,
|
| 670 |
+
"learning_rate": 3.305084745762712e-05,
|
| 671 |
+
"loss": 0.7574,
|
| 672 |
+
"step": 42
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 3.36,
|
| 676 |
+
"eval_accuracy": 0.524,
|
| 677 |
+
"eval_loss": 0.6926249861717224,
|
| 678 |
+
"eval_runtime": 2.0304,
|
| 679 |
+
"eval_samples_per_second": 123.13,
|
| 680 |
+
"eval_steps_per_second": 3.448,
|
| 681 |
+
"step": 42
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.44,
|
| 685 |
+
"grad_norm": 5.510625839233398,
|
| 686 |
+
"learning_rate": 3.26271186440678e-05,
|
| 687 |
+
"loss": 0.6575,
|
| 688 |
+
"step": 43
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.44,
|
| 692 |
+
"eval_accuracy": 0.524,
|
| 693 |
+
"eval_loss": 0.6930938363075256,
|
| 694 |
+
"eval_runtime": 2.0293,
|
| 695 |
+
"eval_samples_per_second": 123.196,
|
| 696 |
+
"eval_steps_per_second": 3.449,
|
| 697 |
+
"step": 43
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 3.52,
|
| 701 |
+
"grad_norm": 4.354837417602539,
|
| 702 |
+
"learning_rate": 3.2203389830508473e-05,
|
| 703 |
+
"loss": 0.7324,
|
| 704 |
+
"step": 44
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.52,
|
| 708 |
+
"eval_accuracy": 0.524,
|
| 709 |
+
"eval_loss": 0.6937890648841858,
|
| 710 |
+
"eval_runtime": 2.0277,
|
| 711 |
+
"eval_samples_per_second": 123.292,
|
| 712 |
+
"eval_steps_per_second": 3.452,
|
| 713 |
+
"step": 44
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 3.6,
|
| 717 |
+
"grad_norm": 5.1033148765563965,
|
| 718 |
+
"learning_rate": 3.177966101694915e-05,
|
| 719 |
+
"loss": 0.6588,
|
| 720 |
+
"step": 45
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 3.6,
|
| 724 |
+
"eval_accuracy": 0.524,
|
| 725 |
+
"eval_loss": 0.6935625076293945,
|
| 726 |
+
"eval_runtime": 2.0277,
|
| 727 |
+
"eval_samples_per_second": 123.291,
|
| 728 |
+
"eval_steps_per_second": 3.452,
|
| 729 |
+
"step": 45
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.68,
|
| 733 |
+
"grad_norm": 7.331698894500732,
|
| 734 |
+
"learning_rate": 3.135593220338983e-05,
|
| 735 |
+
"loss": 0.8145,
|
| 736 |
+
"step": 46
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 3.68,
|
| 740 |
+
"eval_accuracy": 0.524,
|
| 741 |
+
"eval_loss": 0.6932734251022339,
|
| 742 |
+
"eval_runtime": 2.0207,
|
| 743 |
+
"eval_samples_per_second": 123.72,
|
| 744 |
+
"eval_steps_per_second": 3.464,
|
| 745 |
+
"step": 46
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 3.76,
|
| 749 |
+
"grad_norm": 7.018001079559326,
|
| 750 |
+
"learning_rate": 3.093220338983051e-05,
|
| 751 |
+
"loss": 0.7016,
|
| 752 |
+
"step": 47
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.76,
|
| 756 |
+
"eval_accuracy": 0.524,
|
| 757 |
+
"eval_loss": 0.6925547122955322,
|
| 758 |
+
"eval_runtime": 2.0244,
|
| 759 |
+
"eval_samples_per_second": 123.49,
|
| 760 |
+
"eval_steps_per_second": 3.458,
|
| 761 |
+
"step": 47
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 3.84,
|
| 765 |
+
"grad_norm": 3.4472386837005615,
|
| 766 |
+
"learning_rate": 3.050847457627119e-05,
|
| 767 |
+
"loss": 0.6726,
|
| 768 |
+
"step": 48
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 3.84,
|
| 772 |
+
"eval_accuracy": 0.524,
|
| 773 |
+
"eval_loss": 0.692257821559906,
|
| 774 |
+
"eval_runtime": 2.0236,
|
| 775 |
+
"eval_samples_per_second": 123.539,
|
| 776 |
+
"eval_steps_per_second": 3.459,
|
| 777 |
+
"step": 48
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.92,
|
| 781 |
+
"grad_norm": 7.608280181884766,
|
| 782 |
+
"learning_rate": 3.0084745762711864e-05,
|
| 783 |
+
"loss": 0.7211,
|
| 784 |
+
"step": 49
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 3.92,
|
| 788 |
+
"eval_accuracy": 0.528,
|
| 789 |
+
"eval_loss": 0.6909765601158142,
|
| 790 |
+
"eval_runtime": 2.0313,
|
| 791 |
+
"eval_samples_per_second": 123.075,
|
| 792 |
+
"eval_steps_per_second": 3.446,
|
| 793 |
+
"step": 49
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 4.0,
|
| 797 |
+
"grad_norm": 2.3237762451171875,
|
| 798 |
+
"learning_rate": 2.9661016949152544e-05,
|
| 799 |
+
"loss": 0.7066,
|
| 800 |
+
"step": 50
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 4.0,
|
| 804 |
+
"eval_accuracy": 0.528,
|
| 805 |
+
"eval_loss": 0.6903671622276306,
|
| 806 |
+
"eval_runtime": 2.025,
|
| 807 |
+
"eval_samples_per_second": 123.457,
|
| 808 |
+
"eval_steps_per_second": 3.457,
|
| 809 |
+
"step": 50
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 4.08,
|
| 813 |
+
"grad_norm": 3.2661080360412598,
|
| 814 |
+
"learning_rate": 2.9237288135593223e-05,
|
| 815 |
+
"loss": 0.7416,
|
| 816 |
+
"step": 51
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 4.08,
|
| 820 |
+
"eval_accuracy": 0.52,
|
| 821 |
+
"eval_loss": 0.690011739730835,
|
| 822 |
+
"eval_runtime": 2.0217,
|
| 823 |
+
"eval_samples_per_second": 123.657,
|
| 824 |
+
"eval_steps_per_second": 3.462,
|
| 825 |
+
"step": 51
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 4.16,
|
| 829 |
+
"grad_norm": 6.197864532470703,
|
| 830 |
+
"learning_rate": 2.88135593220339e-05,
|
| 831 |
+
"loss": 0.6967,
|
| 832 |
+
"step": 52
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 4.16,
|
| 836 |
+
"eval_accuracy": 0.52,
|
| 837 |
+
"eval_loss": 0.6896718740463257,
|
| 838 |
+
"eval_runtime": 2.0228,
|
| 839 |
+
"eval_samples_per_second": 123.592,
|
| 840 |
+
"eval_steps_per_second": 3.461,
|
| 841 |
+
"step": 52
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 4.24,
|
| 845 |
+
"grad_norm": 12.455964088439941,
|
| 846 |
+
"learning_rate": 2.838983050847458e-05,
|
| 847 |
+
"loss": 0.6901,
|
| 848 |
+
"step": 53
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 4.24,
|
| 852 |
+
"eval_accuracy": 0.528,
|
| 853 |
+
"eval_loss": 0.6897343993186951,
|
| 854 |
+
"eval_runtime": 2.0305,
|
| 855 |
+
"eval_samples_per_second": 123.123,
|
| 856 |
+
"eval_steps_per_second": 3.447,
|
| 857 |
+
"step": 53
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 4.32,
|
| 861 |
+
"grad_norm": 4.135785102844238,
|
| 862 |
+
"learning_rate": 2.7966101694915255e-05,
|
| 863 |
+
"loss": 0.7262,
|
| 864 |
+
"step": 54
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 4.32,
|
| 868 |
+
"eval_accuracy": 0.528,
|
| 869 |
+
"eval_loss": 0.6892734169960022,
|
| 870 |
+
"eval_runtime": 2.022,
|
| 871 |
+
"eval_samples_per_second": 123.642,
|
| 872 |
+
"eval_steps_per_second": 3.462,
|
| 873 |
+
"step": 54
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 4.4,
|
| 877 |
+
"grad_norm": 2.7662761211395264,
|
| 878 |
+
"learning_rate": 2.754237288135593e-05,
|
| 879 |
+
"loss": 0.7369,
|
| 880 |
+
"step": 55
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 4.4,
|
| 884 |
+
"eval_accuracy": 0.528,
|
| 885 |
+
"eval_loss": 0.6887929439544678,
|
| 886 |
+
"eval_runtime": 2.0254,
|
| 887 |
+
"eval_samples_per_second": 123.434,
|
| 888 |
+
"eval_steps_per_second": 3.456,
|
| 889 |
+
"step": 55
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 4.48,
|
| 893 |
+
"grad_norm": 7.013899326324463,
|
| 894 |
+
"learning_rate": 2.711864406779661e-05,
|
| 895 |
+
"loss": 0.754,
|
| 896 |
+
"step": 56
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 4.48,
|
| 900 |
+
"eval_accuracy": 0.524,
|
| 901 |
+
"eval_loss": 0.6891640424728394,
|
| 902 |
+
"eval_runtime": 2.0296,
|
| 903 |
+
"eval_samples_per_second": 123.174,
|
| 904 |
+
"eval_steps_per_second": 3.449,
|
| 905 |
+
"step": 56
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 4.5600000000000005,
|
| 909 |
+
"grad_norm": 4.8530144691467285,
|
| 910 |
+
"learning_rate": 2.669491525423729e-05,
|
| 911 |
+
"loss": 0.707,
|
| 912 |
+
"step": 57
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 4.5600000000000005,
|
| 916 |
+
"eval_accuracy": 0.524,
|
| 917 |
+
"eval_loss": 0.6898828744888306,
|
| 918 |
+
"eval_runtime": 2.0231,
|
| 919 |
+
"eval_samples_per_second": 123.571,
|
| 920 |
+
"eval_steps_per_second": 3.46,
|
| 921 |
+
"step": 57
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 4.64,
|
| 925 |
+
"grad_norm": 3.5552706718444824,
|
| 926 |
+
"learning_rate": 2.627118644067797e-05,
|
| 927 |
+
"loss": 0.7089,
|
| 928 |
+
"step": 58
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 4.64,
|
| 932 |
+
"eval_accuracy": 0.52,
|
| 933 |
+
"eval_loss": 0.6896093487739563,
|
| 934 |
+
"eval_runtime": 2.0292,
|
| 935 |
+
"eval_samples_per_second": 123.2,
|
| 936 |
+
"eval_steps_per_second": 3.45,
|
| 937 |
+
"step": 58
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 4.72,
|
| 941 |
+
"grad_norm": 2.477534532546997,
|
| 942 |
+
"learning_rate": 2.5847457627118642e-05,
|
| 943 |
+
"loss": 0.7266,
|
| 944 |
+
"step": 59
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 4.72,
|
| 948 |
+
"eval_accuracy": 0.524,
|
| 949 |
+
"eval_loss": 0.690679669380188,
|
| 950 |
+
"eval_runtime": 2.0212,
|
| 951 |
+
"eval_samples_per_second": 123.688,
|
| 952 |
+
"eval_steps_per_second": 3.463,
|
| 953 |
+
"step": 59
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 4.8,
|
| 957 |
+
"grad_norm": 7.140619277954102,
|
| 958 |
+
"learning_rate": 2.5423728813559322e-05,
|
| 959 |
+
"loss": 0.7071,
|
| 960 |
+
"step": 60
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 4.8,
|
| 964 |
+
"eval_accuracy": 0.516,
|
| 965 |
+
"eval_loss": 0.6908749938011169,
|
| 966 |
+
"eval_runtime": 2.0308,
|
| 967 |
+
"eval_samples_per_second": 123.105,
|
| 968 |
+
"eval_steps_per_second": 3.447,
|
| 969 |
+
"step": 60
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 4.88,
|
| 973 |
+
"grad_norm": 2.1332101821899414,
|
| 974 |
+
"learning_rate": 2.5e-05,
|
| 975 |
+
"loss": 0.6684,
|
| 976 |
+
"step": 61
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 4.88,
|
| 980 |
+
"eval_accuracy": 0.512,
|
| 981 |
+
"eval_loss": 0.6921796798706055,
|
| 982 |
+
"eval_runtime": 2.0217,
|
| 983 |
+
"eval_samples_per_second": 123.659,
|
| 984 |
+
"eval_steps_per_second": 3.462,
|
| 985 |
+
"step": 61
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 4.96,
|
| 989 |
+
"grad_norm": 6.111132621765137,
|
| 990 |
+
"learning_rate": 2.457627118644068e-05,
|
| 991 |
+
"loss": 0.7108,
|
| 992 |
+
"step": 62
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 4.96,
|
| 996 |
+
"eval_accuracy": 0.512,
|
| 997 |
+
"eval_loss": 0.6918125152587891,
|
| 998 |
+
"eval_runtime": 2.0232,
|
| 999 |
+
"eval_samples_per_second": 123.57,
|
| 1000 |
+
"eval_steps_per_second": 3.46,
|
| 1001 |
+
"step": 62
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 5.04,
|
| 1005 |
+
"grad_norm": 2.674424171447754,
|
| 1006 |
+
"learning_rate": 2.4152542372881357e-05,
|
| 1007 |
+
"loss": 0.6958,
|
| 1008 |
+
"step": 63
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 5.04,
|
| 1012 |
+
"eval_accuracy": 0.516,
|
| 1013 |
+
"eval_loss": 0.692257821559906,
|
| 1014 |
+
"eval_runtime": 2.0217,
|
| 1015 |
+
"eval_samples_per_second": 123.657,
|
| 1016 |
+
"eval_steps_per_second": 3.462,
|
| 1017 |
+
"step": 63
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 5.12,
|
| 1021 |
+
"grad_norm": 4.979844093322754,
|
| 1022 |
+
"learning_rate": 2.3728813559322036e-05,
|
| 1023 |
+
"loss": 0.6996,
|
| 1024 |
+
"step": 64
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 5.12,
|
| 1028 |
+
"eval_accuracy": 0.512,
|
| 1029 |
+
"eval_loss": 0.6926876306533813,
|
| 1030 |
+
"eval_runtime": 2.0292,
|
| 1031 |
+
"eval_samples_per_second": 123.198,
|
| 1032 |
+
"eval_steps_per_second": 3.45,
|
| 1033 |
+
"step": 64
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 5.2,
|
| 1037 |
+
"grad_norm": 1.8670213222503662,
|
| 1038 |
+
"learning_rate": 2.3305084745762712e-05,
|
| 1039 |
+
"loss": 0.7389,
|
| 1040 |
+
"step": 65
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 5.2,
|
| 1044 |
+
"eval_accuracy": 0.512,
|
| 1045 |
+
"eval_loss": 0.693109393119812,
|
| 1046 |
+
"eval_runtime": 2.022,
|
| 1047 |
+
"eval_samples_per_second": 123.639,
|
| 1048 |
+
"eval_steps_per_second": 3.462,
|
| 1049 |
+
"step": 65
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 5.28,
|
| 1053 |
+
"grad_norm": 4.056942939758301,
|
| 1054 |
+
"learning_rate": 2.2881355932203392e-05,
|
| 1055 |
+
"loss": 0.7584,
|
| 1056 |
+
"step": 66
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 5.28,
|
| 1060 |
+
"eval_accuracy": 0.512,
|
| 1061 |
+
"eval_loss": 0.6923593878746033,
|
| 1062 |
+
"eval_runtime": 2.0259,
|
| 1063 |
+
"eval_samples_per_second": 123.399,
|
| 1064 |
+
"eval_steps_per_second": 3.455,
|
| 1065 |
+
"step": 66
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 5.36,
|
| 1069 |
+
"grad_norm": 5.482074737548828,
|
| 1070 |
+
"learning_rate": 2.245762711864407e-05,
|
| 1071 |
+
"loss": 0.6746,
|
| 1072 |
+
"step": 67
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 5.36,
|
| 1076 |
+
"eval_accuracy": 0.512,
|
| 1077 |
+
"eval_loss": 0.6919531226158142,
|
| 1078 |
+
"eval_runtime": 2.026,
|
| 1079 |
+
"eval_samples_per_second": 123.394,
|
| 1080 |
+
"eval_steps_per_second": 3.455,
|
| 1081 |
+
"step": 67
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 5.44,
|
| 1085 |
+
"grad_norm": 2.0411086082458496,
|
| 1086 |
+
"learning_rate": 2.2033898305084748e-05,
|
| 1087 |
+
"loss": 0.7089,
|
| 1088 |
+
"step": 68
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 5.44,
|
| 1092 |
+
"eval_accuracy": 0.516,
|
| 1093 |
+
"eval_loss": 0.6914218664169312,
|
| 1094 |
+
"eval_runtime": 2.0245,
|
| 1095 |
+
"eval_samples_per_second": 123.488,
|
| 1096 |
+
"eval_steps_per_second": 3.458,
|
| 1097 |
+
"step": 68
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 5.52,
|
| 1101 |
+
"grad_norm": 5.141605854034424,
|
| 1102 |
+
"learning_rate": 2.1610169491525427e-05,
|
| 1103 |
+
"loss": 0.6672,
|
| 1104 |
+
"step": 69
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 5.52,
|
| 1108 |
+
"eval_accuracy": 0.52,
|
| 1109 |
+
"eval_loss": 0.6912265419960022,
|
| 1110 |
+
"eval_runtime": 2.0218,
|
| 1111 |
+
"eval_samples_per_second": 123.65,
|
| 1112 |
+
"eval_steps_per_second": 3.462,
|
| 1113 |
+
"step": 69
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 5.6,
|
| 1117 |
+
"grad_norm": 1.6354871988296509,
|
| 1118 |
+
"learning_rate": 2.1186440677966103e-05,
|
| 1119 |
+
"loss": 0.6658,
|
| 1120 |
+
"step": 70
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 5.6,
|
| 1124 |
+
"eval_accuracy": 0.524,
|
| 1125 |
+
"eval_loss": 0.6908749938011169,
|
| 1126 |
+
"eval_runtime": 2.0254,
|
| 1127 |
+
"eval_samples_per_second": 123.435,
|
| 1128 |
+
"eval_steps_per_second": 3.456,
|
| 1129 |
+
"step": 70
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 5.68,
|
| 1133 |
+
"grad_norm": 2.918964385986328,
|
| 1134 |
+
"learning_rate": 2.076271186440678e-05,
|
| 1135 |
+
"loss": 0.7021,
|
| 1136 |
+
"step": 71
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 5.68,
|
| 1140 |
+
"eval_accuracy": 0.528,
|
| 1141 |
+
"eval_loss": 0.6909531354904175,
|
| 1142 |
+
"eval_runtime": 2.0283,
|
| 1143 |
+
"eval_samples_per_second": 123.256,
|
| 1144 |
+
"eval_steps_per_second": 3.451,
|
| 1145 |
+
"step": 71
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 5.76,
|
| 1149 |
+
"grad_norm": 4.230044841766357,
|
| 1150 |
+
"learning_rate": 2.033898305084746e-05,
|
| 1151 |
+
"loss": 0.67,
|
| 1152 |
+
"step": 72
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 5.76,
|
| 1156 |
+
"eval_accuracy": 0.524,
|
| 1157 |
+
"eval_loss": 0.6901953220367432,
|
| 1158 |
+
"eval_runtime": 2.0208,
|
| 1159 |
+
"eval_samples_per_second": 123.712,
|
| 1160 |
+
"eval_steps_per_second": 3.464,
|
| 1161 |
+
"step": 72
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 5.84,
|
| 1165 |
+
"grad_norm": 3.8107471466064453,
|
| 1166 |
+
"learning_rate": 1.9915254237288135e-05,
|
| 1167 |
+
"loss": 0.7184,
|
| 1168 |
+
"step": 73
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 5.84,
|
| 1172 |
+
"eval_accuracy": 0.528,
|
| 1173 |
+
"eval_loss": 0.6903281211853027,
|
| 1174 |
+
"eval_runtime": 2.0192,
|
| 1175 |
+
"eval_samples_per_second": 123.813,
|
| 1176 |
+
"eval_steps_per_second": 3.467,
|
| 1177 |
+
"step": 73
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 5.92,
|
| 1181 |
+
"grad_norm": 8.891433715820312,
|
| 1182 |
+
"learning_rate": 1.9491525423728814e-05,
|
| 1183 |
+
"loss": 0.7887,
|
| 1184 |
+
"step": 74
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 5.92,
|
| 1188 |
+
"eval_accuracy": 0.528,
|
| 1189 |
+
"eval_loss": 0.6897187232971191,
|
| 1190 |
+
"eval_runtime": 2.0311,
|
| 1191 |
+
"eval_samples_per_second": 123.085,
|
| 1192 |
+
"eval_steps_per_second": 3.446,
|
| 1193 |
+
"step": 74
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 6.0,
|
| 1197 |
+
"grad_norm": 3.761192798614502,
|
| 1198 |
+
"learning_rate": 1.906779661016949e-05,
|
| 1199 |
+
"loss": 0.6871,
|
| 1200 |
+
"step": 75
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 6.0,
|
| 1204 |
+
"eval_accuracy": 0.532,
|
| 1205 |
+
"eval_loss": 0.689648449420929,
|
| 1206 |
+
"eval_runtime": 2.0234,
|
| 1207 |
+
"eval_samples_per_second": 123.557,
|
| 1208 |
+
"eval_steps_per_second": 3.46,
|
| 1209 |
+
"step": 75
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 6.08,
|
| 1213 |
+
"grad_norm": 5.231982231140137,
|
| 1214 |
+
"learning_rate": 1.864406779661017e-05,
|
| 1215 |
+
"loss": 0.6555,
|
| 1216 |
+
"step": 76
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 6.08,
|
| 1220 |
+
"eval_accuracy": 0.532,
|
| 1221 |
+
"eval_loss": 0.689203143119812,
|
| 1222 |
+
"eval_runtime": 2.0301,
|
| 1223 |
+
"eval_samples_per_second": 123.147,
|
| 1224 |
+
"eval_steps_per_second": 3.448,
|
| 1225 |
+
"step": 76
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 6.16,
|
| 1229 |
+
"grad_norm": 4.370417594909668,
|
| 1230 |
+
"learning_rate": 1.8220338983050846e-05,
|
| 1231 |
+
"loss": 0.7241,
|
| 1232 |
+
"step": 77
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 6.16,
|
| 1236 |
+
"eval_accuracy": 0.528,
|
| 1237 |
+
"eval_loss": 0.6886523365974426,
|
| 1238 |
+
"eval_runtime": 2.0236,
|
| 1239 |
+
"eval_samples_per_second": 123.543,
|
| 1240 |
+
"eval_steps_per_second": 3.459,
|
| 1241 |
+
"step": 77
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 6.24,
|
| 1245 |
+
"grad_norm": 2.4579694271087646,
|
| 1246 |
+
"learning_rate": 1.7796610169491526e-05,
|
| 1247 |
+
"loss": 0.6802,
|
| 1248 |
+
"step": 78
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 6.24,
|
| 1252 |
+
"eval_accuracy": 0.532,
|
| 1253 |
+
"eval_loss": 0.6887656450271606,
|
| 1254 |
+
"eval_runtime": 2.0193,
|
| 1255 |
+
"eval_samples_per_second": 123.808,
|
| 1256 |
+
"eval_steps_per_second": 3.467,
|
| 1257 |
+
"step": 78
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 6.32,
|
| 1261 |
+
"grad_norm": 2.63549542427063,
|
| 1262 |
+
"learning_rate": 1.7372881355932205e-05,
|
| 1263 |
+
"loss": 0.6833,
|
| 1264 |
+
"step": 79
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 6.32,
|
| 1268 |
+
"eval_accuracy": 0.532,
|
| 1269 |
+
"eval_loss": 0.6883828043937683,
|
| 1270 |
+
"eval_runtime": 2.0284,
|
| 1271 |
+
"eval_samples_per_second": 123.247,
|
| 1272 |
+
"eval_steps_per_second": 3.451,
|
| 1273 |
+
"step": 79
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 6.4,
|
| 1277 |
+
"grad_norm": 4.547414779663086,
|
| 1278 |
+
"learning_rate": 1.694915254237288e-05,
|
| 1279 |
+
"loss": 0.7329,
|
| 1280 |
+
"step": 80
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 6.4,
|
| 1284 |
+
"eval_accuracy": 0.532,
|
| 1285 |
+
"eval_loss": 0.6879101395606995,
|
| 1286 |
+
"eval_runtime": 2.0191,
|
| 1287 |
+
"eval_samples_per_second": 123.819,
|
| 1288 |
+
"eval_steps_per_second": 3.467,
|
| 1289 |
+
"step": 80
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 6.48,
|
| 1293 |
+
"grad_norm": 3.964456558227539,
|
| 1294 |
+
"learning_rate": 1.652542372881356e-05,
|
| 1295 |
+
"loss": 0.6692,
|
| 1296 |
+
"step": 81
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 6.48,
|
| 1300 |
+
"eval_accuracy": 0.532,
|
| 1301 |
+
"eval_loss": 0.6881679892539978,
|
| 1302 |
+
"eval_runtime": 2.0284,
|
| 1303 |
+
"eval_samples_per_second": 123.251,
|
| 1304 |
+
"eval_steps_per_second": 3.451,
|
| 1305 |
+
"step": 81
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 6.5600000000000005,
|
| 1309 |
+
"grad_norm": 5.390689849853516,
|
| 1310 |
+
"learning_rate": 1.6101694915254237e-05,
|
| 1311 |
+
"loss": 0.6828,
|
| 1312 |
+
"step": 82
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 6.5600000000000005,
|
| 1316 |
+
"eval_accuracy": 0.528,
|
| 1317 |
+
"eval_loss": 0.6882968544960022,
|
| 1318 |
+
"eval_runtime": 2.0308,
|
| 1319 |
+
"eval_samples_per_second": 123.105,
|
| 1320 |
+
"eval_steps_per_second": 3.447,
|
| 1321 |
+
"step": 82
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 6.64,
|
| 1325 |
+
"grad_norm": 5.355860710144043,
|
| 1326 |
+
"learning_rate": 1.5677966101694916e-05,
|
| 1327 |
+
"loss": 0.7421,
|
| 1328 |
+
"step": 83
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 6.64,
|
| 1332 |
+
"eval_accuracy": 0.524,
|
| 1333 |
+
"eval_loss": 0.6880898475646973,
|
| 1334 |
+
"eval_runtime": 2.0269,
|
| 1335 |
+
"eval_samples_per_second": 123.342,
|
| 1336 |
+
"eval_steps_per_second": 3.454,
|
| 1337 |
+
"step": 83
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 6.72,
|
| 1341 |
+
"grad_norm": 4.701043128967285,
|
| 1342 |
+
"learning_rate": 1.5254237288135596e-05,
|
| 1343 |
+
"loss": 0.6674,
|
| 1344 |
+
"step": 84
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 6.72,
|
| 1348 |
+
"eval_accuracy": 0.524,
|
| 1349 |
+
"eval_loss": 0.6879178881645203,
|
| 1350 |
+
"eval_runtime": 2.0224,
|
| 1351 |
+
"eval_samples_per_second": 123.617,
|
| 1352 |
+
"eval_steps_per_second": 3.461,
|
| 1353 |
+
"step": 84
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 6.8,
|
| 1357 |
+
"grad_norm": 2.8967323303222656,
|
| 1358 |
+
"learning_rate": 1.4830508474576272e-05,
|
| 1359 |
+
"loss": 0.7777,
|
| 1360 |
+
"step": 85
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 6.8,
|
| 1364 |
+
"eval_accuracy": 0.516,
|
| 1365 |
+
"eval_loss": 0.6875312328338623,
|
| 1366 |
+
"eval_runtime": 2.0275,
|
| 1367 |
+
"eval_samples_per_second": 123.307,
|
| 1368 |
+
"eval_steps_per_second": 3.453,
|
| 1369 |
+
"step": 85
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 6.88,
|
| 1373 |
+
"grad_norm": 1.572066068649292,
|
| 1374 |
+
"learning_rate": 1.440677966101695e-05,
|
| 1375 |
+
"loss": 0.6839,
|
| 1376 |
+
"step": 86
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 6.88,
|
| 1380 |
+
"eval_accuracy": 0.516,
|
| 1381 |
+
"eval_loss": 0.687863290309906,
|
| 1382 |
+
"eval_runtime": 2.0216,
|
| 1383 |
+
"eval_samples_per_second": 123.662,
|
| 1384 |
+
"eval_steps_per_second": 3.463,
|
| 1385 |
+
"step": 86
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 6.96,
|
| 1389 |
+
"grad_norm": 3.870039224624634,
|
| 1390 |
+
"learning_rate": 1.3983050847457627e-05,
|
| 1391 |
+
"loss": 0.7349,
|
| 1392 |
+
"step": 87
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 6.96,
|
| 1396 |
+
"eval_accuracy": 0.52,
|
| 1397 |
+
"eval_loss": 0.6874960660934448,
|
| 1398 |
+
"eval_runtime": 2.0258,
|
| 1399 |
+
"eval_samples_per_second": 123.408,
|
| 1400 |
+
"eval_steps_per_second": 3.455,
|
| 1401 |
+
"step": 87
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 7.04,
|
| 1405 |
+
"grad_norm": 2.870877265930176,
|
| 1406 |
+
"learning_rate": 1.3559322033898305e-05,
|
| 1407 |
+
"loss": 0.6877,
|
| 1408 |
+
"step": 88
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 7.04,
|
| 1412 |
+
"eval_accuracy": 0.528,
|
| 1413 |
+
"eval_loss": 0.6879101395606995,
|
| 1414 |
+
"eval_runtime": 2.0295,
|
| 1415 |
+
"eval_samples_per_second": 123.183,
|
| 1416 |
+
"eval_steps_per_second": 3.449,
|
| 1417 |
+
"step": 88
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 7.12,
|
| 1421 |
+
"grad_norm": 8.396225929260254,
|
| 1422 |
+
"learning_rate": 1.3135593220338985e-05,
|
| 1423 |
+
"loss": 0.7215,
|
| 1424 |
+
"step": 89
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 7.12,
|
| 1428 |
+
"eval_accuracy": 0.528,
|
| 1429 |
+
"eval_loss": 0.6874336004257202,
|
| 1430 |
+
"eval_runtime": 1.9743,
|
| 1431 |
+
"eval_samples_per_second": 126.624,
|
| 1432 |
+
"eval_steps_per_second": 3.545,
|
| 1433 |
+
"step": 89
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 7.2,
|
| 1437 |
+
"grad_norm": 5.108537197113037,
|
| 1438 |
+
"learning_rate": 1.2711864406779661e-05,
|
| 1439 |
+
"loss": 0.7067,
|
| 1440 |
+
"step": 90
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 7.2,
|
| 1444 |
+
"eval_accuracy": 0.532,
|
| 1445 |
+
"eval_loss": 0.6867539286613464,
|
| 1446 |
+
"eval_runtime": 2.0219,
|
| 1447 |
+
"eval_samples_per_second": 123.646,
|
| 1448 |
+
"eval_steps_per_second": 3.462,
|
| 1449 |
+
"step": 90
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 7.28,
|
| 1453 |
+
"grad_norm": 6.04660177230835,
|
| 1454 |
+
"learning_rate": 1.228813559322034e-05,
|
| 1455 |
+
"loss": 0.6296,
|
| 1456 |
+
"step": 91
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 7.28,
|
| 1460 |
+
"eval_accuracy": 0.532,
|
| 1461 |
+
"eval_loss": 0.6873242259025574,
|
| 1462 |
+
"eval_runtime": 2.0208,
|
| 1463 |
+
"eval_samples_per_second": 123.711,
|
| 1464 |
+
"eval_steps_per_second": 3.464,
|
| 1465 |
+
"step": 91
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 7.36,
|
| 1469 |
+
"grad_norm": 1.4922665357589722,
|
| 1470 |
+
"learning_rate": 1.1864406779661018e-05,
|
| 1471 |
+
"loss": 0.7286,
|
| 1472 |
+
"step": 92
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 7.36,
|
| 1476 |
+
"eval_accuracy": 0.524,
|
| 1477 |
+
"eval_loss": 0.687429666519165,
|
| 1478 |
+
"eval_runtime": 2.0278,
|
| 1479 |
+
"eval_samples_per_second": 123.288,
|
| 1480 |
+
"eval_steps_per_second": 3.452,
|
| 1481 |
+
"step": 92
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 7.44,
|
| 1485 |
+
"grad_norm": 2.887815475463867,
|
| 1486 |
+
"learning_rate": 1.1440677966101696e-05,
|
| 1487 |
+
"loss": 0.6758,
|
| 1488 |
+
"step": 93
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 7.44,
|
| 1492 |
+
"eval_accuracy": 0.524,
|
| 1493 |
+
"eval_loss": 0.6870546936988831,
|
| 1494 |
+
"eval_runtime": 2.024,
|
| 1495 |
+
"eval_samples_per_second": 123.517,
|
| 1496 |
+
"eval_steps_per_second": 3.458,
|
| 1497 |
+
"step": 93
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 7.52,
|
| 1501 |
+
"grad_norm": 4.4572272300720215,
|
| 1502 |
+
"learning_rate": 1.1016949152542374e-05,
|
| 1503 |
+
"loss": 0.7017,
|
| 1504 |
+
"step": 94
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 7.52,
|
| 1508 |
+
"eval_accuracy": 0.528,
|
| 1509 |
+
"eval_loss": 0.6872226595878601,
|
| 1510 |
+
"eval_runtime": 2.0285,
|
| 1511 |
+
"eval_samples_per_second": 123.243,
|
| 1512 |
+
"eval_steps_per_second": 3.451,
|
| 1513 |
+
"step": 94
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 7.6,
|
| 1517 |
+
"grad_norm": 3.5533223152160645,
|
| 1518 |
+
"learning_rate": 1.0593220338983052e-05,
|
| 1519 |
+
"loss": 0.7203,
|
| 1520 |
+
"step": 95
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 7.6,
|
| 1524 |
+
"eval_accuracy": 0.54,
|
| 1525 |
+
"eval_loss": 0.6870664358139038,
|
| 1526 |
+
"eval_runtime": 2.0221,
|
| 1527 |
+
"eval_samples_per_second": 123.636,
|
| 1528 |
+
"eval_steps_per_second": 3.462,
|
| 1529 |
+
"step": 95
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 7.68,
|
| 1533 |
+
"grad_norm": 2.765678882598877,
|
| 1534 |
+
"learning_rate": 1.016949152542373e-05,
|
| 1535 |
+
"loss": 0.7448,
|
| 1536 |
+
"step": 96
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 7.68,
|
| 1540 |
+
"eval_accuracy": 0.532,
|
| 1541 |
+
"eval_loss": 0.6872734427452087,
|
| 1542 |
+
"eval_runtime": 2.0298,
|
| 1543 |
+
"eval_samples_per_second": 123.164,
|
| 1544 |
+
"eval_steps_per_second": 3.449,
|
| 1545 |
+
"step": 96
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 7.76,
|
| 1549 |
+
"grad_norm": 4.892889022827148,
|
| 1550 |
+
"learning_rate": 9.745762711864407e-06,
|
| 1551 |
+
"loss": 0.6589,
|
| 1552 |
+
"step": 97
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 7.76,
|
| 1556 |
+
"eval_accuracy": 0.528,
|
| 1557 |
+
"eval_loss": 0.6874336004257202,
|
| 1558 |
+
"eval_runtime": 2.0274,
|
| 1559 |
+
"eval_samples_per_second": 123.309,
|
| 1560 |
+
"eval_steps_per_second": 3.453,
|
| 1561 |
+
"step": 97
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 7.84,
|
| 1565 |
+
"grad_norm": 9.976033210754395,
|
| 1566 |
+
"learning_rate": 9.322033898305085e-06,
|
| 1567 |
+
"loss": 0.7137,
|
| 1568 |
+
"step": 98
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 7.84,
|
| 1572 |
+
"eval_accuracy": 0.532,
|
| 1573 |
+
"eval_loss": 0.6868671774864197,
|
| 1574 |
+
"eval_runtime": 2.0221,
|
| 1575 |
+
"eval_samples_per_second": 123.633,
|
| 1576 |
+
"eval_steps_per_second": 3.462,
|
| 1577 |
+
"step": 98
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 7.92,
|
| 1581 |
+
"grad_norm": 3.153660297393799,
|
| 1582 |
+
"learning_rate": 8.898305084745763e-06,
|
| 1583 |
+
"loss": 0.73,
|
| 1584 |
+
"step": 99
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 7.92,
|
| 1588 |
+
"eval_accuracy": 0.536,
|
| 1589 |
+
"eval_loss": 0.686941385269165,
|
| 1590 |
+
"eval_runtime": 2.0272,
|
| 1591 |
+
"eval_samples_per_second": 123.325,
|
| 1592 |
+
"eval_steps_per_second": 3.453,
|
| 1593 |
+
"step": 99
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 8.0,
|
| 1597 |
+
"grad_norm": 6.274194240570068,
|
| 1598 |
+
"learning_rate": 8.47457627118644e-06,
|
| 1599 |
+
"loss": 0.6882,
|
| 1600 |
+
"step": 100
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 8.0,
|
| 1604 |
+
"eval_accuracy": 0.528,
|
| 1605 |
+
"eval_loss": 0.6874140501022339,
|
| 1606 |
+
"eval_runtime": 2.0308,
|
| 1607 |
+
"eval_samples_per_second": 123.102,
|
| 1608 |
+
"eval_steps_per_second": 3.447,
|
| 1609 |
+
"step": 100
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 8.08,
|
| 1613 |
+
"grad_norm": 2.984788417816162,
|
| 1614 |
+
"learning_rate": 8.050847457627118e-06,
|
| 1615 |
+
"loss": 0.6798,
|
| 1616 |
+
"step": 101
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 8.08,
|
| 1620 |
+
"eval_accuracy": 0.528,
|
| 1621 |
+
"eval_loss": 0.6867109537124634,
|
| 1622 |
+
"eval_runtime": 2.0263,
|
| 1623 |
+
"eval_samples_per_second": 123.378,
|
| 1624 |
+
"eval_steps_per_second": 3.455,
|
| 1625 |
+
"step": 101
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 8.16,
|
| 1629 |
+
"grad_norm": 3.377530813217163,
|
| 1630 |
+
"learning_rate": 7.627118644067798e-06,
|
| 1631 |
+
"loss": 0.7054,
|
| 1632 |
+
"step": 102
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 8.16,
|
| 1636 |
+
"eval_accuracy": 0.536,
|
| 1637 |
+
"eval_loss": 0.6870234608650208,
|
| 1638 |
+
"eval_runtime": 2.0274,
|
| 1639 |
+
"eval_samples_per_second": 123.309,
|
| 1640 |
+
"eval_steps_per_second": 3.453,
|
| 1641 |
+
"step": 102
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 8.24,
|
| 1645 |
+
"grad_norm": 7.250791072845459,
|
| 1646 |
+
"learning_rate": 7.203389830508475e-06,
|
| 1647 |
+
"loss": 0.6952,
|
| 1648 |
+
"step": 103
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 8.24,
|
| 1652 |
+
"eval_accuracy": 0.544,
|
| 1653 |
+
"eval_loss": 0.6866171956062317,
|
| 1654 |
+
"eval_runtime": 2.0228,
|
| 1655 |
+
"eval_samples_per_second": 123.592,
|
| 1656 |
+
"eval_steps_per_second": 3.461,
|
| 1657 |
+
"step": 103
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 8.32,
|
| 1661 |
+
"grad_norm": 5.269489765167236,
|
| 1662 |
+
"learning_rate": 6.779661016949153e-06,
|
| 1663 |
+
"loss": 0.7793,
|
| 1664 |
+
"step": 104
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 8.32,
|
| 1668 |
+
"eval_accuracy": 0.544,
|
| 1669 |
+
"eval_loss": 0.6874960660934448,
|
| 1670 |
+
"eval_runtime": 2.0212,
|
| 1671 |
+
"eval_samples_per_second": 123.691,
|
| 1672 |
+
"eval_steps_per_second": 3.463,
|
| 1673 |
+
"step": 104
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 8.4,
|
| 1677 |
+
"grad_norm": 4.358240127563477,
|
| 1678 |
+
"learning_rate": 6.3559322033898304e-06,
|
| 1679 |
+
"loss": 0.7286,
|
| 1680 |
+
"step": 105
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 8.4,
|
| 1684 |
+
"eval_accuracy": 0.536,
|
| 1685 |
+
"eval_loss": 0.6872695088386536,
|
| 1686 |
+
"eval_runtime": 2.0305,
|
| 1687 |
+
"eval_samples_per_second": 123.124,
|
| 1688 |
+
"eval_steps_per_second": 3.447,
|
| 1689 |
+
"step": 105
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 8.48,
|
| 1693 |
+
"grad_norm": 2.62113881111145,
|
| 1694 |
+
"learning_rate": 5.932203389830509e-06,
|
| 1695 |
+
"loss": 0.7209,
|
| 1696 |
+
"step": 106
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 8.48,
|
| 1700 |
+
"eval_accuracy": 0.524,
|
| 1701 |
+
"eval_loss": 0.6873710751533508,
|
| 1702 |
+
"eval_runtime": 2.0243,
|
| 1703 |
+
"eval_samples_per_second": 123.499,
|
| 1704 |
+
"eval_steps_per_second": 3.458,
|
| 1705 |
+
"step": 106
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 8.56,
|
| 1709 |
+
"grad_norm": 4.648255348205566,
|
| 1710 |
+
"learning_rate": 5.508474576271187e-06,
|
| 1711 |
+
"loss": 0.6545,
|
| 1712 |
+
"step": 107
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 8.56,
|
| 1716 |
+
"eval_accuracy": 0.532,
|
| 1717 |
+
"eval_loss": 0.687738299369812,
|
| 1718 |
+
"eval_runtime": 2.0205,
|
| 1719 |
+
"eval_samples_per_second": 123.731,
|
| 1720 |
+
"eval_steps_per_second": 3.464,
|
| 1721 |
+
"step": 107
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 8.64,
|
| 1725 |
+
"grad_norm": 2.2081334590911865,
|
| 1726 |
+
"learning_rate": 5.084745762711865e-06,
|
| 1727 |
+
"loss": 0.7435,
|
| 1728 |
+
"step": 108
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 8.64,
|
| 1732 |
+
"eval_accuracy": 0.516,
|
| 1733 |
+
"eval_loss": 0.687386691570282,
|
| 1734 |
+
"eval_runtime": 2.0291,
|
| 1735 |
+
"eval_samples_per_second": 123.207,
|
| 1736 |
+
"eval_steps_per_second": 3.45,
|
| 1737 |
+
"step": 108
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 8.72,
|
| 1741 |
+
"grad_norm": 2.0511488914489746,
|
| 1742 |
+
"learning_rate": 4.6610169491525425e-06,
|
| 1743 |
+
"loss": 0.6881,
|
| 1744 |
+
"step": 109
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 8.72,
|
| 1748 |
+
"eval_accuracy": 0.52,
|
| 1749 |
+
"eval_loss": 0.6879023313522339,
|
| 1750 |
+
"eval_runtime": 2.0181,
|
| 1751 |
+
"eval_samples_per_second": 123.877,
|
| 1752 |
+
"eval_steps_per_second": 3.469,
|
| 1753 |
+
"step": 109
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 8.8,
|
| 1757 |
+
"grad_norm": 2.262899160385132,
|
| 1758 |
+
"learning_rate": 4.23728813559322e-06,
|
| 1759 |
+
"loss": 0.7414,
|
| 1760 |
+
"step": 110
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 8.8,
|
| 1764 |
+
"eval_accuracy": 0.524,
|
| 1765 |
+
"eval_loss": 0.68798828125,
|
| 1766 |
+
"eval_runtime": 2.0297,
|
| 1767 |
+
"eval_samples_per_second": 123.17,
|
| 1768 |
+
"eval_steps_per_second": 3.449,
|
| 1769 |
+
"step": 110
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 8.88,
|
| 1773 |
+
"grad_norm": 2.8543484210968018,
|
| 1774 |
+
"learning_rate": 3.813559322033899e-06,
|
| 1775 |
+
"loss": 0.6834,
|
| 1776 |
+
"step": 111
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 8.88,
|
| 1780 |
+
"eval_accuracy": 0.524,
|
| 1781 |
+
"eval_loss": 0.6876718997955322,
|
| 1782 |
+
"eval_runtime": 2.0227,
|
| 1783 |
+
"eval_samples_per_second": 123.595,
|
| 1784 |
+
"eval_steps_per_second": 3.461,
|
| 1785 |
+
"step": 111
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 8.96,
|
| 1789 |
+
"grad_norm": 7.8969855308532715,
|
| 1790 |
+
"learning_rate": 3.3898305084745763e-06,
|
| 1791 |
+
"loss": 0.7387,
|
| 1792 |
+
"step": 112
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 8.96,
|
| 1796 |
+
"eval_accuracy": 0.524,
|
| 1797 |
+
"eval_loss": 0.6874452829360962,
|
| 1798 |
+
"eval_runtime": 2.0222,
|
| 1799 |
+
"eval_samples_per_second": 123.629,
|
| 1800 |
+
"eval_steps_per_second": 3.462,
|
| 1801 |
+
"step": 112
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 9.04,
|
| 1805 |
+
"grad_norm": 15.415665626525879,
|
| 1806 |
+
"learning_rate": 2.9661016949152545e-06,
|
| 1807 |
+
"loss": 0.6816,
|
| 1808 |
+
"step": 113
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 9.04,
|
| 1812 |
+
"eval_accuracy": 0.524,
|
| 1813 |
+
"eval_loss": 0.6880937218666077,
|
| 1814 |
+
"eval_runtime": 2.0198,
|
| 1815 |
+
"eval_samples_per_second": 123.774,
|
| 1816 |
+
"eval_steps_per_second": 3.466,
|
| 1817 |
+
"step": 113
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 9.12,
|
| 1821 |
+
"grad_norm": 2.6060779094696045,
|
| 1822 |
+
"learning_rate": 2.5423728813559323e-06,
|
| 1823 |
+
"loss": 0.6739,
|
| 1824 |
+
"step": 114
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 9.12,
|
| 1828 |
+
"eval_accuracy": 0.52,
|
| 1829 |
+
"eval_loss": 0.6881679892539978,
|
| 1830 |
+
"eval_runtime": 2.0217,
|
| 1831 |
+
"eval_samples_per_second": 123.661,
|
| 1832 |
+
"eval_steps_per_second": 3.463,
|
| 1833 |
+
"step": 114
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 9.2,
|
| 1837 |
+
"grad_norm": 3.591651201248169,
|
| 1838 |
+
"learning_rate": 2.11864406779661e-06,
|
| 1839 |
+
"loss": 0.6649,
|
| 1840 |
+
"step": 115
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 9.2,
|
| 1844 |
+
"eval_accuracy": 0.52,
|
| 1845 |
+
"eval_loss": 0.6879257559776306,
|
| 1846 |
+
"eval_runtime": 2.0224,
|
| 1847 |
+
"eval_samples_per_second": 123.614,
|
| 1848 |
+
"eval_steps_per_second": 3.461,
|
| 1849 |
+
"step": 115
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 9.28,
|
| 1853 |
+
"grad_norm": 2.9647672176361084,
|
| 1854 |
+
"learning_rate": 1.6949152542372882e-06,
|
| 1855 |
+
"loss": 0.7469,
|
| 1856 |
+
"step": 116
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 9.28,
|
| 1860 |
+
"eval_accuracy": 0.524,
|
| 1861 |
+
"eval_loss": 0.6880781054496765,
|
| 1862 |
+
"eval_runtime": 2.0268,
|
| 1863 |
+
"eval_samples_per_second": 123.347,
|
| 1864 |
+
"eval_steps_per_second": 3.454,
|
| 1865 |
+
"step": 116
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 9.36,
|
| 1869 |
+
"grad_norm": 4.3675031661987305,
|
| 1870 |
+
"learning_rate": 1.2711864406779662e-06,
|
| 1871 |
+
"loss": 0.7278,
|
| 1872 |
+
"step": 117
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 9.36,
|
| 1876 |
+
"eval_accuracy": 0.524,
|
| 1877 |
+
"eval_loss": 0.6877461075782776,
|
| 1878 |
+
"eval_runtime": 2.0288,
|
| 1879 |
+
"eval_samples_per_second": 123.227,
|
| 1880 |
+
"eval_steps_per_second": 3.45,
|
| 1881 |
+
"step": 117
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 9.44,
|
| 1885 |
+
"grad_norm": 5.043523788452148,
|
| 1886 |
+
"learning_rate": 8.474576271186441e-07,
|
| 1887 |
+
"loss": 0.6509,
|
| 1888 |
+
"step": 118
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 9.44,
|
| 1892 |
+
"eval_accuracy": 0.52,
|
| 1893 |
+
"eval_loss": 0.6879922151565552,
|
| 1894 |
+
"eval_runtime": 2.0252,
|
| 1895 |
+
"eval_samples_per_second": 123.447,
|
| 1896 |
+
"eval_steps_per_second": 3.457,
|
| 1897 |
+
"step": 118
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 9.52,
|
| 1901 |
+
"grad_norm": 5.11408805847168,
|
| 1902 |
+
"learning_rate": 4.2372881355932204e-07,
|
| 1903 |
+
"loss": 0.6899,
|
| 1904 |
+
"step": 119
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 9.52,
|
| 1908 |
+
"eval_accuracy": 0.52,
|
| 1909 |
+
"eval_loss": 0.6880234479904175,
|
| 1910 |
+
"eval_runtime": 2.0206,
|
| 1911 |
+
"eval_samples_per_second": 123.725,
|
| 1912 |
+
"eval_steps_per_second": 3.464,
|
| 1913 |
+
"step": 119
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 9.6,
|
| 1917 |
+
"grad_norm": 2.0295844078063965,
|
| 1918 |
+
"learning_rate": 0.0,
|
| 1919 |
+
"loss": 0.7045,
|
| 1920 |
+
"step": 120
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 9.6,
|
| 1924 |
+
"eval_accuracy": 0.52,
|
| 1925 |
+
"eval_loss": 0.687429666519165,
|
| 1926 |
+
"eval_runtime": 2.0271,
|
| 1927 |
+
"eval_samples_per_second": 123.33,
|
| 1928 |
+
"eval_steps_per_second": 3.453,
|
| 1929 |
+
"step": 120
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 9.6,
|
| 1933 |
+
"step": 120,
|
| 1934 |
+
"total_flos": 70235960737792.0,
|
| 1935 |
+
"train_loss": 0.7138384501139323,
|
| 1936 |
+
"train_runtime": 562.6296,
|
| 1937 |
+
"train_samples_per_second": 17.774,
|
| 1938 |
+
"train_steps_per_second": 0.213
|
| 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": 70235960737792.0,
|
| 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 sha256:1ec66e19413e3def23079012da4a882114c3a59fa0632e20dc3efa65b87f9915
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|