Task: SequenceClassification
Browse files- README.md +202 -0
- adapter_config.json +36 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
- trainer_state-llama2-bnb4-QLORA-super_glue-axg-sequence_classification.json +1470 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: RMHalak/Llama-2-7b-hf-BNB-4bits
|
| 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 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "RMHalak/Llama-2-7b-hf-BNB-4bits",
|
| 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 |
+
"o_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"gate_proj"
|
| 32 |
+
],
|
| 33 |
+
"task_type": "SEQ_CLS",
|
| 34 |
+
"use_dora": false,
|
| 35 |
+
"use_rslora": false
|
| 36 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5d19736f5c303f31f2175454ebe47c917e59610566458c144007754f1086f9a
|
| 3 |
+
size 80045992
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 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.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": "</s>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
+
"unk_token": "<unk>",
|
| 40 |
+
"use_default_system_prompt": false
|
| 41 |
+
}
|
trainer_state-llama2-bnb4-QLORA-super_glue-axg-sequence_classification.json
ADDED
|
@@ -0,0 +1,1470 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 90,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1111111111111111,
|
| 13 |
+
"grad_norm": 71.10752868652344,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 1.4086,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1111111111111111,
|
| 20 |
+
"eval_accuracy": 0.5555555555555556,
|
| 21 |
+
"eval_loss": 1.0401158332824707,
|
| 22 |
+
"eval_runtime": 1.5415,
|
| 23 |
+
"eval_samples_per_second": 46.709,
|
| 24 |
+
"eval_steps_per_second": 3.244,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.2222222222222222,
|
| 29 |
+
"grad_norm": 70.05866241455078,
|
| 30 |
+
"learning_rate": 5e-05,
|
| 31 |
+
"loss": 1.2969,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.2222222222222222,
|
| 36 |
+
"eval_accuracy": 0.4722222222222222,
|
| 37 |
+
"eval_loss": 0.957859456539154,
|
| 38 |
+
"eval_runtime": 1.6886,
|
| 39 |
+
"eval_samples_per_second": 42.639,
|
| 40 |
+
"eval_steps_per_second": 2.961,
|
| 41 |
+
"step": 2
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.3333333333333333,
|
| 45 |
+
"grad_norm": 51.52368927001953,
|
| 46 |
+
"learning_rate": 4.943181818181818e-05,
|
| 47 |
+
"loss": 1.0192,
|
| 48 |
+
"step": 3
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.3333333333333333,
|
| 52 |
+
"eval_accuracy": 0.4166666666666667,
|
| 53 |
+
"eval_loss": 1.2530348300933838,
|
| 54 |
+
"eval_runtime": 1.7908,
|
| 55 |
+
"eval_samples_per_second": 40.206,
|
| 56 |
+
"eval_steps_per_second": 2.792,
|
| 57 |
+
"step": 3
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.4444444444444444,
|
| 61 |
+
"grad_norm": 28.69840431213379,
|
| 62 |
+
"learning_rate": 4.886363636363637e-05,
|
| 63 |
+
"loss": 0.8252,
|
| 64 |
+
"step": 4
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.4444444444444444,
|
| 68 |
+
"eval_accuracy": 0.4027777777777778,
|
| 69 |
+
"eval_loss": 1.3205498456954956,
|
| 70 |
+
"eval_runtime": 1.7073,
|
| 71 |
+
"eval_samples_per_second": 42.172,
|
| 72 |
+
"eval_steps_per_second": 2.929,
|
| 73 |
+
"step": 4
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.5555555555555556,
|
| 77 |
+
"grad_norm": 26.98361587524414,
|
| 78 |
+
"learning_rate": 4.829545454545455e-05,
|
| 79 |
+
"loss": 0.8993,
|
| 80 |
+
"step": 5
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.5555555555555556,
|
| 84 |
+
"eval_accuracy": 0.4166666666666667,
|
| 85 |
+
"eval_loss": 1.1885122060775757,
|
| 86 |
+
"eval_runtime": 1.7972,
|
| 87 |
+
"eval_samples_per_second": 40.062,
|
| 88 |
+
"eval_steps_per_second": 2.782,
|
| 89 |
+
"step": 5
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.6666666666666666,
|
| 93 |
+
"grad_norm": 32.78493881225586,
|
| 94 |
+
"learning_rate": 4.772727272727273e-05,
|
| 95 |
+
"loss": 0.8969,
|
| 96 |
+
"step": 6
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.6666666666666666,
|
| 100 |
+
"eval_accuracy": 0.4722222222222222,
|
| 101 |
+
"eval_loss": 1.0518155097961426,
|
| 102 |
+
"eval_runtime": 1.7895,
|
| 103 |
+
"eval_samples_per_second": 40.235,
|
| 104 |
+
"eval_steps_per_second": 2.794,
|
| 105 |
+
"step": 6
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.7777777777777778,
|
| 109 |
+
"grad_norm": 35.246402740478516,
|
| 110 |
+
"learning_rate": 4.715909090909091e-05,
|
| 111 |
+
"loss": 0.7789,
|
| 112 |
+
"step": 7
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.7777777777777778,
|
| 116 |
+
"eval_accuracy": 0.4027777777777778,
|
| 117 |
+
"eval_loss": 0.95684814453125,
|
| 118 |
+
"eval_runtime": 1.782,
|
| 119 |
+
"eval_samples_per_second": 40.405,
|
| 120 |
+
"eval_steps_per_second": 2.806,
|
| 121 |
+
"step": 7
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8888888888888888,
|
| 125 |
+
"grad_norm": 10.608202934265137,
|
| 126 |
+
"learning_rate": 4.659090909090909e-05,
|
| 127 |
+
"loss": 0.8172,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8888888888888888,
|
| 132 |
+
"eval_accuracy": 0.4722222222222222,
|
| 133 |
+
"eval_loss": 0.9124009609222412,
|
| 134 |
+
"eval_runtime": 1.7,
|
| 135 |
+
"eval_samples_per_second": 42.354,
|
| 136 |
+
"eval_steps_per_second": 2.941,
|
| 137 |
+
"step": 8
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.0,
|
| 141 |
+
"grad_norm": 20.640520095825195,
|
| 142 |
+
"learning_rate": 4.602272727272727e-05,
|
| 143 |
+
"loss": 0.9466,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.0,
|
| 148 |
+
"eval_accuracy": 0.4722222222222222,
|
| 149 |
+
"eval_loss": 0.8895958662033081,
|
| 150 |
+
"eval_runtime": 1.6914,
|
| 151 |
+
"eval_samples_per_second": 42.569,
|
| 152 |
+
"eval_steps_per_second": 2.956,
|
| 153 |
+
"step": 9
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.1111111111111112,
|
| 157 |
+
"grad_norm": 16.80632972717285,
|
| 158 |
+
"learning_rate": 4.545454545454546e-05,
|
| 159 |
+
"loss": 0.7398,
|
| 160 |
+
"step": 10
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.1111111111111112,
|
| 164 |
+
"eval_accuracy": 0.4722222222222222,
|
| 165 |
+
"eval_loss": 0.8696831464767456,
|
| 166 |
+
"eval_runtime": 1.7281,
|
| 167 |
+
"eval_samples_per_second": 41.664,
|
| 168 |
+
"eval_steps_per_second": 2.893,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.2222222222222223,
|
| 173 |
+
"grad_norm": 33.25798797607422,
|
| 174 |
+
"learning_rate": 4.488636363636364e-05,
|
| 175 |
+
"loss": 0.8393,
|
| 176 |
+
"step": 11
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.2222222222222223,
|
| 180 |
+
"eval_accuracy": 0.4722222222222222,
|
| 181 |
+
"eval_loss": 0.8458387851715088,
|
| 182 |
+
"eval_runtime": 1.6403,
|
| 183 |
+
"eval_samples_per_second": 43.894,
|
| 184 |
+
"eval_steps_per_second": 3.048,
|
| 185 |
+
"step": 11
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.3333333333333333,
|
| 189 |
+
"grad_norm": 18.833730697631836,
|
| 190 |
+
"learning_rate": 4.431818181818182e-05,
|
| 191 |
+
"loss": 0.627,
|
| 192 |
+
"step": 12
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.3333333333333333,
|
| 196 |
+
"eval_accuracy": 0.4305555555555556,
|
| 197 |
+
"eval_loss": 0.8363681435585022,
|
| 198 |
+
"eval_runtime": 1.7646,
|
| 199 |
+
"eval_samples_per_second": 40.803,
|
| 200 |
+
"eval_steps_per_second": 2.834,
|
| 201 |
+
"step": 12
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.4444444444444444,
|
| 205 |
+
"grad_norm": 11.44498062133789,
|
| 206 |
+
"learning_rate": 4.375e-05,
|
| 207 |
+
"loss": 0.5691,
|
| 208 |
+
"step": 13
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.4444444444444444,
|
| 212 |
+
"eval_accuracy": 0.4166666666666667,
|
| 213 |
+
"eval_loss": 0.8569539189338684,
|
| 214 |
+
"eval_runtime": 1.6972,
|
| 215 |
+
"eval_samples_per_second": 42.423,
|
| 216 |
+
"eval_steps_per_second": 2.946,
|
| 217 |
+
"step": 13
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.5555555555555556,
|
| 221 |
+
"grad_norm": 6.994156360626221,
|
| 222 |
+
"learning_rate": 4.318181818181819e-05,
|
| 223 |
+
"loss": 0.6796,
|
| 224 |
+
"step": 14
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.5555555555555556,
|
| 228 |
+
"eval_accuracy": 0.4444444444444444,
|
| 229 |
+
"eval_loss": 0.9024861454963684,
|
| 230 |
+
"eval_runtime": 1.6366,
|
| 231 |
+
"eval_samples_per_second": 43.995,
|
| 232 |
+
"eval_steps_per_second": 3.055,
|
| 233 |
+
"step": 14
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.6666666666666665,
|
| 237 |
+
"grad_norm": 23.839618682861328,
|
| 238 |
+
"learning_rate": 4.261363636363637e-05,
|
| 239 |
+
"loss": 0.6225,
|
| 240 |
+
"step": 15
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.6666666666666665,
|
| 244 |
+
"eval_accuracy": 0.4722222222222222,
|
| 245 |
+
"eval_loss": 0.9257575273513794,
|
| 246 |
+
"eval_runtime": 1.6451,
|
| 247 |
+
"eval_samples_per_second": 43.767,
|
| 248 |
+
"eval_steps_per_second": 3.039,
|
| 249 |
+
"step": 15
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.7777777777777777,
|
| 253 |
+
"grad_norm": 23.61461639404297,
|
| 254 |
+
"learning_rate": 4.204545454545455e-05,
|
| 255 |
+
"loss": 0.6299,
|
| 256 |
+
"step": 16
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.7777777777777777,
|
| 260 |
+
"eval_accuracy": 0.4583333333333333,
|
| 261 |
+
"eval_loss": 0.9147135615348816,
|
| 262 |
+
"eval_runtime": 1.7411,
|
| 263 |
+
"eval_samples_per_second": 41.353,
|
| 264 |
+
"eval_steps_per_second": 2.872,
|
| 265 |
+
"step": 16
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.8888888888888888,
|
| 269 |
+
"grad_norm": 15.60508918762207,
|
| 270 |
+
"learning_rate": 4.1477272727272734e-05,
|
| 271 |
+
"loss": 0.5009,
|
| 272 |
+
"step": 17
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.8888888888888888,
|
| 276 |
+
"eval_accuracy": 0.4583333333333333,
|
| 277 |
+
"eval_loss": 0.8712971806526184,
|
| 278 |
+
"eval_runtime": 1.688,
|
| 279 |
+
"eval_samples_per_second": 42.653,
|
| 280 |
+
"eval_steps_per_second": 2.962,
|
| 281 |
+
"step": 17
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.0,
|
| 285 |
+
"grad_norm": 14.364876747131348,
|
| 286 |
+
"learning_rate": 4.0909090909090915e-05,
|
| 287 |
+
"loss": 0.4875,
|
| 288 |
+
"step": 18
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.0,
|
| 292 |
+
"eval_accuracy": 0.4305555555555556,
|
| 293 |
+
"eval_loss": 0.8122490644454956,
|
| 294 |
+
"eval_runtime": 1.6995,
|
| 295 |
+
"eval_samples_per_second": 42.366,
|
| 296 |
+
"eval_steps_per_second": 2.942,
|
| 297 |
+
"step": 18
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.111111111111111,
|
| 301 |
+
"grad_norm": 9.64327621459961,
|
| 302 |
+
"learning_rate": 4.034090909090909e-05,
|
| 303 |
+
"loss": 0.4547,
|
| 304 |
+
"step": 19
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.111111111111111,
|
| 308 |
+
"eval_accuracy": 0.4444444444444444,
|
| 309 |
+
"eval_loss": 0.7631157636642456,
|
| 310 |
+
"eval_runtime": 1.7098,
|
| 311 |
+
"eval_samples_per_second": 42.11,
|
| 312 |
+
"eval_steps_per_second": 2.924,
|
| 313 |
+
"step": 19
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.2222222222222223,
|
| 317 |
+
"grad_norm": 8.928176879882812,
|
| 318 |
+
"learning_rate": 3.9772727272727275e-05,
|
| 319 |
+
"loss": 0.3933,
|
| 320 |
+
"step": 20
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.2222222222222223,
|
| 324 |
+
"eval_accuracy": 0.5138888888888888,
|
| 325 |
+
"eval_loss": 0.7445746660232544,
|
| 326 |
+
"eval_runtime": 1.7154,
|
| 327 |
+
"eval_samples_per_second": 41.973,
|
| 328 |
+
"eval_steps_per_second": 2.915,
|
| 329 |
+
"step": 20
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.3333333333333335,
|
| 333 |
+
"grad_norm": 12.450410842895508,
|
| 334 |
+
"learning_rate": 3.9204545454545456e-05,
|
| 335 |
+
"loss": 0.3994,
|
| 336 |
+
"step": 21
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.3333333333333335,
|
| 340 |
+
"eval_accuracy": 0.5416666666666666,
|
| 341 |
+
"eval_loss": 0.7361382246017456,
|
| 342 |
+
"eval_runtime": 1.6893,
|
| 343 |
+
"eval_samples_per_second": 42.621,
|
| 344 |
+
"eval_steps_per_second": 2.96,
|
| 345 |
+
"step": 21
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.4444444444444446,
|
| 349 |
+
"grad_norm": 9.766682624816895,
|
| 350 |
+
"learning_rate": 3.8636363636363636e-05,
|
| 351 |
+
"loss": 0.4413,
|
| 352 |
+
"step": 22
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.4444444444444446,
|
| 356 |
+
"eval_accuracy": 0.5972222222222222,
|
| 357 |
+
"eval_loss": 0.7318115234375,
|
| 358 |
+
"eval_runtime": 1.6931,
|
| 359 |
+
"eval_samples_per_second": 42.526,
|
| 360 |
+
"eval_steps_per_second": 2.953,
|
| 361 |
+
"step": 22
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.5555555555555554,
|
| 365 |
+
"grad_norm": 9.650227546691895,
|
| 366 |
+
"learning_rate": 3.8068181818181816e-05,
|
| 367 |
+
"loss": 0.4032,
|
| 368 |
+
"step": 23
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.5555555555555554,
|
| 372 |
+
"eval_accuracy": 0.5972222222222222,
|
| 373 |
+
"eval_loss": 0.7219780683517456,
|
| 374 |
+
"eval_runtime": 1.6928,
|
| 375 |
+
"eval_samples_per_second": 42.532,
|
| 376 |
+
"eval_steps_per_second": 2.954,
|
| 377 |
+
"step": 23
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.6666666666666665,
|
| 381 |
+
"grad_norm": 8.477367401123047,
|
| 382 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 383 |
+
"loss": 0.4308,
|
| 384 |
+
"step": 24
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.6666666666666665,
|
| 388 |
+
"eval_accuracy": 0.6527777777777778,
|
| 389 |
+
"eval_loss": 0.7055935263633728,
|
| 390 |
+
"eval_runtime": 1.7353,
|
| 391 |
+
"eval_samples_per_second": 41.492,
|
| 392 |
+
"eval_steps_per_second": 2.881,
|
| 393 |
+
"step": 24
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.7777777777777777,
|
| 397 |
+
"grad_norm": 8.381991386413574,
|
| 398 |
+
"learning_rate": 3.6931818181818184e-05,
|
| 399 |
+
"loss": 0.3827,
|
| 400 |
+
"step": 25
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.7777777777777777,
|
| 404 |
+
"eval_accuracy": 0.6666666666666666,
|
| 405 |
+
"eval_loss": 0.6947495937347412,
|
| 406 |
+
"eval_runtime": 1.69,
|
| 407 |
+
"eval_samples_per_second": 42.604,
|
| 408 |
+
"eval_steps_per_second": 2.959,
|
| 409 |
+
"step": 25
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.888888888888889,
|
| 413 |
+
"grad_norm": 18.475757598876953,
|
| 414 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 415 |
+
"loss": 0.3719,
|
| 416 |
+
"step": 26
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.888888888888889,
|
| 420 |
+
"eval_accuracy": 0.6388888888888888,
|
| 421 |
+
"eval_loss": 0.695068359375,
|
| 422 |
+
"eval_runtime": 1.7654,
|
| 423 |
+
"eval_samples_per_second": 40.785,
|
| 424 |
+
"eval_steps_per_second": 2.832,
|
| 425 |
+
"step": 26
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.0,
|
| 429 |
+
"grad_norm": 4.149219036102295,
|
| 430 |
+
"learning_rate": 3.579545454545455e-05,
|
| 431 |
+
"loss": 0.2756,
|
| 432 |
+
"step": 27
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.0,
|
| 436 |
+
"eval_accuracy": 0.625,
|
| 437 |
+
"eval_loss": 0.7118733525276184,
|
| 438 |
+
"eval_runtime": 1.7076,
|
| 439 |
+
"eval_samples_per_second": 42.165,
|
| 440 |
+
"eval_steps_per_second": 2.928,
|
| 441 |
+
"step": 27
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.111111111111111,
|
| 445 |
+
"grad_norm": 6.201833248138428,
|
| 446 |
+
"learning_rate": 3.522727272727273e-05,
|
| 447 |
+
"loss": 0.3048,
|
| 448 |
+
"step": 28
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 3.111111111111111,
|
| 452 |
+
"eval_accuracy": 0.6388888888888888,
|
| 453 |
+
"eval_loss": 0.7207743525505066,
|
| 454 |
+
"eval_runtime": 1.6906,
|
| 455 |
+
"eval_samples_per_second": 42.59,
|
| 456 |
+
"eval_steps_per_second": 2.958,
|
| 457 |
+
"step": 28
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 3.2222222222222223,
|
| 461 |
+
"grad_norm": 10.069761276245117,
|
| 462 |
+
"learning_rate": 3.465909090909091e-05,
|
| 463 |
+
"loss": 0.2833,
|
| 464 |
+
"step": 29
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.2222222222222223,
|
| 468 |
+
"eval_accuracy": 0.6111111111111112,
|
| 469 |
+
"eval_loss": 0.758392333984375,
|
| 470 |
+
"eval_runtime": 1.689,
|
| 471 |
+
"eval_samples_per_second": 42.629,
|
| 472 |
+
"eval_steps_per_second": 2.96,
|
| 473 |
+
"step": 29
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.3333333333333335,
|
| 477 |
+
"grad_norm": 14.6091947555542,
|
| 478 |
+
"learning_rate": 3.409090909090909e-05,
|
| 479 |
+
"loss": 0.2192,
|
| 480 |
+
"step": 30
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 3.3333333333333335,
|
| 484 |
+
"eval_accuracy": 0.625,
|
| 485 |
+
"eval_loss": 0.7625613808631897,
|
| 486 |
+
"eval_runtime": 1.6873,
|
| 487 |
+
"eval_samples_per_second": 42.671,
|
| 488 |
+
"eval_steps_per_second": 2.963,
|
| 489 |
+
"step": 30
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.4444444444444446,
|
| 493 |
+
"grad_norm": 12.838824272155762,
|
| 494 |
+
"learning_rate": 3.352272727272727e-05,
|
| 495 |
+
"loss": 0.159,
|
| 496 |
+
"step": 31
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 3.4444444444444446,
|
| 500 |
+
"eval_accuracy": 0.6666666666666666,
|
| 501 |
+
"eval_loss": 0.7382490634918213,
|
| 502 |
+
"eval_runtime": 1.689,
|
| 503 |
+
"eval_samples_per_second": 42.629,
|
| 504 |
+
"eval_steps_per_second": 2.96,
|
| 505 |
+
"step": 31
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 3.5555555555555554,
|
| 509 |
+
"grad_norm": 5.576656341552734,
|
| 510 |
+
"learning_rate": 3.295454545454545e-05,
|
| 511 |
+
"loss": 0.1545,
|
| 512 |
+
"step": 32
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.5555555555555554,
|
| 516 |
+
"eval_accuracy": 0.6805555555555556,
|
| 517 |
+
"eval_loss": 0.7160136103630066,
|
| 518 |
+
"eval_runtime": 1.688,
|
| 519 |
+
"eval_samples_per_second": 42.655,
|
| 520 |
+
"eval_steps_per_second": 2.962,
|
| 521 |
+
"step": 32
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 3.6666666666666665,
|
| 525 |
+
"grad_norm": 3.911334753036499,
|
| 526 |
+
"learning_rate": 3.238636363636364e-05,
|
| 527 |
+
"loss": 0.2048,
|
| 528 |
+
"step": 33
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 3.6666666666666665,
|
| 532 |
+
"eval_accuracy": 0.6944444444444444,
|
| 533 |
+
"eval_loss": 0.7091013789176941,
|
| 534 |
+
"eval_runtime": 1.6904,
|
| 535 |
+
"eval_samples_per_second": 42.594,
|
| 536 |
+
"eval_steps_per_second": 2.958,
|
| 537 |
+
"step": 33
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 3.7777777777777777,
|
| 541 |
+
"grad_norm": 4.566244125366211,
|
| 542 |
+
"learning_rate": 3.181818181818182e-05,
|
| 543 |
+
"loss": 0.1285,
|
| 544 |
+
"step": 34
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 3.7777777777777777,
|
| 548 |
+
"eval_accuracy": 0.7361111111111112,
|
| 549 |
+
"eval_loss": 0.7089945673942566,
|
| 550 |
+
"eval_runtime": 1.6878,
|
| 551 |
+
"eval_samples_per_second": 42.659,
|
| 552 |
+
"eval_steps_per_second": 2.962,
|
| 553 |
+
"step": 34
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.888888888888889,
|
| 557 |
+
"grad_norm": 4.949621677398682,
|
| 558 |
+
"learning_rate": 3.125e-05,
|
| 559 |
+
"loss": 0.0972,
|
| 560 |
+
"step": 35
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.888888888888889,
|
| 564 |
+
"eval_accuracy": 0.7361111111111112,
|
| 565 |
+
"eval_loss": 0.7177971601486206,
|
| 566 |
+
"eval_runtime": 1.7101,
|
| 567 |
+
"eval_samples_per_second": 42.104,
|
| 568 |
+
"eval_steps_per_second": 2.924,
|
| 569 |
+
"step": 35
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 4.0,
|
| 573 |
+
"grad_norm": 5.815789699554443,
|
| 574 |
+
"learning_rate": 3.068181818181818e-05,
|
| 575 |
+
"loss": 0.1396,
|
| 576 |
+
"step": 36
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 4.0,
|
| 580 |
+
"eval_accuracy": 0.7361111111111112,
|
| 581 |
+
"eval_loss": 0.7336485385894775,
|
| 582 |
+
"eval_runtime": 1.704,
|
| 583 |
+
"eval_samples_per_second": 42.252,
|
| 584 |
+
"eval_steps_per_second": 2.934,
|
| 585 |
+
"step": 36
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 4.111111111111111,
|
| 589 |
+
"grad_norm": 5.0971174240112305,
|
| 590 |
+
"learning_rate": 3.0113636363636365e-05,
|
| 591 |
+
"loss": 0.1058,
|
| 592 |
+
"step": 37
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 4.111111111111111,
|
| 596 |
+
"eval_accuracy": 0.6944444444444444,
|
| 597 |
+
"eval_loss": 0.7677508592605591,
|
| 598 |
+
"eval_runtime": 1.6634,
|
| 599 |
+
"eval_samples_per_second": 43.285,
|
| 600 |
+
"eval_steps_per_second": 3.006,
|
| 601 |
+
"step": 37
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 4.222222222222222,
|
| 605 |
+
"grad_norm": 3.026982545852661,
|
| 606 |
+
"learning_rate": 2.954545454545455e-05,
|
| 607 |
+
"loss": 0.1036,
|
| 608 |
+
"step": 38
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 4.222222222222222,
|
| 612 |
+
"eval_accuracy": 0.6666666666666666,
|
| 613 |
+
"eval_loss": 0.81514573097229,
|
| 614 |
+
"eval_runtime": 1.7527,
|
| 615 |
+
"eval_samples_per_second": 41.08,
|
| 616 |
+
"eval_steps_per_second": 2.853,
|
| 617 |
+
"step": 38
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 4.333333333333333,
|
| 621 |
+
"grad_norm": 3.815314531326294,
|
| 622 |
+
"learning_rate": 2.8977272727272732e-05,
|
| 623 |
+
"loss": 0.0651,
|
| 624 |
+
"step": 39
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 4.333333333333333,
|
| 628 |
+
"eval_accuracy": 0.6944444444444444,
|
| 629 |
+
"eval_loss": 0.8406186699867249,
|
| 630 |
+
"eval_runtime": 1.7692,
|
| 631 |
+
"eval_samples_per_second": 40.696,
|
| 632 |
+
"eval_steps_per_second": 2.826,
|
| 633 |
+
"step": 39
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 4.444444444444445,
|
| 637 |
+
"grad_norm": 2.897125244140625,
|
| 638 |
+
"learning_rate": 2.8409090909090912e-05,
|
| 639 |
+
"loss": 0.0643,
|
| 640 |
+
"step": 40
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 4.444444444444445,
|
| 644 |
+
"eval_accuracy": 0.6944444444444444,
|
| 645 |
+
"eval_loss": 0.8639495372772217,
|
| 646 |
+
"eval_runtime": 1.7505,
|
| 647 |
+
"eval_samples_per_second": 41.132,
|
| 648 |
+
"eval_steps_per_second": 2.856,
|
| 649 |
+
"step": 40
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 4.555555555555555,
|
| 653 |
+
"grad_norm": 8.826624870300293,
|
| 654 |
+
"learning_rate": 2.784090909090909e-05,
|
| 655 |
+
"loss": 0.0708,
|
| 656 |
+
"step": 41
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 4.555555555555555,
|
| 660 |
+
"eval_accuracy": 0.7083333333333334,
|
| 661 |
+
"eval_loss": 0.8449772000312805,
|
| 662 |
+
"eval_runtime": 1.7389,
|
| 663 |
+
"eval_samples_per_second": 41.404,
|
| 664 |
+
"eval_steps_per_second": 2.875,
|
| 665 |
+
"step": 41
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 4.666666666666667,
|
| 669 |
+
"grad_norm": 4.310912132263184,
|
| 670 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 671 |
+
"loss": 0.0571,
|
| 672 |
+
"step": 42
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 4.666666666666667,
|
| 676 |
+
"eval_accuracy": 0.7222222222222222,
|
| 677 |
+
"eval_loss": 0.8496870398521423,
|
| 678 |
+
"eval_runtime": 1.6953,
|
| 679 |
+
"eval_samples_per_second": 42.471,
|
| 680 |
+
"eval_steps_per_second": 2.949,
|
| 681 |
+
"step": 42
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 4.777777777777778,
|
| 685 |
+
"grad_norm": 0.9157137870788574,
|
| 686 |
+
"learning_rate": 2.6704545454545453e-05,
|
| 687 |
+
"loss": 0.0101,
|
| 688 |
+
"step": 43
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 4.777777777777778,
|
| 692 |
+
"eval_accuracy": 0.75,
|
| 693 |
+
"eval_loss": 0.8314664363861084,
|
| 694 |
+
"eval_runtime": 1.696,
|
| 695 |
+
"eval_samples_per_second": 42.452,
|
| 696 |
+
"eval_steps_per_second": 2.948,
|
| 697 |
+
"step": 43
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 4.888888888888889,
|
| 701 |
+
"grad_norm": 4.54341983795166,
|
| 702 |
+
"learning_rate": 2.6136363636363637e-05,
|
| 703 |
+
"loss": 0.0345,
|
| 704 |
+
"step": 44
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.888888888888889,
|
| 708 |
+
"eval_accuracy": 0.75,
|
| 709 |
+
"eval_loss": 0.8536232709884644,
|
| 710 |
+
"eval_runtime": 1.7637,
|
| 711 |
+
"eval_samples_per_second": 40.822,
|
| 712 |
+
"eval_steps_per_second": 2.835,
|
| 713 |
+
"step": 44
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 5.0,
|
| 717 |
+
"grad_norm": 2.6652591228485107,
|
| 718 |
+
"learning_rate": 2.5568181818181817e-05,
|
| 719 |
+
"loss": 0.0194,
|
| 720 |
+
"step": 45
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 5.0,
|
| 724 |
+
"eval_accuracy": 0.75,
|
| 725 |
+
"eval_loss": 0.8400527834892273,
|
| 726 |
+
"eval_runtime": 1.7745,
|
| 727 |
+
"eval_samples_per_second": 40.575,
|
| 728 |
+
"eval_steps_per_second": 2.818,
|
| 729 |
+
"step": 45
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 5.111111111111111,
|
| 733 |
+
"grad_norm": 0.518764078617096,
|
| 734 |
+
"learning_rate": 2.5e-05,
|
| 735 |
+
"loss": 0.005,
|
| 736 |
+
"step": 46
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 5.111111111111111,
|
| 740 |
+
"eval_accuracy": 0.75,
|
| 741 |
+
"eval_loss": 0.8562726378440857,
|
| 742 |
+
"eval_runtime": 1.7488,
|
| 743 |
+
"eval_samples_per_second": 41.171,
|
| 744 |
+
"eval_steps_per_second": 2.859,
|
| 745 |
+
"step": 46
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 5.222222222222222,
|
| 749 |
+
"grad_norm": 0.5080448389053345,
|
| 750 |
+
"learning_rate": 2.4431818181818185e-05,
|
| 751 |
+
"loss": 0.0092,
|
| 752 |
+
"step": 47
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 5.222222222222222,
|
| 756 |
+
"eval_accuracy": 0.75,
|
| 757 |
+
"eval_loss": 0.8858435153961182,
|
| 758 |
+
"eval_runtime": 1.7362,
|
| 759 |
+
"eval_samples_per_second": 41.469,
|
| 760 |
+
"eval_steps_per_second": 2.88,
|
| 761 |
+
"step": 47
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 5.333333333333333,
|
| 765 |
+
"grad_norm": 1.4881385564804077,
|
| 766 |
+
"learning_rate": 2.3863636363636365e-05,
|
| 767 |
+
"loss": 0.0117,
|
| 768 |
+
"step": 48
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 5.333333333333333,
|
| 772 |
+
"eval_accuracy": 0.7638888888888888,
|
| 773 |
+
"eval_loss": 0.9373347163200378,
|
| 774 |
+
"eval_runtime": 1.7561,
|
| 775 |
+
"eval_samples_per_second": 40.999,
|
| 776 |
+
"eval_steps_per_second": 2.847,
|
| 777 |
+
"step": 48
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 5.444444444444445,
|
| 781 |
+
"grad_norm": 0.4491148293018341,
|
| 782 |
+
"learning_rate": 2.3295454545454546e-05,
|
| 783 |
+
"loss": 0.006,
|
| 784 |
+
"step": 49
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 5.444444444444445,
|
| 788 |
+
"eval_accuracy": 0.7638888888888888,
|
| 789 |
+
"eval_loss": 0.9894835352897644,
|
| 790 |
+
"eval_runtime": 1.7035,
|
| 791 |
+
"eval_samples_per_second": 42.267,
|
| 792 |
+
"eval_steps_per_second": 2.935,
|
| 793 |
+
"step": 49
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 5.555555555555555,
|
| 797 |
+
"grad_norm": 0.5586861371994019,
|
| 798 |
+
"learning_rate": 2.272727272727273e-05,
|
| 799 |
+
"loss": 0.0063,
|
| 800 |
+
"step": 50
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 5.555555555555555,
|
| 804 |
+
"eval_accuracy": 0.7777777777777778,
|
| 805 |
+
"eval_loss": 1.0309796333312988,
|
| 806 |
+
"eval_runtime": 1.7142,
|
| 807 |
+
"eval_samples_per_second": 42.001,
|
| 808 |
+
"eval_steps_per_second": 2.917,
|
| 809 |
+
"step": 50
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 5.666666666666667,
|
| 813 |
+
"grad_norm": 1.2758698463439941,
|
| 814 |
+
"learning_rate": 2.215909090909091e-05,
|
| 815 |
+
"loss": 0.0057,
|
| 816 |
+
"step": 51
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 5.666666666666667,
|
| 820 |
+
"eval_accuracy": 0.7777777777777778,
|
| 821 |
+
"eval_loss": 1.0968831777572632,
|
| 822 |
+
"eval_runtime": 1.6931,
|
| 823 |
+
"eval_samples_per_second": 42.526,
|
| 824 |
+
"eval_steps_per_second": 2.953,
|
| 825 |
+
"step": 51
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 5.777777777777778,
|
| 829 |
+
"grad_norm": 0.4022962152957916,
|
| 830 |
+
"learning_rate": 2.1590909090909093e-05,
|
| 831 |
+
"loss": 0.0024,
|
| 832 |
+
"step": 52
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 5.777777777777778,
|
| 836 |
+
"eval_accuracy": 0.7777777777777778,
|
| 837 |
+
"eval_loss": 1.1657804250717163,
|
| 838 |
+
"eval_runtime": 1.7525,
|
| 839 |
+
"eval_samples_per_second": 41.083,
|
| 840 |
+
"eval_steps_per_second": 2.853,
|
| 841 |
+
"step": 52
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 5.888888888888889,
|
| 845 |
+
"grad_norm": 8.325399398803711,
|
| 846 |
+
"learning_rate": 2.1022727272727274e-05,
|
| 847 |
+
"loss": 0.0283,
|
| 848 |
+
"step": 53
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 5.888888888888889,
|
| 852 |
+
"eval_accuracy": 0.7777777777777778,
|
| 853 |
+
"eval_loss": 1.1517949104309082,
|
| 854 |
+
"eval_runtime": 1.7207,
|
| 855 |
+
"eval_samples_per_second": 41.843,
|
| 856 |
+
"eval_steps_per_second": 2.906,
|
| 857 |
+
"step": 53
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 6.0,
|
| 861 |
+
"grad_norm": 0.6889083981513977,
|
| 862 |
+
"learning_rate": 2.0454545454545457e-05,
|
| 863 |
+
"loss": 0.0031,
|
| 864 |
+
"step": 54
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 6.0,
|
| 868 |
+
"eval_accuracy": 0.7777777777777778,
|
| 869 |
+
"eval_loss": 1.131449580192566,
|
| 870 |
+
"eval_runtime": 1.7267,
|
| 871 |
+
"eval_samples_per_second": 41.698,
|
| 872 |
+
"eval_steps_per_second": 2.896,
|
| 873 |
+
"step": 54
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 6.111111111111111,
|
| 877 |
+
"grad_norm": 0.12238375097513199,
|
| 878 |
+
"learning_rate": 1.9886363636363638e-05,
|
| 879 |
+
"loss": 0.0006,
|
| 880 |
+
"step": 55
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 6.111111111111111,
|
| 884 |
+
"eval_accuracy": 0.8055555555555556,
|
| 885 |
+
"eval_loss": 1.120394229888916,
|
| 886 |
+
"eval_runtime": 1.7518,
|
| 887 |
+
"eval_samples_per_second": 41.1,
|
| 888 |
+
"eval_steps_per_second": 2.854,
|
| 889 |
+
"step": 55
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 6.222222222222222,
|
| 893 |
+
"grad_norm": 0.04647090286016464,
|
| 894 |
+
"learning_rate": 1.9318181818181818e-05,
|
| 895 |
+
"loss": 0.0004,
|
| 896 |
+
"step": 56
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 6.222222222222222,
|
| 900 |
+
"eval_accuracy": 0.8333333333333334,
|
| 901 |
+
"eval_loss": 1.1473143100738525,
|
| 902 |
+
"eval_runtime": 1.6957,
|
| 903 |
+
"eval_samples_per_second": 42.461,
|
| 904 |
+
"eval_steps_per_second": 2.949,
|
| 905 |
+
"step": 56
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 6.333333333333333,
|
| 909 |
+
"grad_norm": 0.07002800703048706,
|
| 910 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 911 |
+
"loss": 0.0004,
|
| 912 |
+
"step": 57
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 6.333333333333333,
|
| 916 |
+
"eval_accuracy": 0.8333333333333334,
|
| 917 |
+
"eval_loss": 1.1827261447906494,
|
| 918 |
+
"eval_runtime": 1.6914,
|
| 919 |
+
"eval_samples_per_second": 42.567,
|
| 920 |
+
"eval_steps_per_second": 2.956,
|
| 921 |
+
"step": 57
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 6.444444444444445,
|
| 925 |
+
"grad_norm": 0.057534411549568176,
|
| 926 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 927 |
+
"loss": 0.0002,
|
| 928 |
+
"step": 58
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 6.444444444444445,
|
| 932 |
+
"eval_accuracy": 0.8333333333333334,
|
| 933 |
+
"eval_loss": 1.224190592765808,
|
| 934 |
+
"eval_runtime": 1.6907,
|
| 935 |
+
"eval_samples_per_second": 42.587,
|
| 936 |
+
"eval_steps_per_second": 2.957,
|
| 937 |
+
"step": 58
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 6.555555555555555,
|
| 941 |
+
"grad_norm": 0.1322898268699646,
|
| 942 |
+
"learning_rate": 1.7613636363636366e-05,
|
| 943 |
+
"loss": 0.0006,
|
| 944 |
+
"step": 59
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 6.555555555555555,
|
| 948 |
+
"eval_accuracy": 0.8333333333333334,
|
| 949 |
+
"eval_loss": 1.2592931985855103,
|
| 950 |
+
"eval_runtime": 1.6878,
|
| 951 |
+
"eval_samples_per_second": 42.659,
|
| 952 |
+
"eval_steps_per_second": 2.962,
|
| 953 |
+
"step": 59
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 6.666666666666667,
|
| 957 |
+
"grad_norm": 0.014222492463886738,
|
| 958 |
+
"learning_rate": 1.7045454545454546e-05,
|
| 959 |
+
"loss": 0.0001,
|
| 960 |
+
"step": 60
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 6.666666666666667,
|
| 964 |
+
"eval_accuracy": 0.8333333333333334,
|
| 965 |
+
"eval_loss": 1.281473159790039,
|
| 966 |
+
"eval_runtime": 1.6928,
|
| 967 |
+
"eval_samples_per_second": 42.532,
|
| 968 |
+
"eval_steps_per_second": 2.954,
|
| 969 |
+
"step": 60
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 6.777777777777778,
|
| 973 |
+
"grad_norm": 3.633732795715332,
|
| 974 |
+
"learning_rate": 1.6477272727272726e-05,
|
| 975 |
+
"loss": 0.0144,
|
| 976 |
+
"step": 61
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 6.777777777777778,
|
| 980 |
+
"eval_accuracy": 0.8333333333333334,
|
| 981 |
+
"eval_loss": 1.2948687076568604,
|
| 982 |
+
"eval_runtime": 1.6886,
|
| 983 |
+
"eval_samples_per_second": 42.64,
|
| 984 |
+
"eval_steps_per_second": 2.961,
|
| 985 |
+
"step": 61
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 6.888888888888889,
|
| 989 |
+
"grad_norm": 0.6753994226455688,
|
| 990 |
+
"learning_rate": 1.590909090909091e-05,
|
| 991 |
+
"loss": 0.0021,
|
| 992 |
+
"step": 62
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 6.888888888888889,
|
| 996 |
+
"eval_accuracy": 0.8333333333333334,
|
| 997 |
+
"eval_loss": 1.303892731666565,
|
| 998 |
+
"eval_runtime": 1.691,
|
| 999 |
+
"eval_samples_per_second": 42.579,
|
| 1000 |
+
"eval_steps_per_second": 2.957,
|
| 1001 |
+
"step": 62
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 7.0,
|
| 1005 |
+
"grad_norm": 0.047468412667512894,
|
| 1006 |
+
"learning_rate": 1.534090909090909e-05,
|
| 1007 |
+
"loss": 0.0002,
|
| 1008 |
+
"step": 63
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 7.0,
|
| 1012 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1013 |
+
"eval_loss": 1.3037166595458984,
|
| 1014 |
+
"eval_runtime": 1.6895,
|
| 1015 |
+
"eval_samples_per_second": 42.615,
|
| 1016 |
+
"eval_steps_per_second": 2.959,
|
| 1017 |
+
"step": 63
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 7.111111111111111,
|
| 1021 |
+
"grad_norm": 0.04554079473018646,
|
| 1022 |
+
"learning_rate": 1.4772727272727274e-05,
|
| 1023 |
+
"loss": 0.0001,
|
| 1024 |
+
"step": 64
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 7.111111111111111,
|
| 1028 |
+
"eval_accuracy": 0.8194444444444444,
|
| 1029 |
+
"eval_loss": 1.3078640699386597,
|
| 1030 |
+
"eval_runtime": 1.6898,
|
| 1031 |
+
"eval_samples_per_second": 42.608,
|
| 1032 |
+
"eval_steps_per_second": 2.959,
|
| 1033 |
+
"step": 64
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 7.222222222222222,
|
| 1037 |
+
"grad_norm": 0.010344511829316616,
|
| 1038 |
+
"learning_rate": 1.4204545454545456e-05,
|
| 1039 |
+
"loss": 0.0001,
|
| 1040 |
+
"step": 65
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 7.222222222222222,
|
| 1044 |
+
"eval_accuracy": 0.8055555555555556,
|
| 1045 |
+
"eval_loss": 1.3234918117523193,
|
| 1046 |
+
"eval_runtime": 1.6967,
|
| 1047 |
+
"eval_samples_per_second": 42.434,
|
| 1048 |
+
"eval_steps_per_second": 2.947,
|
| 1049 |
+
"step": 65
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 7.333333333333333,
|
| 1053 |
+
"grad_norm": 0.006933713797479868,
|
| 1054 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 1055 |
+
"loss": 0.0001,
|
| 1056 |
+
"step": 66
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 7.333333333333333,
|
| 1060 |
+
"eval_accuracy": 0.8055555555555556,
|
| 1061 |
+
"eval_loss": 1.3226008415222168,
|
| 1062 |
+
"eval_runtime": 1.6947,
|
| 1063 |
+
"eval_samples_per_second": 42.485,
|
| 1064 |
+
"eval_steps_per_second": 2.95,
|
| 1065 |
+
"step": 66
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 7.444444444444445,
|
| 1069 |
+
"grad_norm": 0.004614418838173151,
|
| 1070 |
+
"learning_rate": 1.3068181818181819e-05,
|
| 1071 |
+
"loss": 0.0,
|
| 1072 |
+
"step": 67
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 7.444444444444445,
|
| 1076 |
+
"eval_accuracy": 0.8055555555555556,
|
| 1077 |
+
"eval_loss": 1.3420900106430054,
|
| 1078 |
+
"eval_runtime": 1.6925,
|
| 1079 |
+
"eval_samples_per_second": 42.54,
|
| 1080 |
+
"eval_steps_per_second": 2.954,
|
| 1081 |
+
"step": 67
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 7.555555555555555,
|
| 1085 |
+
"grad_norm": 0.011573988012969494,
|
| 1086 |
+
"learning_rate": 1.25e-05,
|
| 1087 |
+
"loss": 0.0001,
|
| 1088 |
+
"step": 68
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 7.555555555555555,
|
| 1092 |
+
"eval_accuracy": 0.8055555555555556,
|
| 1093 |
+
"eval_loss": 1.3453483581542969,
|
| 1094 |
+
"eval_runtime": 1.6925,
|
| 1095 |
+
"eval_samples_per_second": 42.539,
|
| 1096 |
+
"eval_steps_per_second": 2.954,
|
| 1097 |
+
"step": 68
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 7.666666666666667,
|
| 1101 |
+
"grad_norm": 0.05624835565686226,
|
| 1102 |
+
"learning_rate": 1.1931818181818183e-05,
|
| 1103 |
+
"loss": 0.0002,
|
| 1104 |
+
"step": 69
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 7.666666666666667,
|
| 1108 |
+
"eval_accuracy": 0.8055555555555556,
|
| 1109 |
+
"eval_loss": 1.3481894731521606,
|
| 1110 |
+
"eval_runtime": 1.6884,
|
| 1111 |
+
"eval_samples_per_second": 42.643,
|
| 1112 |
+
"eval_steps_per_second": 2.961,
|
| 1113 |
+
"step": 69
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 7.777777777777778,
|
| 1117 |
+
"grad_norm": 0.026880212128162384,
|
| 1118 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 1119 |
+
"loss": 0.0001,
|
| 1120 |
+
"step": 70
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 7.777777777777778,
|
| 1124 |
+
"eval_accuracy": 0.7916666666666666,
|
| 1125 |
+
"eval_loss": 1.3691877126693726,
|
| 1126 |
+
"eval_runtime": 1.689,
|
| 1127 |
+
"eval_samples_per_second": 42.628,
|
| 1128 |
+
"eval_steps_per_second": 2.96,
|
| 1129 |
+
"step": 70
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 7.888888888888889,
|
| 1133 |
+
"grad_norm": 0.014328360557556152,
|
| 1134 |
+
"learning_rate": 1.0795454545454547e-05,
|
| 1135 |
+
"loss": 0.0001,
|
| 1136 |
+
"step": 71
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 7.888888888888889,
|
| 1140 |
+
"eval_accuracy": 0.7916666666666666,
|
| 1141 |
+
"eval_loss": 1.3764379024505615,
|
| 1142 |
+
"eval_runtime": 1.692,
|
| 1143 |
+
"eval_samples_per_second": 42.552,
|
| 1144 |
+
"eval_steps_per_second": 2.955,
|
| 1145 |
+
"step": 71
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 8.0,
|
| 1149 |
+
"grad_norm": 0.004069478716701269,
|
| 1150 |
+
"learning_rate": 1.0227272727272729e-05,
|
| 1151 |
+
"loss": 0.0,
|
| 1152 |
+
"step": 72
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 8.0,
|
| 1156 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1157 |
+
"eval_loss": 1.3799124956130981,
|
| 1158 |
+
"eval_runtime": 1.6421,
|
| 1159 |
+
"eval_samples_per_second": 43.845,
|
| 1160 |
+
"eval_steps_per_second": 3.045,
|
| 1161 |
+
"step": 72
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 8.11111111111111,
|
| 1165 |
+
"grad_norm": 0.029666263610124588,
|
| 1166 |
+
"learning_rate": 9.659090909090909e-06,
|
| 1167 |
+
"loss": 0.0001,
|
| 1168 |
+
"step": 73
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 8.11111111111111,
|
| 1172 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1173 |
+
"eval_loss": 1.3902004957199097,
|
| 1174 |
+
"eval_runtime": 1.6942,
|
| 1175 |
+
"eval_samples_per_second": 42.498,
|
| 1176 |
+
"eval_steps_per_second": 2.951,
|
| 1177 |
+
"step": 73
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 8.222222222222221,
|
| 1181 |
+
"grad_norm": 0.005981099791824818,
|
| 1182 |
+
"learning_rate": 9.090909090909091e-06,
|
| 1183 |
+
"loss": 0.0,
|
| 1184 |
+
"step": 74
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 8.222222222222221,
|
| 1188 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1189 |
+
"eval_loss": 1.3968830108642578,
|
| 1190 |
+
"eval_runtime": 1.6929,
|
| 1191 |
+
"eval_samples_per_second": 42.531,
|
| 1192 |
+
"eval_steps_per_second": 2.954,
|
| 1193 |
+
"step": 74
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 8.333333333333334,
|
| 1197 |
+
"grad_norm": 0.008150852285325527,
|
| 1198 |
+
"learning_rate": 8.522727272727273e-06,
|
| 1199 |
+
"loss": 0.0001,
|
| 1200 |
+
"step": 75
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 8.333333333333334,
|
| 1204 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1205 |
+
"eval_loss": 1.4002034664154053,
|
| 1206 |
+
"eval_runtime": 1.692,
|
| 1207 |
+
"eval_samples_per_second": 42.554,
|
| 1208 |
+
"eval_steps_per_second": 2.955,
|
| 1209 |
+
"step": 75
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 8.444444444444445,
|
| 1213 |
+
"grad_norm": 0.10769578814506531,
|
| 1214 |
+
"learning_rate": 7.954545454545455e-06,
|
| 1215 |
+
"loss": 0.0004,
|
| 1216 |
+
"step": 76
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 8.444444444444445,
|
| 1220 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1221 |
+
"eval_loss": 1.4117597341537476,
|
| 1222 |
+
"eval_runtime": 1.6904,
|
| 1223 |
+
"eval_samples_per_second": 42.595,
|
| 1224 |
+
"eval_steps_per_second": 2.958,
|
| 1225 |
+
"step": 76
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 8.555555555555555,
|
| 1229 |
+
"grad_norm": 0.026451965793967247,
|
| 1230 |
+
"learning_rate": 7.386363636363637e-06,
|
| 1231 |
+
"loss": 0.0001,
|
| 1232 |
+
"step": 77
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 8.555555555555555,
|
| 1236 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1237 |
+
"eval_loss": 1.4056729078292847,
|
| 1238 |
+
"eval_runtime": 1.6873,
|
| 1239 |
+
"eval_samples_per_second": 42.672,
|
| 1240 |
+
"eval_steps_per_second": 2.963,
|
| 1241 |
+
"step": 77
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 8.666666666666666,
|
| 1245 |
+
"grad_norm": 0.07714568078517914,
|
| 1246 |
+
"learning_rate": 6.818181818181818e-06,
|
| 1247 |
+
"loss": 0.0003,
|
| 1248 |
+
"step": 78
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 8.666666666666666,
|
| 1252 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1253 |
+
"eval_loss": 1.4086921215057373,
|
| 1254 |
+
"eval_runtime": 1.6884,
|
| 1255 |
+
"eval_samples_per_second": 42.643,
|
| 1256 |
+
"eval_steps_per_second": 2.961,
|
| 1257 |
+
"step": 78
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 8.777777777777779,
|
| 1261 |
+
"grad_norm": 0.03726133331656456,
|
| 1262 |
+
"learning_rate": 6.25e-06,
|
| 1263 |
+
"loss": 0.0001,
|
| 1264 |
+
"step": 79
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 8.777777777777779,
|
| 1268 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1269 |
+
"eval_loss": 1.4101053476333618,
|
| 1270 |
+
"eval_runtime": 1.6929,
|
| 1271 |
+
"eval_samples_per_second": 42.53,
|
| 1272 |
+
"eval_steps_per_second": 2.954,
|
| 1273 |
+
"step": 79
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 8.88888888888889,
|
| 1277 |
+
"grad_norm": 0.01760346069931984,
|
| 1278 |
+
"learning_rate": 5.681818181818182e-06,
|
| 1279 |
+
"loss": 0.0001,
|
| 1280 |
+
"step": 80
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 8.88888888888889,
|
| 1284 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1285 |
+
"eval_loss": 1.4063137769699097,
|
| 1286 |
+
"eval_runtime": 1.6938,
|
| 1287 |
+
"eval_samples_per_second": 42.508,
|
| 1288 |
+
"eval_steps_per_second": 2.952,
|
| 1289 |
+
"step": 80
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 9.0,
|
| 1293 |
+
"grad_norm": 0.05216860771179199,
|
| 1294 |
+
"learning_rate": 5.113636363636364e-06,
|
| 1295 |
+
"loss": 0.0003,
|
| 1296 |
+
"step": 81
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 9.0,
|
| 1300 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1301 |
+
"eval_loss": 1.4048177003860474,
|
| 1302 |
+
"eval_runtime": 1.6922,
|
| 1303 |
+
"eval_samples_per_second": 42.549,
|
| 1304 |
+
"eval_steps_per_second": 2.955,
|
| 1305 |
+
"step": 81
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 9.11111111111111,
|
| 1309 |
+
"grad_norm": 0.019384268671274185,
|
| 1310 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 1311 |
+
"loss": 0.0001,
|
| 1312 |
+
"step": 82
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 9.11111111111111,
|
| 1316 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1317 |
+
"eval_loss": 1.4030442237854004,
|
| 1318 |
+
"eval_runtime": 1.6903,
|
| 1319 |
+
"eval_samples_per_second": 42.595,
|
| 1320 |
+
"eval_steps_per_second": 2.958,
|
| 1321 |
+
"step": 82
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 9.222222222222221,
|
| 1325 |
+
"grad_norm": 0.04530010744929314,
|
| 1326 |
+
"learning_rate": 3.9772727272727275e-06,
|
| 1327 |
+
"loss": 0.0002,
|
| 1328 |
+
"step": 83
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 9.222222222222221,
|
| 1332 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1333 |
+
"eval_loss": 1.406543254852295,
|
| 1334 |
+
"eval_runtime": 1.6884,
|
| 1335 |
+
"eval_samples_per_second": 42.643,
|
| 1336 |
+
"eval_steps_per_second": 2.961,
|
| 1337 |
+
"step": 83
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 9.333333333333334,
|
| 1341 |
+
"grad_norm": 0.006314022000879049,
|
| 1342 |
+
"learning_rate": 3.409090909090909e-06,
|
| 1343 |
+
"loss": 0.0,
|
| 1344 |
+
"step": 84
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 9.333333333333334,
|
| 1348 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1349 |
+
"eval_loss": 1.4123640060424805,
|
| 1350 |
+
"eval_runtime": 1.6879,
|
| 1351 |
+
"eval_samples_per_second": 42.656,
|
| 1352 |
+
"eval_steps_per_second": 2.962,
|
| 1353 |
+
"step": 84
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 9.444444444444445,
|
| 1357 |
+
"grad_norm": 0.010984798893332481,
|
| 1358 |
+
"learning_rate": 2.840909090909091e-06,
|
| 1359 |
+
"loss": 0.0001,
|
| 1360 |
+
"step": 85
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 9.444444444444445,
|
| 1364 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1365 |
+
"eval_loss": 1.4055116176605225,
|
| 1366 |
+
"eval_runtime": 1.6923,
|
| 1367 |
+
"eval_samples_per_second": 42.547,
|
| 1368 |
+
"eval_steps_per_second": 2.955,
|
| 1369 |
+
"step": 85
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 9.555555555555555,
|
| 1373 |
+
"grad_norm": 0.04161923751235008,
|
| 1374 |
+
"learning_rate": 2.2727272727272728e-06,
|
| 1375 |
+
"loss": 0.0002,
|
| 1376 |
+
"step": 86
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 9.555555555555555,
|
| 1380 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1381 |
+
"eval_loss": 1.4036388397216797,
|
| 1382 |
+
"eval_runtime": 1.6941,
|
| 1383 |
+
"eval_samples_per_second": 42.5,
|
| 1384 |
+
"eval_steps_per_second": 2.951,
|
| 1385 |
+
"step": 86
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 9.666666666666666,
|
| 1389 |
+
"grad_norm": 0.02397008240222931,
|
| 1390 |
+
"learning_rate": 1.7045454545454546e-06,
|
| 1391 |
+
"loss": 0.0001,
|
| 1392 |
+
"step": 87
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 9.666666666666666,
|
| 1396 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1397 |
+
"eval_loss": 1.4052443504333496,
|
| 1398 |
+
"eval_runtime": 1.6935,
|
| 1399 |
+
"eval_samples_per_second": 42.517,
|
| 1400 |
+
"eval_steps_per_second": 2.953,
|
| 1401 |
+
"step": 87
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 9.777777777777779,
|
| 1405 |
+
"grad_norm": 0.020388655364513397,
|
| 1406 |
+
"learning_rate": 1.1363636363636364e-06,
|
| 1407 |
+
"loss": 0.0001,
|
| 1408 |
+
"step": 88
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 9.777777777777779,
|
| 1412 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1413 |
+
"eval_loss": 1.403831958770752,
|
| 1414 |
+
"eval_runtime": 1.693,
|
| 1415 |
+
"eval_samples_per_second": 42.529,
|
| 1416 |
+
"eval_steps_per_second": 2.953,
|
| 1417 |
+
"step": 88
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 9.88888888888889,
|
| 1421 |
+
"grad_norm": 0.03793564811348915,
|
| 1422 |
+
"learning_rate": 5.681818181818182e-07,
|
| 1423 |
+
"loss": 0.0002,
|
| 1424 |
+
"step": 89
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 9.88888888888889,
|
| 1428 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1429 |
+
"eval_loss": 1.4065537452697754,
|
| 1430 |
+
"eval_runtime": 1.6926,
|
| 1431 |
+
"eval_samples_per_second": 42.537,
|
| 1432 |
+
"eval_steps_per_second": 2.954,
|
| 1433 |
+
"step": 89
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 10.0,
|
| 1437 |
+
"grad_norm": 0.003561729798093438,
|
| 1438 |
+
"learning_rate": 0.0,
|
| 1439 |
+
"loss": 0.0,
|
| 1440 |
+
"step": 90
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 10.0,
|
| 1444 |
+
"eval_accuracy": 0.7777777777777778,
|
| 1445 |
+
"eval_loss": 1.4016788005828857,
|
| 1446 |
+
"eval_runtime": 1.693,
|
| 1447 |
+
"eval_samples_per_second": 42.528,
|
| 1448 |
+
"eval_steps_per_second": 2.953,
|
| 1449 |
+
"step": 90
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 10.0,
|
| 1453 |
+
"step": 90,
|
| 1454 |
+
"total_flos": 5016736558481408.0,
|
| 1455 |
+
"train_loss": 0.22732360793484582,
|
| 1456 |
+
"train_runtime": 316.2669,
|
| 1457 |
+
"train_samples_per_second": 8.98,
|
| 1458 |
+
"train_steps_per_second": 0.285
|
| 1459 |
+
}
|
| 1460 |
+
],
|
| 1461 |
+
"logging_steps": 1,
|
| 1462 |
+
"max_steps": 90,
|
| 1463 |
+
"num_input_tokens_seen": 0,
|
| 1464 |
+
"num_train_epochs": 10,
|
| 1465 |
+
"save_steps": 500,
|
| 1466 |
+
"total_flos": 5016736558481408.0,
|
| 1467 |
+
"train_batch_size": 4,
|
| 1468 |
+
"trial_name": null,
|
| 1469 |
+
"trial_params": null
|
| 1470 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54b2fdfc105e4076be4895c4b6354f4d528ec75ef56f5d8e1a28f69d19666043
|
| 3 |
+
size 5048
|