Task: SequenceClassification

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: RMHalak/opt-6.7b-GPTQ-4bits-128g-wikitext2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

adapter_config.json

@@ -0,0 +1,35 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "RMHalak/opt-6.7b-GPTQ-4bits-128g-wikitext2",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layer_replication": null,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "loftq_config": {},
+ "lora_alpha": 32,
+ "lora_dropout": 0.1,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": [
+ "score"
+ ],
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "q_proj",
+ "fc1",
+ "fc2",
+ "v_proj",
+ "k_proj",
+ "out_proj"
+ ],
+ "task_type": "SEQ_CLS",
+ "use_dora": false,
+ "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbec4648b083d46ba9fe6765b3a505658268e920262e4b272fceb3a9b8e86951
+size 75566824

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "</s>",
+ "unk_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+ "add_bos_token": true,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "1": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "</s>",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "</s>",
+ "errors": "replace",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "</s>",
+ "tokenizer_class": "GPT2Tokenizer",
+ "unk_token": "</s>"
+}

trainer_state-opt-gptq-QLORA-super_glue-copa-sequence_classification.json

@@ -0,0 +1,830 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 10.0,
+ "eval_steps": 1,
+ "global_step": 50,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.2,
+ "grad_norm": 23.256885528564453,
+ "learning_rate": 2.5e-05,
+ "loss": 0.9107,
+ "step": 1
+ },
+ {
+ "epoch": 0.2,
+ "eval_accuracy": 0.57,
+ "eval_loss": 0.8262696862220764,
+ "eval_runtime": 0.8414,
+ "eval_samples_per_second": 118.852,
+ "eval_steps_per_second": 3.566,
+ "step": 1
+ },
+ {
+ "epoch": 0.4,
+ "grad_norm": 23.631181716918945,
+ "learning_rate": 5e-05,
+ "loss": 0.9117,
+ "step": 2
+ },
+ {
+ "epoch": 0.4,
+ "eval_accuracy": 0.57,
+ "eval_loss": 0.8167089819908142,
+ "eval_runtime": 0.8385,
+ "eval_samples_per_second": 119.261,
+ "eval_steps_per_second": 3.578,
+ "step": 2
+ },
+ {
+ "epoch": 0.6,
+ "grad_norm": 28.508174896240234,
+ "learning_rate": 4.8958333333333335e-05,
+ "loss": 0.9991,
+ "step": 3
+ },
+ {
+ "epoch": 0.6,
+ "eval_accuracy": 0.57,
+ "eval_loss": 0.7878709435462952,
+ "eval_runtime": 0.8413,
+ "eval_samples_per_second": 118.87,
+ "eval_steps_per_second": 3.566,
+ "step": 3
+ },
+ {
+ "epoch": 0.8,
+ "grad_norm": 19.008262634277344,
+ "learning_rate": 4.791666666666667e-05,
+ "loss": 0.8288,
+ "step": 4
+ },
+ {
+ "epoch": 0.8,
+ "eval_accuracy": 0.56,
+ "eval_loss": 0.7578710913658142,
+ "eval_runtime": 0.8391,
+ "eval_samples_per_second": 119.176,
+ "eval_steps_per_second": 3.575,
+ "step": 4
+ },
+ {
+ "epoch": 1.0,
+ "grad_norm": 23.889429092407227,
+ "learning_rate": 4.6875e-05,
+ "loss": 0.8763,
+ "step": 5
+ },
+ {
+ "epoch": 1.0,
+ "eval_accuracy": 0.53,
+ "eval_loss": 0.7321679592132568,
+ "eval_runtime": 0.8386,
+ "eval_samples_per_second": 119.253,
+ "eval_steps_per_second": 3.578,
+ "step": 5
+ },
+ {
+ "epoch": 1.2,
+ "grad_norm": 9.946539878845215,
+ "learning_rate": 4.5833333333333334e-05,
+ "loss": 0.7244,
+ "step": 6
+ },
+ {
+ "epoch": 1.2,
+ "eval_accuracy": 0.55,
+ "eval_loss": 0.7117968797683716,
+ "eval_runtime": 0.8351,
+ "eval_samples_per_second": 119.747,
+ "eval_steps_per_second": 3.592,
+ "step": 6
+ },
+ {
+ "epoch": 1.4,
+ "grad_norm": 9.386951446533203,
+ "learning_rate": 4.4791666666666673e-05,
+ "loss": 0.7601,
+ "step": 7
+ },
+ {
+ "epoch": 1.4,
+ "eval_accuracy": 0.54,
+ "eval_loss": 0.6952930688858032,
+ "eval_runtime": 0.8393,
+ "eval_samples_per_second": 119.145,
+ "eval_steps_per_second": 3.574,
+ "step": 7
+ },
+ {
+ "epoch": 1.6,
+ "grad_norm": 20.157466888427734,
+ "learning_rate": 4.375e-05,
+ "loss": 0.8343,
+ "step": 8
+ },
+ {
+ "epoch": 1.6,
+ "eval_accuracy": 0.54,
+ "eval_loss": 0.6882422566413879,
+ "eval_runtime": 0.8343,
+ "eval_samples_per_second": 119.865,
+ "eval_steps_per_second": 3.596,
+ "step": 8
+ },
+ {
+ "epoch": 1.8,
+ "grad_norm": 6.170377731323242,
+ "learning_rate": 4.270833333333333e-05,
+ "loss": 0.6825,
+ "step": 9
+ },
+ {
+ "epoch": 1.8,
+ "eval_accuracy": 0.53,
+ "eval_loss": 0.6919335126876831,
+ "eval_runtime": 0.8402,
+ "eval_samples_per_second": 119.014,
+ "eval_steps_per_second": 3.57,
+ "step": 9
+ },
+ {
+ "epoch": 2.0,
+ "grad_norm": 3.945521831512451,
+ "learning_rate": 4.166666666666667e-05,
+ "loss": 0.7545,
+ "step": 10
+ },
+ {
+ "epoch": 2.0,
+ "eval_accuracy": 0.45,
+ "eval_loss": 0.6997266411781311,
+ "eval_runtime": 0.8398,
+ "eval_samples_per_second": 119.072,
+ "eval_steps_per_second": 3.572,
+ "step": 10
+ },
+ {
+ "epoch": 2.2,
+ "grad_norm": 8.659540176391602,
+ "learning_rate": 4.0625000000000005e-05,
+ "loss": 0.709,
+ "step": 11
+ },
+ {
+ "epoch": 2.2,
+ "eval_accuracy": 0.45,
+ "eval_loss": 0.7026562690734863,
+ "eval_runtime": 0.8388,
+ "eval_samples_per_second": 119.217,
+ "eval_steps_per_second": 3.577,
+ "step": 11
+ },
+ {
+ "epoch": 2.4,
+ "grad_norm": 3.4722447395324707,
+ "learning_rate": 3.958333333333333e-05,
+ "loss": 0.6914,
+ "step": 12
+ },
+ {
+ "epoch": 2.4,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.704160213470459,
+ "eval_runtime": 0.839,
+ "eval_samples_per_second": 119.192,
+ "eval_steps_per_second": 3.576,
+ "step": 12
+ },
+ {
+ "epoch": 2.6,
+ "grad_norm": 4.033767223358154,
+ "learning_rate": 3.854166666666667e-05,
+ "loss": 0.6999,
+ "step": 13
+ },
+ {
+ "epoch": 2.6,
+ "eval_accuracy": 0.48,
+ "eval_loss": 0.7015135884284973,
+ "eval_runtime": 0.8381,
+ "eval_samples_per_second": 119.324,
+ "eval_steps_per_second": 3.58,
+ "step": 13
+ },
+ {
+ "epoch": 2.8,
+ "grad_norm": 2.7851364612579346,
+ "learning_rate": 3.7500000000000003e-05,
+ "loss": 0.6829,
+ "step": 14
+ },
+ {
+ "epoch": 2.8,
+ "eval_accuracy": 0.49,
+ "eval_loss": 0.7031835913658142,
+ "eval_runtime": 0.839,
+ "eval_samples_per_second": 119.197,
+ "eval_steps_per_second": 3.576,
+ "step": 14
+ },
+ {
+ "epoch": 3.0,
+ "grad_norm": 2.5898079872131348,
+ "learning_rate": 3.6458333333333336e-05,
+ "loss": 0.6776,
+ "step": 15
+ },
+ {
+ "epoch": 3.0,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.7040430307388306,
+ "eval_runtime": 0.8373,
+ "eval_samples_per_second": 119.43,
+ "eval_steps_per_second": 3.583,
+ "step": 15
+ },
+ {
+ "epoch": 3.2,
+ "grad_norm": 7.040603160858154,
+ "learning_rate": 3.541666666666667e-05,
+ "loss": 0.7151,
+ "step": 16
+ },
+ {
+ "epoch": 3.2,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.7056737542152405,
+ "eval_runtime": 0.8384,
+ "eval_samples_per_second": 119.274,
+ "eval_steps_per_second": 3.578,
+ "step": 16
+ },
+ {
+ "epoch": 3.4,
+ "grad_norm": 6.8378705978393555,
+ "learning_rate": 3.4375e-05,
+ "loss": 0.7186,
+ "step": 17
+ },
+ {
+ "epoch": 3.4,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.7082374095916748,
+ "eval_runtime": 0.8394,
+ "eval_samples_per_second": 119.131,
+ "eval_steps_per_second": 3.574,
+ "step": 17
+ },
+ {
+ "epoch": 3.6,
+ "grad_norm": 4.7442545890808105,
+ "learning_rate": 3.3333333333333335e-05,
+ "loss": 0.7058,
+ "step": 18
+ },
+ {
+ "epoch": 3.6,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.7107178568840027,
+ "eval_runtime": 0.7888,
+ "eval_samples_per_second": 126.768,
+ "eval_steps_per_second": 3.803,
+ "step": 18
+ },
+ {
+ "epoch": 3.8,
+ "grad_norm": 5.4023237228393555,
+ "learning_rate": 3.229166666666667e-05,
+ "loss": 0.7207,
+ "step": 19
+ },
+ {
+ "epoch": 3.8,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.7103956341743469,
+ "eval_runtime": 0.8395,
+ "eval_samples_per_second": 119.117,
+ "eval_steps_per_second": 3.573,
+ "step": 19
+ },
+ {
+ "epoch": 4.0,
+ "grad_norm": 5.683109283447266,
+ "learning_rate": 3.125e-05,
+ "loss": 0.6839,
+ "step": 20
+ },
+ {
+ "epoch": 4.0,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.7080614566802979,
+ "eval_runtime": 0.8405,
+ "eval_samples_per_second": 118.971,
+ "eval_steps_per_second": 3.569,
+ "step": 20
+ },
+ {
+ "epoch": 4.2,
+ "grad_norm": 4.991653919219971,
+ "learning_rate": 3.0208333333333334e-05,
+ "loss": 0.6378,
+ "step": 21
+ },
+ {
+ "epoch": 4.2,
+ "eval_accuracy": 0.49,
+ "eval_loss": 0.7062841653823853,
+ "eval_runtime": 0.839,
+ "eval_samples_per_second": 119.188,
+ "eval_steps_per_second": 3.576,
+ "step": 21
+ },
+ {
+ "epoch": 4.4,
+ "grad_norm": 4.332605361938477,
+ "learning_rate": 2.916666666666667e-05,
+ "loss": 0.7266,
+ "step": 22
+ },
+ {
+ "epoch": 4.4,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.7057519555091858,
+ "eval_runtime": 0.8392,
+ "eval_samples_per_second": 119.161,
+ "eval_steps_per_second": 3.575,
+ "step": 22
+ },
+ {
+ "epoch": 4.6,
+ "grad_norm": 3.1174395084381104,
+ "learning_rate": 2.8125000000000003e-05,
+ "loss": 0.6729,
+ "step": 23
+ },
+ {
+ "epoch": 4.6,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.7046825885772705,
+ "eval_runtime": 0.8377,
+ "eval_samples_per_second": 119.373,
+ "eval_steps_per_second": 3.581,
+ "step": 23
+ },
+ {
+ "epoch": 4.8,
+ "grad_norm": 3.505262613296509,
+ "learning_rate": 2.7083333333333332e-05,
+ "loss": 0.7189,
+ "step": 24
+ },
+ {
+ "epoch": 4.8,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.702241063117981,
+ "eval_runtime": 0.8383,
+ "eval_samples_per_second": 119.288,
+ "eval_steps_per_second": 3.579,
+ "step": 24
+ },
+ {
+ "epoch": 5.0,
+ "grad_norm": 3.249929904937744,
+ "learning_rate": 2.604166666666667e-05,
+ "loss": 0.7092,
+ "step": 25
+ },
+ {
+ "epoch": 5.0,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.7012988328933716,
+ "eval_runtime": 0.8369,
+ "eval_samples_per_second": 119.494,
+ "eval_steps_per_second": 3.585,
+ "step": 25
+ },
+ {
+ "epoch": 5.2,
+ "grad_norm": 2.5304999351501465,
+ "learning_rate": 2.5e-05,
+ "loss": 0.7145,
+ "step": 26
+ },
+ {
+ "epoch": 5.2,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.7005956768989563,
+ "eval_runtime": 0.836,
+ "eval_samples_per_second": 119.623,
+ "eval_steps_per_second": 3.589,
+ "step": 26
+ },
+ {
+ "epoch": 5.4,
+ "grad_norm": 2.5304205417633057,
+ "learning_rate": 2.3958333333333334e-05,
+ "loss": 0.6946,
+ "step": 27
+ },
+ {
+ "epoch": 5.4,
+ "eval_accuracy": 0.48,
+ "eval_loss": 0.7012646198272705,
+ "eval_runtime": 0.8366,
+ "eval_samples_per_second": 119.526,
+ "eval_steps_per_second": 3.586,
+ "step": 27
+ },
+ {
+ "epoch": 5.6,
+ "grad_norm": 7.720176696777344,
+ "learning_rate": 2.2916666666666667e-05,
+ "loss": 0.7456,
+ "step": 28
+ },
+ {
+ "epoch": 5.6,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.7020359635353088,
+ "eval_runtime": 0.8393,
+ "eval_samples_per_second": 119.141,
+ "eval_steps_per_second": 3.574,
+ "step": 28
+ },
+ {
+ "epoch": 5.8,
+ "grad_norm": 4.178812026977539,
+ "learning_rate": 2.1875e-05,
+ "loss": 0.7231,
+ "step": 29
+ },
+ {
+ "epoch": 5.8,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.7020019292831421,
+ "eval_runtime": 0.8397,
+ "eval_samples_per_second": 119.086,
+ "eval_steps_per_second": 3.573,
+ "step": 29
+ },
+ {
+ "epoch": 6.0,
+ "grad_norm": 6.495377063751221,
+ "learning_rate": 2.0833333333333336e-05,
+ "loss": 0.6874,
+ "step": 30
+ },
+ {
+ "epoch": 6.0,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.7010400295257568,
+ "eval_runtime": 0.7916,
+ "eval_samples_per_second": 126.329,
+ "eval_steps_per_second": 3.79,
+ "step": 30
+ },
+ {
+ "epoch": 6.2,
+ "grad_norm": 1.7229987382888794,
+ "learning_rate": 1.9791666666666665e-05,
+ "loss": 0.7039,
+ "step": 31
+ },
+ {
+ "epoch": 6.2,
+ "eval_accuracy": 0.45,
+ "eval_loss": 0.7006199359893799,
+ "eval_runtime": 0.8371,
+ "eval_samples_per_second": 119.466,
+ "eval_steps_per_second": 3.584,
+ "step": 31
+ },
+ {
+ "epoch": 6.4,
+ "grad_norm": 4.806630611419678,
+ "learning_rate": 1.8750000000000002e-05,
+ "loss": 0.6858,
+ "step": 32
+ },
+ {
+ "epoch": 6.4,
+ "eval_accuracy": 0.45,
+ "eval_loss": 0.6990869045257568,
+ "eval_runtime": 0.836,
+ "eval_samples_per_second": 119.617,
+ "eval_steps_per_second": 3.589,
+ "step": 32
+ },
+ {
+ "epoch": 6.6,
+ "grad_norm": 2.4336676597595215,
+ "learning_rate": 1.7708333333333335e-05,
+ "loss": 0.6571,
+ "step": 33
+ },
+ {
+ "epoch": 6.6,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.6985548138618469,
+ "eval_runtime": 0.8383,
+ "eval_samples_per_second": 119.293,
+ "eval_steps_per_second": 3.579,
+ "step": 33
+ },
+ {
+ "epoch": 6.8,
+ "grad_norm": 2.346224784851074,
+ "learning_rate": 1.6666666666666667e-05,
+ "loss": 0.7069,
+ "step": 34
+ },
+ {
+ "epoch": 6.8,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.6970605254173279,
+ "eval_runtime": 0.8399,
+ "eval_samples_per_second": 119.069,
+ "eval_steps_per_second": 3.572,
+ "step": 34
+ },
+ {
+ "epoch": 7.0,
+ "grad_norm": 6.023119926452637,
+ "learning_rate": 1.5625e-05,
+ "loss": 0.6878,
+ "step": 35
+ },
+ {
+ "epoch": 7.0,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.6974707245826721,
+ "eval_runtime": 0.8356,
+ "eval_samples_per_second": 119.671,
+ "eval_steps_per_second": 3.59,
+ "step": 35
+ },
+ {
+ "epoch": 7.2,
+ "grad_norm": 2.5812861919403076,
+ "learning_rate": 1.4583333333333335e-05,
+ "loss": 0.7148,
+ "step": 36
+ },
+ {
+ "epoch": 7.2,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.6966310143470764,
+ "eval_runtime": 0.8396,
+ "eval_samples_per_second": 119.101,
+ "eval_steps_per_second": 3.573,
+ "step": 36
+ },
+ {
+ "epoch": 7.4,
+ "grad_norm": 6.9987263679504395,
+ "learning_rate": 1.3541666666666666e-05,
+ "loss": 0.6821,
+ "step": 37
+ },
+ {
+ "epoch": 7.4,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.6957228183746338,
+ "eval_runtime": 0.838,
+ "eval_samples_per_second": 119.326,
+ "eval_steps_per_second": 3.58,
+ "step": 37
+ },
+ {
+ "epoch": 7.6,
+ "grad_norm": 4.426673889160156,
+ "learning_rate": 1.25e-05,
+ "loss": 0.6866,
+ "step": 38
+ },
+ {
+ "epoch": 7.6,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.6958692073822021,
+ "eval_runtime": 0.8381,
+ "eval_samples_per_second": 119.321,
+ "eval_steps_per_second": 3.58,
+ "step": 38
+ },
+ {
+ "epoch": 7.8,
+ "grad_norm": 1.72467839717865,
+ "learning_rate": 1.1458333333333333e-05,
+ "loss": 0.6441,
+ "step": 39
+ },
+ {
+ "epoch": 7.8,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.6971582174301147,
+ "eval_runtime": 0.8397,
+ "eval_samples_per_second": 119.085,
+ "eval_steps_per_second": 3.573,
+ "step": 39
+ },
+ {
+ "epoch": 8.0,
+ "grad_norm": 10.352705001831055,
+ "learning_rate": 1.0416666666666668e-05,
+ "loss": 0.7264,
+ "step": 40
+ },
+ {
+ "epoch": 8.0,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.6962793469429016,
+ "eval_runtime": 0.8388,
+ "eval_samples_per_second": 119.219,
+ "eval_steps_per_second": 3.577,
+ "step": 40
+ },
+ {
+ "epoch": 8.2,
+ "grad_norm": 4.645693778991699,
+ "learning_rate": 9.375000000000001e-06,
+ "loss": 0.7164,
+ "step": 41
+ },
+ {
+ "epoch": 8.2,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.695371150970459,
+ "eval_runtime": 0.839,
+ "eval_samples_per_second": 119.183,
+ "eval_steps_per_second": 3.575,
+ "step": 41
+ },
+ {
+ "epoch": 8.4,
+ "grad_norm": 7.059908390045166,
+ "learning_rate": 8.333333333333334e-06,
+ "loss": 0.737,
+ "step": 42
+ },
+ {
+ "epoch": 8.4,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.6947849988937378,
+ "eval_runtime": 0.8369,
+ "eval_samples_per_second": 119.483,
+ "eval_steps_per_second": 3.585,
+ "step": 42
+ },
+ {
+ "epoch": 8.6,
+ "grad_norm": 1.3762595653533936,
+ "learning_rate": 7.2916666666666674e-06,
+ "loss": 0.7173,
+ "step": 43
+ },
+ {
+ "epoch": 8.6,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.6942089796066284,
+ "eval_runtime": 0.8392,
+ "eval_samples_per_second": 119.159,
+ "eval_steps_per_second": 3.575,
+ "step": 43
+ },
+ {
+ "epoch": 8.8,
+ "grad_norm": 4.145285129547119,
+ "learning_rate": 6.25e-06,
+ "loss": 0.6933,
+ "step": 44
+ },
+ {
+ "epoch": 8.8,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.6938575506210327,
+ "eval_runtime": 0.8362,
+ "eval_samples_per_second": 119.582,
+ "eval_steps_per_second": 3.587,
+ "step": 44
+ },
+ {
+ "epoch": 9.0,
+ "grad_norm": 3.7309446334838867,
+ "learning_rate": 5.208333333333334e-06,
+ "loss": 0.7204,
+ "step": 45
+ },
+ {
+ "epoch": 9.0,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.6939452886581421,
+ "eval_runtime": 0.7873,
+ "eval_samples_per_second": 127.008,
+ "eval_steps_per_second": 3.81,
+ "step": 45
+ },
+ {
+ "epoch": 9.2,
+ "grad_norm": 2.0658915042877197,
+ "learning_rate": 4.166666666666667e-06,
+ "loss": 0.707,
+ "step": 46
+ },
+ {
+ "epoch": 9.2,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.6938378810882568,
+ "eval_runtime": 0.8363,
+ "eval_samples_per_second": 119.577,
+ "eval_steps_per_second": 3.587,
+ "step": 46
+ },
+ {
+ "epoch": 9.4,
+ "grad_norm": 2.766176223754883,
+ "learning_rate": 3.125e-06,
+ "loss": 0.7343,
+ "step": 47
+ },
+ {
+ "epoch": 9.4,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.6941795945167542,
+ "eval_runtime": 0.8392,
+ "eval_samples_per_second": 119.163,
+ "eval_steps_per_second": 3.575,
+ "step": 47
+ },
+ {
+ "epoch": 9.6,
+ "grad_norm": 3.535402774810791,
+ "learning_rate": 2.0833333333333334e-06,
+ "loss": 0.7072,
+ "step": 48
+ },
+ {
+ "epoch": 9.6,
+ "eval_accuracy": 0.48,
+ "eval_loss": 0.6940819621086121,
+ "eval_runtime": 0.79,
+ "eval_samples_per_second": 126.575,
+ "eval_steps_per_second": 3.797,
+ "step": 48
+ },
+ {
+ "epoch": 9.8,
+ "grad_norm": 4.9612932205200195,
+ "learning_rate": 1.0416666666666667e-06,
+ "loss": 0.6949,
+ "step": 49
+ },
+ {
+ "epoch": 9.8,
+ "eval_accuracy": 0.47,
+ "eval_loss": 0.6937304139137268,
+ "eval_runtime": 0.8383,
+ "eval_samples_per_second": 119.288,
+ "eval_steps_per_second": 3.579,
+ "step": 49
+ },
+ {
+ "epoch": 10.0,
+ "grad_norm": 3.1242637634277344,
+ "learning_rate": 0.0,
+ "loss": 0.6862,
+ "step": 50
+ },
+ {
+ "epoch": 10.0,
+ "eval_accuracy": 0.46,
+ "eval_loss": 0.6938574910163879,
+ "eval_runtime": 0.7902,
+ "eval_samples_per_second": 126.558,
+ "eval_steps_per_second": 3.797,
+ "step": 50
+ },
+ {
+ "epoch": 10.0,
+ "step": 50,
+ "total_flos": 24115496386560.0,
+ "train_loss": 0.7265405237674714,
+ "train_runtime": 165.0104,
+ "train_samples_per_second": 24.241,
+ "train_steps_per_second": 0.303
+ }
+ ],
+ "logging_steps": 1,
+ "max_steps": 50,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 10,
+ "save_steps": 500,
+ "total_flos": 24115496386560.0,
+ "train_batch_size": 10,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ec1f19dcb6cfa57e4cf60b5de4a8cce11ac256e6b172066ab19624fee9de02
+size 5048