Training in progress, epoch 1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3d7c22b9afccc03e7eb9460080a3cae91db773767d1e71ca3f32c5378666e0
+oid sha256:725e3e8cda639a0d4f705d4fcc32c0a98e093c67a232387442e912197aa10834
 size 2372416

run-0/checkpoint-13/README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: google-bert/bert-base-uncased
+base_model: bert-base-uncased
 ---
 
 # Model Card for Model ID

run-0/checkpoint-13/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google-bert/bert-base-uncased",
+  "base_model_name_or_path": "bert-base-uncased",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -11,12 +11,12 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

run-0/checkpoint-13/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a6263233df2137711d45dcc809552258696413797bd53bd89868551875e1ff
-size 602816
+oid sha256:4299b1c2a222b655dc3c2c05796afb86f100d43c4523a5bd0bf0ccf7a2c9e5c7
+size 2372416

run-0/checkpoint-13/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88bf059a998df62f65a4d5e3544d934847cd6db524fda196192b603cc72c25c
-size 660858
+oid sha256:9decf441c751ba560d645c9dccb2cfd476e2698d8f0b35e6f48f669e9dffb5f6
+size 1251642

run-0/checkpoint-13/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2e81846170be0b1c13b8f803a80c6a61fa72027ed3f746470e521b5420ab98
+oid sha256:d38ede53d33f59610c7c0d6744c450c0bfed05d88c83c5303daaa1e32512e949
 size 14244

run-0/checkpoint-13/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37fd155a26e6858f88a6bc6a9115a9120b1df4e01bf5b48242cb2cae403a5ed4
+oid sha256:23b4ca290a9d390c8f6763a939d5869c7aa95c43442a39f80f01e2172afc374c
 size 1064

run-0/checkpoint-13/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5125224685440384,
+  "best_metric": 0.5775862068965517,
   "best_model_checkpoint": "bert-finetuned-spam/run-0/checkpoint-13",
   "epoch": 0.9811320754716981,
   "eval_steps": 500,
@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 0.9811320754716981,
-      "eval_accuracy": 0.5125224685440384,
-      "eval_loss": 0.6872516870498657,
-      "eval_runtime": 102.1088,
-      "eval_samples_per_second": 163.453,
-      "eval_steps_per_second": 20.439,
+      "eval_accuracy": 0.5775862068965517,
+      "eval_loss": 0.6792163848876953,
+      "eval_runtime": 20.3957,
+      "eval_samples_per_second": 51.187,
+      "eval_steps_per_second": 1.618,
       "step": 13
     }
   ],
   "logging_steps": 500,
-  "max_steps": 39,
+  "max_steps": 13,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.491420045821173e-06,
-    "num_train_epochs": 3,
+    "learning_rate": 6.432402847051035e-05,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 64,
-    "seed": 30
+    "seed": 34
   }
 }

run-0/checkpoint-13/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d93d60a9a1529339de39d9f9f994ca3ad953970cb4cb9d367d4c93b2235dbcd
+oid sha256:fa84561d988a5a950451ae9b0bac4547bd7cb07e1811e48298c1b69c48164a56
 size 4984

run-1/checkpoint-104/README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: google-bert/bert-base-uncased
+base_model: bert-base-uncased
 ---
 
 # Model Card for Model ID

run-1/checkpoint-104/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google-bert/bert-base-uncased",
+  "base_model_name_or_path": "bert-base-uncased",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -11,12 +11,12 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

run-1/checkpoint-104/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13da6c856b0bdf72ce9d6f45754de36d1756efaa5a04fe3674bb3ee69fe99bed
-size 602816
+oid sha256:c5e67f011769bccf8fbfe5ff4a3e8b3ed46974895e2664661206009039349103
+size 2372416

run-1/checkpoint-104/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eba02c6d135d90281bb12ca8293a5cb737627f85d0cced3b67d5f39d914d5ad
-size 660858
+oid sha256:5ff7136e4240c6ff9b4bf0f76c2cbc0eda49459ab81173d0e6207555da79118b
+size 1251642

run-1/checkpoint-104/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57ff959c71e3584c3b52315fa688015a6f198fbe19ea52fae976cab8fd47c30
+oid sha256:bb469aba7ce04aec96c43a317fbd7e4ebaacde06783df3921ea19c0af6d920cc
 size 14244

run-1/checkpoint-104/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b5407c8f8724e7e43e6bdd3a21b50f604d14419bcd949985ff13641023fdcb
+oid sha256:fd97622fd52a33609f7b058ef87bad5c4a65e629b6f43832c1c2d3e7b051ca7c
 size 1064

run-1/checkpoint-104/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.47399640503295387,
-  "best_model_checkpoint": "bert-finetuned-spam/run-1/checkpoint-52",
-  "epoch": 1.9904306220095693,
+  "best_metric": 0.4885057471264368,
+  "best_model_checkpoint": "bert-finetuned-spam/run-1/checkpoint-104",
+  "epoch": 0.9952153110047847,
   "eval_steps": 500,
   "global_step": 104,
   "is_hyper_param_search": true,
@@ -10,35 +10,26 @@
   "log_history": [
     {
       "epoch": 0.9952153110047847,
-      "eval_accuracy": 0.47399640503295387,
-      "eval_loss": NaN,
-      "eval_runtime": 103.4506,
-      "eval_samples_per_second": 161.333,
-      "eval_steps_per_second": 20.174,
-      "step": 52
-    },
-    {
-      "epoch": 1.9904306220095693,
-      "eval_accuracy": 0.47399640503295387,
-      "eval_loss": NaN,
-      "eval_runtime": 103.5051,
-      "eval_samples_per_second": 161.248,
-      "eval_steps_per_second": 20.163,
+      "eval_accuracy": 0.4885057471264368,
+      "eval_loss": 0.6971799731254578,
+      "eval_runtime": 20.2395,
+      "eval_samples_per_second": 51.582,
+      "eval_steps_per_second": 1.63,
       "step": 104
     }
   ],
   "logging_steps": 500,
-  "max_steps": 104,
+  "max_steps": 208,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 16,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 8.46705518946506e-06,
+    "learning_rate": 1.0294379557649764e-06,
     "num_train_epochs": 2,
-    "per_device_train_batch_size": 16,
-    "seed": 18
+    "per_device_train_batch_size": 8,
+    "seed": 39
   }
 }

run-1/checkpoint-104/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf464b011df5047c12e9ab0c7aa3f647e1fe2c89e6a4237f784c1600fad61a68
+oid sha256:3aa09b21119024cccc386165022e2ff4819a3a190a502f385dee6c2c3a6e3966
 size 4984

run-1/checkpoint-208/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: bert-base-uncased
+---
+
+# 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

run-1/checkpoint-208/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bert-base-uncased",
+  "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": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value",
+    "query"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

run-1/checkpoint-208/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3621e6019e73eedc9ed0831328d41ed88e4eeffe2289378c69374eaf4909aebb
+size 2372416

run-1/checkpoint-208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a085c21a0ece2ab8d72b7e39ce3bf385f58f51e9cd944c8f898ec2ec6fc1628
+size 1251642

run-1/checkpoint-208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e641c1b2feb84b6347efbc01214adada85ff1da1bc1164d84dfc8315b6b3060
+size 14244

run-1/checkpoint-208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c59cfc3ec3bddd1071d2fd29535121ac050e97e059528fc2abc4cfc3aa71ba3
+size 1064

run-1/checkpoint-208/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-208/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-208/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.5009578544061303,
+  "best_model_checkpoint": "bert-finetuned-spam/run-1/checkpoint-208",
+  "epoch": 1.9904306220095693,
+  "eval_steps": 500,
+  "global_step": 208,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9952153110047847,
+      "eval_accuracy": 0.4885057471264368,
+      "eval_loss": 0.6971799731254578,
+      "eval_runtime": 20.2395,
+      "eval_samples_per_second": 51.582,
+      "eval_steps_per_second": 1.63,
+      "step": 104
+    },
+    {
+      "epoch": 1.9904306220095693,
+      "eval_accuracy": 0.5009578544061303,
+      "eval_loss": 0.6964148879051208,
+      "eval_runtime": 20.2954,
+      "eval_samples_per_second": 51.44,
+      "eval_steps_per_second": 1.626,
+      "step": 208
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0294379557649764e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 39
+  }
+}

run-1/checkpoint-208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa09b21119024cccc386165022e2ff4819a3a190a502f385dee6c2c3a6e3966
+size 4984

run-2/checkpoint-13/README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: google-bert/bert-base-uncased
+base_model: bert-base-uncased
 ---
 
 # Model Card for Model ID

run-2/checkpoint-13/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google-bert/bert-base-uncased",
+  "base_model_name_or_path": "bert-base-uncased",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -11,12 +11,12 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

run-2/checkpoint-13/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b02a26c169abe9195a045dbb5b39971f0ca58337fd1af2f4d24e7df23aaaed2
-size 602816
+oid sha256:1da2935bc931a3435f713e01db818603a58e0f3579ff3f6a098dab4d8f8accb9
+size 2372416

run-2/checkpoint-13/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e44f08c6b7787a9ba53e16e121cb0a4618ce7e6d2150462be39347a42b03714
-size 660858
+oid sha256:0c15b8a92746f64670ba869fca776ec0a3c3ab59dd503ce8e99c24ea6e36a38f
+size 1251642

run-2/checkpoint-13/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c8e370aedd8b7561d4535523eb1c15f5524dbc2eb4a38b760f6145f3338ef3
+oid sha256:67e11968e806a7a000fa93c4037a7671c7e925037c8a582ffbe5bba544c0859d
 size 14308

run-2/checkpoint-13/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e4463ad3755b2dfc3443944a58a8b1f07c164dc2aa42cf1e9838fbf114f2fc1
+oid sha256:01110c5a18e0f34fa429a404a88535e918e9095764ceb01044d6d53c39ced63b
 size 1064

run-2/checkpoint-13/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.47399640503295387,
+  "best_metric": 0.5201149425287356,
   "best_model_checkpoint": "bert-finetuned-spam/run-2/checkpoint-13",
   "epoch": 0.9811320754716981,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 0.9811320754716981,
-      "eval_accuracy": 0.47399640503295387,
-      "eval_loss": 0.8083081841468811,
-      "eval_runtime": 103.651,
-      "eval_samples_per_second": 161.021,
-      "eval_steps_per_second": 20.135,
+      "eval_accuracy": 0.5201149425287356,
+      "eval_loss": 0.7263713479042053,
+      "eval_runtime": 20.2886,
+      "eval_samples_per_second": 51.457,
+      "eval_steps_per_second": 1.627,
       "step": 13
     }
   ],
@@ -27,9 +27,9 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.616634659922366e-06,
+    "learning_rate": 3.1436979979087796e-05,
     "num_train_epochs": 3,
     "per_device_train_batch_size": 64,
-    "seed": 8
+    "seed": 32
   }
 }

run-2/checkpoint-13/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4836333ade6016bf5baac215292836f3a17a1c875576861472678ef49fe0a85d
+oid sha256:de4e41e121af7a82574e2467a1ce497f08ca103ccd86549bda68b0f3024fe148
 size 4984

run-2/checkpoint-26/README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: google-bert/bert-base-uncased
+base_model: bert-base-uncased
 ---
 
 # Model Card for Model ID

run-2/checkpoint-26/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google-bert/bert-base-uncased",
+  "base_model_name_or_path": "bert-base-uncased",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -11,12 +11,12 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

run-2/checkpoint-26/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6d7951e1462d3ee067cb9c7c6137b4e55701161156795d679398c2072ed2cc
-size 602816
+oid sha256:d1a23203eb40b70fb77d7503a05bc7fa998f71e0ff59c5f910b09edb8163feb3
+size 2372416

run-2/checkpoint-26/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd2c7431081bc195ea8b3a47184e8d2f1ec411e9c30e185207a8243660bf019
-size 660858
+oid sha256:ac5eeea7e38b5cad22e0844ee77a5b2cd28530ee21083d9fa700bd675d2fe911
+size 1251642

run-2/checkpoint-26/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb90549b4b49fc41fbb950e3432a901d282862781129366441e88a7a3409183
+oid sha256:3ad339b79f0981aad0a4d83283fb386e740d68c8df504f88c644cdc2e492d1f1
 size 14308

run-2/checkpoint-26/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed58e4b7d9f64317f6a0c0404fcfd79f2584e8eba5ed2e4ea4318b3613111e85
+oid sha256:6e4c404220a13c60dd4c1e014a4e2962e1a3f91e01e65e091e3e53a1548a776d
 size 1064

run-2/checkpoint-26/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.47399640503295387,
+  "best_metric": 0.5201149425287356,
   "best_model_checkpoint": "bert-finetuned-spam/run-2/checkpoint-13",
   "epoch": 1.9622641509433962,
   "eval_steps": 500,
@@ -10,20 +10,20 @@
   "log_history": [
     {
       "epoch": 0.9811320754716981,
-      "eval_accuracy": 0.47399640503295387,
-      "eval_loss": 0.8083081841468811,
-      "eval_runtime": 103.651,
-      "eval_samples_per_second": 161.021,
-      "eval_steps_per_second": 20.135,
+      "eval_accuracy": 0.5201149425287356,
+      "eval_loss": 0.7263713479042053,
+      "eval_runtime": 20.2886,
+      "eval_samples_per_second": 51.457,
+      "eval_steps_per_second": 1.627,
       "step": 13
     },
     {
       "epoch": 1.9622641509433962,
-      "eval_accuracy": 0.47399640503295387,
-      "eval_loss": 0.8073155283927917,
-      "eval_runtime": 102.4849,
-      "eval_samples_per_second": 162.853,
-      "eval_steps_per_second": 20.364,
+      "eval_accuracy": 0.5191570881226054,
+      "eval_loss": 0.709879457950592,
+      "eval_runtime": 20.2957,
+      "eval_samples_per_second": 51.44,
+      "eval_steps_per_second": 1.626,
       "step": 26
     }
   ],
@@ -36,9 +36,9 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.616634659922366e-06,
+    "learning_rate": 3.1436979979087796e-05,
     "num_train_epochs": 3,
     "per_device_train_batch_size": 64,
-    "seed": 8
+    "seed": 32
   }
 }

run-2/checkpoint-26/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4836333ade6016bf5baac215292836f3a17a1c875576861472678ef49fe0a85d
+oid sha256:de4e41e121af7a82574e2467a1ce497f08ca103ccd86549bda68b0f3024fe148
 size 4984

run-2/checkpoint-39/README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: google-bert/bert-base-uncased
+base_model: bert-base-uncased
 ---
 
 # Model Card for Model ID

run-2/checkpoint-39/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google-bert/bert-base-uncased",
+  "base_model_name_or_path": "bert-base-uncased",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -11,12 +11,12 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

run-2/checkpoint-39/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333607637a8e9da4cbd40a0c465b3993836a8a90c365d498a0dc95963fada12e
-size 602816
+oid sha256:0b6cc571f370a6baf0e19621db0bfc73e3f81ba783f637dfe15e95da0317b52f
+size 2372416

run-2/checkpoint-39/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a8dfdfafc70b53121b607e46c53f7364c4b2119e09caf0228ea9139b6b2617d
-size 660858
+oid sha256:2e72b716e36315a289aa6696c501d4e4aca5db77ae4a6cb8bae371f6614c6741
+size 1251642

run-2/checkpoint-39/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0be50e76ee5398269ecc3fe8661439e7b9143c345a1e62c838dcdd82dffd5e41
+oid sha256:92bb0676550c784abaf5c45b9426aa78770d086b16039e37541efff3235add74
 size 14308