Model save

README.md

@@ -31,8 +31,8 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.051110418843398e-06
-- train_batch_size: 32
+- learning_rate: 4.6496174473363295e-06
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4267c53b60ba80772c2bf654f6b7f83b8c1b47c519106a6cb0c90f49848bcb7
+oid sha256:3159237ae974dce61bdb13af2ea26953279457c0e870da08e1c2f002729cd792
 size 498612824

run-400fa_00003/checkpoint-25/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "allenai/biomed_roberta_base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-400fa_00003/checkpoint-25/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3159237ae974dce61bdb13af2ea26953279457c0e870da08e1c2f002729cd792
+size 498612824

run-400fa_00003/checkpoint-25/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa25691e891847074e4c61a488170381cc5c7f18cfc1e67c54ded546ab513aa
+size 997345530

run-400fa_00003/checkpoint-25/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017d3df6e5fb067508737abc8295ae69dec18fe37eca55d3a2c979c256d43ff1
+size 14244

run-400fa_00003/checkpoint-25/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89353ac62eae8fcc589a94d05e5bfd10e1efcebc9cb0128a7d8cf78df73dc471
+size 1064

run-400fa_00003/checkpoint-25/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_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
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-400fa_00003/checkpoint-25/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "padding": true,
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "truncation": true,
+  "unk_token": "<unk>"
+}

run-400fa_00003/checkpoint-25/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.6986096501350403,
+  "best_model_checkpoint": "Mach_0_tuning/run-400fa_00003/checkpoint-25",
+  "epoch": 5.0,
+  "eval_steps": 1,
+  "global_step": 25,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.6990227699279785,
+      "eval_runtime": 1.9702,
+      "eval_samples_per_second": 10.151,
+      "eval_steps_per_second": 1.523,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.6987298130989075,
+      "eval_runtime": 2.1339,
+      "eval_samples_per_second": 9.373,
+      "eval_steps_per_second": 1.406,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.6989489793777466,
+      "eval_runtime": 2.1877,
+      "eval_samples_per_second": 9.142,
+      "eval_steps_per_second": 1.371,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.698739230632782,
+      "eval_runtime": 2.2159,
+      "eval_samples_per_second": 9.026,
+      "eval_steps_per_second": 1.354,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.6986096501350403,
+      "eval_runtime": 1.9541,
+      "eval_samples_per_second": 10.235,
+      "eval_steps_per_second": 1.535,
+      "step": 25
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 25,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.6496174473363295e-06,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.0019307837536547132
+  }
+}

run-400fa_00003/checkpoint-25/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631214f07854034da8719b3f10fabcf61fc13197e074fde972ebbc449d0516df
+size 4600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06d60b4a0882ab77af62ff7ebe9c298b7709578e3291ad3d379cdabc67d31a2
+oid sha256:631214f07854034da8719b3f10fabcf61fc13197e074fde972ebbc449d0516df
 size 4600