Model save

README.md

@@ -31,8 +31,8 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3.625617634576222e-05
-- train_batch_size: 8
+- learning_rate: 2.051110418843398e-06
+- train_batch_size: 32
 - 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 sha256:540f79ec1b6b1256dd71114f83e4d6917d5b344e47978c133dae2205298fcf2c
+oid sha256:d4267c53b60ba80772c2bf654f6b7f83b8c1b47c519106a6cb0c90f49848bcb7
 size 498612824

run-400fa_00002/checkpoint-15/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_00002/checkpoint-15/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4267c53b60ba80772c2bf654f6b7f83b8c1b47c519106a6cb0c90f49848bcb7
+size 498612824

run-400fa_00002/checkpoint-15/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52378555a61787d6d863114e067743c6b9a4f5629e093a53661e803b7500832d
+size 997345530

run-400fa_00002/checkpoint-15/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea2d5d579605d351356116935ba1d8d5ab5c6faf483011546da8f4e87ddaad1
+size 14244

run-400fa_00002/checkpoint-15/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d583d7ad4ee414542510ae185c95f3fb5a0ae3374dc8b7dcb2df09287736ad6a
+size 1064

run-400fa_00002/checkpoint-15/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_00002/checkpoint-15/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_00002/checkpoint-15/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.700579047203064,
+  "best_model_checkpoint": "Mach_0_tuning/run-400fa_00002/checkpoint-15",
+  "epoch": 5.0,
+  "eval_steps": 1,
+  "global_step": 15,
+  "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": 0.7014357447624207,
+      "eval_runtime": 1.9965,
+      "eval_samples_per_second": 10.018,
+      "eval_steps_per_second": 1.503,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.7010012865066528,
+      "eval_runtime": 1.9646,
+      "eval_samples_per_second": 10.18,
+      "eval_steps_per_second": 1.527,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.7007691264152527,
+      "eval_runtime": 2.0134,
+      "eval_samples_per_second": 9.933,
+      "eval_steps_per_second": 1.49,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.700641930103302,
+      "eval_runtime": 1.9461,
+      "eval_samples_per_second": 10.277,
+      "eval_steps_per_second": 1.542,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.6206896551724138,
+      "eval_loss": 0.700579047203064,
+      "eval_runtime": 1.9745,
+      "eval_samples_per_second": 10.129,
+      "eval_steps_per_second": 1.519,
+      "step": 15
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.051110418843398e-06,
+    "per_device_train_batch_size": 32,
+    "weight_decay": 0.0013066739238053284
+  }
+}

run-400fa_00002/checkpoint-15/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06d60b4a0882ab77af62ff7ebe9c298b7709578e3291ad3d379cdabc67d31a2
+size 4600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c972cccc0360e2c0c0f5b2a7fcca5f0d11cde5db2be26eeb5e7317b62459b2d
+oid sha256:c06d60b4a0882ab77af62ff7ebe9c298b7709578e3291ad3d379cdabc67d31a2
 size 4600