Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "no",
+    "1": "undetermined",
+    "2": "yes"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "no": 0,
+    "undetermined": 1,
+    "yes": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a748c1ab33837bc3a63346bb1a609553c03ec298903d57127fbdc8ae41d7d4
+size 737722356

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf9e954b1f558803d6c32f85ae4e96f81cbbf548ec178f4db1f4c4f1af1ad98
+size 1475564538

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3d5e0266651b678e8aeb775670681209a8f5307bbb491acb32c448d19c17f1
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a56ba2d77e666d1d1ae070faa9461d05bd079a4d3902c81c7c3926ae43ea2e
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": 0.1245394252026529,
+  "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-183",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 183,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.546448087431694,
+      "grad_norm": 4.420255661010742,
+      "learning_rate": 4.890710382513661e-05,
+      "loss": 1.0582,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.1245394252026529,
+      "eval_loss": 1.1087555885314941,
+      "eval_runtime": 13.0214,
+      "eval_samples_per_second": 7.065,
+      "eval_steps_per_second": 3.533,
+      "step": 183
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4575,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 487693576890000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4cef7ab6f4ff209dd756db3bbb721abd11ddfea5e6d59d89d58906d87bc93f
+size 5432