Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e847162584a63fc2b5ba5e89709a11e8088b406ea094129b0c68313a2d0e39
+oid sha256:92437c70ed70c1376223ded7a486f40caf899afc7a9a81ac0c41b5b333bcb2ba
 size 267832560

run-0/checkpoint-188/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-188/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92437c70ed70c1376223ded7a486f40caf899afc7a9a81ac0c41b5b333bcb2ba
+size 267832560

run-0/checkpoint-188/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90328a129a12021acc4a3fbfe6efde33b5b1bc180233923c8d2d98f221fb5c5f
+size 535727290

run-0/checkpoint-188/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19510c438ef4ab6c3cf8a277b989da9ea2b7fd7f7e67c219fa1a9557e404f745
+size 14244

run-0/checkpoint-188/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb39c66480bf8de3e936eec3f680f6b904c7b202cfedf3a61b81d8e527934ce8
+size 1064

run-0/checkpoint-188/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 188,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8344827586206897,
+      "eval_f1": 0.8345990695128626,
+      "eval_loss": 0.36505451798439026,
+      "eval_precision": 0.8347741140987747,
+      "eval_recall": 0.8344827586206897,
+      "eval_runtime": 6.2346,
+      "eval_samples_per_second": 162.801,
+      "eval_steps_per_second": 20.37,
+      "step": 94
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8443349753694581,
+      "eval_f1": 0.8446557137443836,
+      "eval_loss": 0.35532429814338684,
+      "eval_precision": 0.8456343508178881,
+      "eval_recall": 0.8443349753694581,
+      "eval_runtime": 6.3305,
+      "eval_samples_per_second": 160.334,
+      "eval_steps_per_second": 20.062,
+      "step": 188
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 188,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.9540891862156024e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32
+  }
+}

run-0/checkpoint-188/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6208cda24d8fa7973d51f688e4629da400fdd1e533b33bcb3230b504718b42
+size 5240

runs/Sep25_10-49-38_40a6cf7e9f4d/events.out.tfevents.1727261380.40a6cf7e9f4d.32062.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769295d2508a1274574caa73ac0478fe5d092df64ccfc8c5936bc5a08bb5db2a
-size 5331
+oid sha256:9fda01aa5ef0843c96ed15999f7c53da7e2f5e9a951fc33a2e120c33cd25f0e0
+size 6157