Training in progress, step 1000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,81 @@
+{
+  "_name_or_path": "pilotj/distilbert-base-uncased-fibe-full-finetuned",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9aff6b4377d4db5d1dd8d57109ad2b1bb837f8deb3e8d5cd433eef331ab78a6
+size 267906392

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75cae182ed7928992fa29bbc0b1b6b0913ae56ccacbb300c79db7a0b68fd8a27
+size 535874874

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc63afadff5169faba1d70af89c7adf294d3b9445e91fc01e2fc366a69fd4ac3
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e985453b58764f07d3d99014cb269bf51ad4885870b52e389b12b9d89e2e66f6
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 0.4119344651699066,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-1000",
+  "epoch": 0.048118564142046,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024059282071023,
+      "grad_norm": 2.836960792541504,
+      "learning_rate": 3.849485131363681e-06,
+      "loss": 0.3677,
+      "step": 500
+    },
+    {
+      "epoch": 0.048118564142046,
+      "grad_norm": 3.160072088241577,
+      "learning_rate": 7.698970262727362e-06,
+      "loss": 0.386,
+      "step": 1000
+    },
+    {
+      "epoch": 0.048118564142046,
+      "eval_loss": 0.4119344651699066,
+      "eval_runtime": 244.2084,
+      "eval_samples_per_second": 107.085,
+      "eval_steps_per_second": 0.839,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4240771055616000.0,
+  "train_batch_size": 32,
+  "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:c8585dcafab5345f844add4e2bc002a3a051b8ac0a38199ffecd63f43e65610c
+size 5240