Upload 7 files

sentibot/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/CDS525_Deep_Learning/Bert/checkpoint-160/",
+  "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"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.48.3",
+  "vocab_size": 30522
+}

sentibot/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f69a6cc19d5237bdbfb671ba1e88759f8d931ca30263deb66099eb134f38175
+size 267835644

sentibot/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb9c85dce1405fd4979599afa8b2d41ea576d9b9a727f70c400802fabac8b17
+size 535733434

sentibot/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfef049d1fd4fcd4491555e1ebe254f1c632800ef2ed3346a3243ec630794b94
+size 14244

sentibot/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684c3e2167c5a4e88fb6c84465f9d1b861ad3145efebcf9adf0596790d98dbaa
+size 1064

sentibot/trainer_state.json

@@ -0,0 +1,209 @@
+{
+  "best_metric": 0.85,
+  "best_model_checkpoint": "/content/drive/MyDrive/CDS525_Deep_Learning/Bert/checkpoint-200",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.345510959625244,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.5124,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.1650004386901855,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.5809,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.9150302410125732,
+      "learning_rate": 3e-06,
+      "loss": 0.5794,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.3806991577148438,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.5496,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.5721051692962646,
+      "learning_rate": 5e-06,
+      "loss": 0.465,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.76,
+      "eval_loss": 0.6291395425796509,
+      "eval_runtime": 0.2848,
+      "eval_samples_per_second": 351.184,
+      "eval_steps_per_second": 45.654,
+      "step": 50
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 4.393792152404785,
+      "learning_rate": 6e-06,
+      "loss": 0.5082,
+      "step": 60
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 5.113018989562988,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 0.4634,
+      "step": 70
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 6.131932258605957,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4731,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 6.784789562225342,
+      "learning_rate": 9e-06,
+      "loss": 0.4512,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 18.650039672851562,
+      "learning_rate": 1e-05,
+      "loss": 0.3553,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.5160402655601501,
+      "eval_runtime": 0.2705,
+      "eval_samples_per_second": 369.636,
+      "eval_steps_per_second": 48.053,
+      "step": 100
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 6.815101146697998,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.3335,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.4982528686523438,
+      "learning_rate": 1.2e-05,
+      "loss": 0.3452,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 18.664701461791992,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 0.2615,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 13.972925186157227,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.2938,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.012152671813965,
+      "learning_rate": 1.5e-05,
+      "loss": 0.2145,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.82,
+      "eval_loss": 0.4765576124191284,
+      "eval_runtime": 0.1806,
+      "eval_samples_per_second": 553.641,
+      "eval_steps_per_second": 71.973,
+      "step": 150
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 12.484073638916016,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.174,
+      "step": 160
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 1.2589740753173828,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.1341,
+      "step": 170
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.848324179649353,
+      "learning_rate": 1.8e-05,
+      "loss": 0.1065,
+      "step": 180
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.6378048658370972,
+      "learning_rate": 1.9e-05,
+      "loss": 0.1847,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 20.119579315185547,
+      "learning_rate": 2e-05,
+      "loss": 0.2493,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.85,
+      "eval_loss": 0.4600130319595337,
+      "eval_runtime": 0.2984,
+      "eval_samples_per_second": 335.087,
+      "eval_steps_per_second": 43.561,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 20233721076408.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

sentibot/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48538da40bb01c3193f7e4aef4908d09047795caa3b6370646bfe19e47539938
+size 5304