Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2fc5302aedc3e5ce150c1f244cd6f7e9a4d1f31e0c820d0bf4abecf8d4821b
+oid sha256:621e5a70e25a697cdb6af3dcab28982705a4524d2a4cdabb610720748a9817d0
 size 267835644

run-2/checkpoint-879/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "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": "4.38.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-879/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:621e5a70e25a697cdb6af3dcab28982705a4524d2a4cdabb610720748a9817d0
+size 267835644

run-2/checkpoint-879/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9484aefbbad054f5f6220057ea1bec5ccff17acbeeed0ae519c160e75d95840d
+size 535733434

run-2/checkpoint-879/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:889b87c05082290121246664e6235d98b87a68dbf8113c4b269a7294fe753d1f
+size 14244

run-2/checkpoint-879/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04894354ba0486729145ec6a411f866a096bb41ede98e8c74c030827cf78ed0a
+size 1064

run-2/checkpoint-879/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-879/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-879/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.7808219178082192,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-2/checkpoint-879",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 879,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7791095890410958,
+      "eval_loss": 0.4647526144981384,
+      "eval_runtime": 3.3644,
+      "eval_samples_per_second": 173.581,
+      "eval_steps_per_second": 10.997,
+      "step": 293
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 12.796131134033203,
+      "learning_rate": 1.0510539180585223e-05,
+      "loss": 0.5057,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7773972602739726,
+      "eval_loss": 0.452179491519928,
+      "eval_runtime": 3.3787,
+      "eval_samples_per_second": 172.846,
+      "eval_steps_per_second": 10.951,
+      "step": 586
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7808219178082192,
+      "eval_loss": 0.47243908047676086,
+      "eval_runtime": 3.3703,
+      "eval_samples_per_second": 173.279,
+      "eval_steps_per_second": 10.978,
+      "step": 879
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 879,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 632183474186820.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.4376685856819023e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 1
+  }
+}

run-2/checkpoint-879/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3932c714b605371539fb65a2f969f3ef4f8526d436c1a28e802b95b0c1c31630
+size 4984

runs/Apr02_02-49-58_ef019a3ab26d/events.out.tfevents.1712027124.ef019a3ab26d.26.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b53d0f9cf5e015e16981a1e5eedaf195b5aa8b6fca58646cf45d1fb8922f86
-size 5514
+oid sha256:809ac7e439bdab5d9cf1340923b488538f95e64a2ebc4998af3445218f45b601
+size 6191