Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5851c29922d531e4ae175a6cecb8422145bcce10d20e981d5315755e6c7c7d3
+oid sha256:c03e07eb7a22c8639d2c219ce73e97cd70c1830781593152055e945cd9fe081d
 size 267835644

run-0/checkpoint-294/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-0/checkpoint-294/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03e07eb7a22c8639d2c219ce73e97cd70c1830781593152055e945cd9fe081d
+size 267835644

run-0/checkpoint-294/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fa6c6d2a8e5681989dbf1cea782d3b1c907c12e0115ae553904db1886abc96
+size 535733434

run-0/checkpoint-294/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6ff0bf052b4b2c62c01ba83ee8211129025fbda9d04a3c8017af114c23b1ff
+size 14244

run-0/checkpoint-294/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9510a080607dfd7d80cbcb60efd33760cfc2a8e145d245cc98071019dc4afc
+size 1064

run-0/checkpoint-294/special_tokens_map.json

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

run-0/checkpoint-294/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-0/checkpoint-294/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.7825342465753424,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-0/checkpoint-294",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 294,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7688356164383562,
+      "eval_loss": 0.5073187947273254,
+      "eval_runtime": 3.5613,
+      "eval_samples_per_second": 163.984,
+      "eval_steps_per_second": 10.389,
+      "step": 147
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7825342465753424,
+      "eval_loss": 0.5155062675476074,
+      "eval_runtime": 3.5634,
+      "eval_samples_per_second": 163.888,
+      "eval_steps_per_second": 10.383,
+      "step": 294
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 735,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.745243169419031e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 6
+  }
+}

run-0/checkpoint-294/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da9af0f97bb745edd8810ff01baa7a946d32695a46eb9392d72614a6bff5844a
+size 4984

runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711978294.c7a746a4e968.35.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b5a6c35c03ed96ba03f2407f5435abf3fc689579d6f3b76b5ac158864ded8d5
-size 5013
+oid sha256:658f7858dc9eeeb5f24bfaba55ed3a846c3bbea916adaf1827f1203845d56152
+size 5336