Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:507bd3c7beab0c0ea26bc5642b0f7c99c4fc15dd058a6d771e2b572986dac1cb
+oid sha256:1efc22763465d0b8d7dfb1290411a8a76743145b1e37dfc5d290764ecb3c857d
 size 267835644

run-6/checkpoint-74/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-6/checkpoint-74/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1efc22763465d0b8d7dfb1290411a8a76743145b1e37dfc5d290764ecb3c857d
+size 267835644

run-6/checkpoint-74/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17996f759447c2605506e2f193384f3af57807c2acb43f872730e4ab59a9495
+size 535733434

run-6/checkpoint-74/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f332ab43c4373a929184c67b6cc15ae614f5a6420c1d9f5b4b712d70bfbfaf
+size 14244

run-6/checkpoint-74/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f698395ea4b0822625bf9ba6bdc4cc380b604171bd9c5589a2088089150fcae0
+size 1064

run-6/checkpoint-74/special_tokens_map.json

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

run-6/checkpoint-74/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-6/checkpoint-74/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.7773972602739726,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-6/checkpoint-74",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 74,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7773972602739726,
+      "eval_loss": 0.49054154753685,
+      "eval_runtime": 3.5826,
+      "eval_samples_per_second": 163.009,
+      "eval_steps_per_second": 10.328,
+      "step": 74
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 222,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.4994070101208046e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 12
+  }
+}

run-6/checkpoint-74/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00fd4888413ade9131ee6d977b2bc7c070f2facd269c2d1c528bfcdca035b67
+size 4984

runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711980578.c7a746a4e968.35.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed24fbbff1018148db1b2785e5e5ffd3b2a9946910aff79f61013c45e1c77c80
+size 4975

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2169875d997fb2cd49501109cfd101c2eb5aaba058ae6185bc1a61c9a68c978a
+oid sha256:c00fd4888413ade9131ee6d977b2bc7c070f2facd269c2d1c528bfcdca035b67
 size 4984