Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05fccb75155fd3e76595b9fab6d6c7a85335077fdfb78802cbf4f876d9b8c257
+oid sha256:660adf2801f75a7d2e7d30bbf079280332a902672f373039e475628ce4bbc370
 size 267835644

run-2/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-2/checkpoint-294/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660adf2801f75a7d2e7d30bbf079280332a902672f373039e475628ce4bbc370
+size 267835644

run-2/checkpoint-294/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9f2ec53df39a49f8c2d2bdc898fdacab5e2e49f0d1bb303c0c832494f4ea67
+size 535733434

run-2/checkpoint-294/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1774b836e54466712b5269dd8a4c5aa7d3cda0097295a2152b36a310f9112aa6
+size 14308

run-2/checkpoint-294/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4e8511548ab23100b435e50fd6bcfcf88b8a33c6ad613db7e628caf9d8742d
+size 1064

run-2/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-2/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-2/checkpoint-294/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.7722602739726028,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-2/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": 0.6643835616438356,
+      "eval_loss": 0.7592821717262268,
+      "eval_runtime": 3.589,
+      "eval_samples_per_second": 162.72,
+      "eval_steps_per_second": 10.309,
+      "step": 147
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7722602739726028,
+      "eval_loss": 0.5706833004951477,
+      "eval_runtime": 3.5712,
+      "eval_samples_per_second": 163.531,
+      "eval_steps_per_second": 10.361,
+      "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": 6.031594833830981e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 20
+  }
+}

run-2/checkpoint-294/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36120bb4b2d0b720eac4a646b1e2a8af896ce0926f8d47d5e1fdf1d13dfce58c
+size 4984

runs/Apr01_13-09-37_c7a746a4e968/events.out.tfevents.1711979017.c7a746a4e968.35.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be0a5dc2f5aa05ef179181ce45044395f80b253d815dc0951064a92998638c4
-size 4980
+oid sha256:64c1dd1694ecf7707c5278fa03b95e84e738bbffaad82cd80f39fd0ac5b879eb
+size 5303