Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f1685a9028863a21c8ef068a0a7a678cb05ab05a763225f577817bf7ae4cc2
+oid sha256:d5f36f5143a84b783caa75582d6b1acdff3f98d3aa49b30f3fe8f5631eea1300
 size 267832560

run-0/checkpoint-1072/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "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": "4.37.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-1072/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f36f5143a84b783caa75582d6b1acdff3f98d3aa49b30f3fe8f5631eea1300
+size 267832560

run-0/checkpoint-1072/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05f7290d16f2c662e264f1f69c2007a4bb4ad3c3a9a500f8b9c20c28f6680e1
+size 535724410

run-0/checkpoint-1072/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11db3ca3d969ca5a2a167ed02f325f4b2319be7133dd66e0d82814e6cdfe8b33
+size 13990

run-0/checkpoint-1072/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd43116678b4f6157cfdf3c204f6b8600f5120ce5fbd046bef7b2e9776d1688
+size 1064

run-0/checkpoint-1072/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-1072/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-1072/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.5460649174667868,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1072",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1072,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4662749767303467,
+      "eval_matthews_correlation": 0.42386559425174,
+      "eval_runtime": 30.5523,
+      "eval_samples_per_second": 34.138,
+      "eval_steps_per_second": 2.16,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.9114607492078965e-05,
+      "loss": 0.425,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5247857570648193,
+      "eval_matthews_correlation": 0.48074996963903815,
+      "eval_runtime": 31.3458,
+      "eval_samples_per_second": 33.274,
+      "eval_steps_per_second": 2.106,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5911181569099426,
+      "eval_matthews_correlation": 0.5325167447166456,
+      "eval_runtime": 30.5442,
+      "eval_samples_per_second": 34.147,
+      "eval_steps_per_second": 2.161,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 4.923517026974974e-06,
+      "loss": 0.1387,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8381235003471375,
+      "eval_matthews_correlation": 0.5460649174667868,
+      "eval_runtime": 31.6632,
+      "eval_samples_per_second": 32.94,
+      "eval_steps_per_second": 2.084,
+      "step": 1072
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 191447731731420.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.330569795718295e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 19
+  }
+}

run-0/checkpoint-1072/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72f1b39c9effe99043a3e407e4dedd56e0eb00ce40829698b7ced9fd0a7ccf6
+size 4792

runs/Jan26_08-04-50_7ac5f092fd85/events.out.tfevents.1706278490.7ac5f092fd85.1710.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2c6eb72d694ed7baa82a5563292fa129c835baa4dd49c90d9ef20b04480a8a
-size 5493
+oid sha256:f516b01de13e934935b4191933db7ad0b9a5272256ad01148761c7a9de7f5071
+size 6339