Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bbbc757980d40efb5a432d3cb1e55a9113e054003a7e3d88471a88d97b98ea1
+oid sha256:b6bc8f2c476cdf221059a09cdd59fdc414ad543144746ab93d529c28824af76f
 size 267832560

run-0/checkpoint-1070/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bc8f2c476cdf221059a09cdd59fdc414ad543144746ab93d529c28824af76f
+size 267832560

run-0/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3afc0d33dbc447b459d976b9e1d7e8569b8a3775f2b66f13527e185ca79f2ff9
+size 535727290

run-0/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c03f8dbea380c37eb38fc129a2d937ca61022aedda1cc98bd40a51a4e790bb
+size 14308

run-0/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8f1e816de9d6142f548bd669df4faa1464569e3c25062fe1ad580242d5aec3
+size 1064

run-0/checkpoint-1070/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-1070/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-1070/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.4465618323468758,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1070",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.355229248248623e-05,
+      "loss": 0.5639,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5066079497337341,
+      "eval_matthews_correlation": 0.3915828968181581,
+      "eval_runtime": 0.697,
+      "eval_samples_per_second": 1496.499,
+      "eval_steps_per_second": 94.697,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.8942570072719275e-05,
+      "loss": 0.3737,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5427648425102234,
+      "eval_matthews_correlation": 0.4465618323468758,
+      "eval_runtime": 0.7057,
+      "eval_samples_per_second": 1478.025,
+      "eval_steps_per_second": 93.528,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 85591274132772.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.816201489225318e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 37
+  }
+}

run-0/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb2d563a1a63fc11ba4d05f1b4a9a4f37d59cc535c711b0aa9d5040b632ff21
+size 4792

runs/Dec23_02-11-24_38c624d3e13b/events.out.tfevents.1703299070.38c624d3e13b.382.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eb502acaed99a308800ad2d1c93ca762ce7b0ba025d996a7f907ce3a2acaf76
-size 4846
+oid sha256:7d25de18fc4d69f27f59d4da4e63bf3d901cf55d437dd5e58e5cbfe761b3e44e
+size 5338