Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3ec27e465fbede207e4e3824e193818d95d870bee61da0752ccea5dbefb20e9
+oid sha256:261be5b5c7290814887a09e19c546a7800725a2e4dd7792f61195ef75798460f
 size 267832560

run-9/checkpoint-214/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": "4.38.1",
+  "vocab_size": 30522
+}

run-9/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63aeb203727644fca31e5055047795658f92330e053dae32edd4d629b7ca94f
+size 267832560

run-9/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a46ca6427964e22fbd5aafcd22086a047d3fd31c4c9e08a6e67dcc327b51dcf
+size 535727290

run-9/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c4a99b5ed9ee3fcab6d990a1fc4b7359ff5b09468bc41b290af5c406a6dbb9
+size 14244

run-9/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:150011e0e8252d8b587c7f80d8ff9552a868e6f92e2c98c92a746024dce0ca9e
+size 1064

run-9/checkpoint-214/special_tokens_map.json

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

run-9/checkpoint-214/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-9/checkpoint-214/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-107",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6132212281227112,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7898,
+      "eval_samples_per_second": 1320.54,
+      "eval_steps_per_second": 83.562,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.610018253326416,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8002,
+      "eval_samples_per_second": 1303.475,
+      "eval_steps_per_second": 82.483,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.233914191146871e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 34
+  }
+}

run-9/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954dbe40442ceee1a365a09ad487c87b89c6b85858c584d72d74fb3fd22179b9
+size 4984

runs/Feb27_12-48-22_1e7c639bcfdf/events.out.tfevents.1709040095.1e7c639bcfdf.1356.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60837de741f1e7da03471d0866113baba44ecf3ea4c50a35a2784de66c4967bb
+size 6547

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:954dbe40442ceee1a365a09ad487c87b89c6b85858c584d72d74fb3fd22179b9
+oid sha256:69153e9bbab207ff12f995d64fcbc179aebf9c056495013eeb831a9bd3f09fb4
 size 4984