Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ed0ce45abda1941230f1014b68d24540c24d9f2b42814e29d0f7efc942d25b
+oid sha256:9370cd4d7520110c4062be569af9c95d30e92f27da9255763696d75b468560a2
 size 267832560

run-8/checkpoint-27/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-8/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9370cd4d7520110c4062be569af9c95d30e92f27da9255763696d75b468560a2
+size 267832560

run-8/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4ff42018704cdee85c0b5d50e38e8ca2b495562a1fe03965d28fecdeb080a7
+size 535727290

run-8/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9353c5bc7c84b0753ff0ba0c2c8fd0e72cd0eeac4007abe2d57134a9743a22
+size 14244

run-8/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539fe9f3c1e4fbb13b11a5a208921d08ddf3d21efac896ba035b3d676ada2112
+size 1064

run-8/checkpoint-27/special_tokens_map.json

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

run-8/checkpoint-27/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-8/checkpoint-27/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-27",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6348778605461121,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7419,
+      "eval_samples_per_second": 1405.779,
+      "eval_steps_per_second": 88.956,
+      "step": 27
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 81,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.837985511423762e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 38
+  }
+}

run-8/checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20a5e603679fdf0c856aa7604cd6020bf500bfd0d4e0b6222354662318aedba
+size 4984

runs/Feb27_13-13-45_1f21758cd63c/events.out.tfevents.1709041530.1f21758cd63c.270.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36f7282c22b7aaa9c3c956b7c9e9765169655548f567edbdfc7312fdc4e9a2a
+size 4871

runs/Feb27_13-13-45_1f21758cd63c/events.out.tfevents.1709041537.1f21758cd63c.270.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7662d8452307692f7a931abee8ed35b88d0706507432394b4e10336c2f767a31
+size 5877

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67cd1e1f45ea162c3276224ec096955ac7a053afaf32de336765b08f264423e
+oid sha256:c20a5e603679fdf0c856aa7604cd6020bf500bfd0d4e0b6222354662318aedba
 size 4984