Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ce3ad60cef1e6feccfea104b5cf8b6d767565705e14682f6f0e8ce22fffb8d2
+oid sha256:f9fd82df05a08c3051f43fb89686dc2adefa42e8d7d22d1a76ba55f015d4c7c1
 size 267832560

run-2/checkpoint-2138/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": "4.39.3",
+  "vocab_size": 30522
+}

run-2/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fd82df05a08c3051f43fb89686dc2adefa42e8d7d22d1a76ba55f015d4c7c1
+size 267832560

run-2/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fee8b61b68fb8e04991832f092fcb32a34ad3aef6c7777dc9f43a5d157a8bf6
+size 535724410

run-2/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3553dcfbe5525edefb39f241c4a80f16389e6d118c9fa5cbdc74404f1a7e5cb3
+size 14054

run-2/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71c640a2b0c12978c58c1d0eb08b32a85d2c94036651b68c08511bf8bc0ee5c
+size 1064

run-2/checkpoint-2138/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-2138/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-2138/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.4183935375368045,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2138",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 13.065943717956543,
+      "learning_rate": 9.837377839260441e-06,
+      "loss": 0.5777,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 14.142450332641602,
+      "learning_rate": 9.226512349986941e-06,
+      "loss": 0.5355,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.057891845703125,
+      "learning_rate": 8.615646860713443e-06,
+      "loss": 0.5373,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 7.0049896240234375,
+      "learning_rate": 8.004781371439942e-06,
+      "loss": 0.5423,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6402870416641235,
+      "eval_matthews_correlation": 0.4183935375368045,
+      "eval_runtime": 37.1869,
+      "eval_samples_per_second": 28.048,
+      "eval_steps_per_second": 1.775,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 32605608297312.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0448243328533941e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 17
+  }
+}

run-2/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a659579e67a9dc400cc873b4a2558b8281975c5f7d68079e1715fffe3b7c06
+size 4984

runs/Apr06_21-18-55_3b2751949eb5/events.out.tfevents.1712455662.3b2751949eb5.9166.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4f48ee8305998c3d839bac330b9180144665e55dc910c512f15caa0eceaee1
+size 5753

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa5b935ca08b0b7d98978f23a4eaf03b4afc2e6ee9cc6948f40b4c1adac9206e
+oid sha256:94a659579e67a9dc400cc873b4a2558b8281975c5f7d68079e1715fffe3b7c06
 size 4984