Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9533b2071acf8adc45b12085153135a595570e6ebc96380b9e145f579c506ff7
+oid sha256:3842cbeb9c80ecc10d415d7fc4b0e674dad4c34a5fa0afc3d7d516aff9af1669
 size 267832560

run-3/checkpoint-6414/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-3/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3842cbeb9c80ecc10d415d7fc4b0e674dad4c34a5fa0afc3d7d516aff9af1669
+size 267832560

run-3/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092723afd4f6725521ccf3a70fe2779cca52e8bd7a418b7b51e3c8c638b42d43
+size 535727290

run-3/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e638ee70d645caff5d428fcc5315efdc83fde310b7ad9be4bda2ed58870194ac
+size 14244

run-3/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1525455bc351e7c57d7c4abab54c700f4609a2a0d94f5604c77dd3d2f57a2e86
+size 1064

run-3/checkpoint-6414/special_tokens_map.json

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

run-3/checkpoint-6414/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-3/checkpoint-6414/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.4116764797450708,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-6414",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6414,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8134386732635114e-06,
+      "loss": 0.6097,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.6601212338601031e-06,
+      "loss": 0.5883,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.506803794456695e-06,
+      "loss": 0.562,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.3534863550532868e-06,
+      "loss": 0.5302,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5693901181221008,
+      "eval_matthews_correlation": 0.2787671229651657,
+      "eval_runtime": 0.716,
+      "eval_samples_per_second": 1456.694,
+      "eval_steps_per_second": 92.178,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.2001689156498788e-06,
+      "loss": 0.5141,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.0468514762464705e-06,
+      "loss": 0.5067,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.935340368430625e-07,
+      "loss": 0.4926,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 7.402165974396544e-07,
+      "loss": 0.501,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5920860171318054,
+      "eval_matthews_correlation": 0.4068953869702192,
+      "eval_runtime": 0.7393,
+      "eval_samples_per_second": 1410.839,
+      "eval_steps_per_second": 89.276,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 5.868991580362463e-07,
+      "loss": 0.487,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 4.3358171863283815e-07,
+      "loss": 0.4612,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.802642792294301e-07,
+      "loss": 0.4818,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.2694683982602193e-07,
+      "loss": 0.4724,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6004377007484436,
+      "eval_matthews_correlation": 0.4116764797450708,
+      "eval_runtime": 0.7351,
+      "eval_samples_per_second": 1418.79,
+      "eval_steps_per_second": 89.78,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 97649170840512.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9667561126669194e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 1
+  }
+}

run-3/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b91e4836dde5a11432215e79bbc165d4ffa71f41124bd5e3404c89fe5fe37126
+size 4792

runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703299284.04248f4b0c3a.492.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3530fccc718c2aaeb2a5a5b3a3ee7014f61c517e0b1fcc7f55eb211617a86a61
-size 6747
+oid sha256:8e19f98a58079b301ac421a1767c0f0d3c646bfa158763a47e5cac6ed2e3b8d1
+size 7593