Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:686dae01a5f5ff62ca84deb385085fe832215d27a85fb7dea19c6554428eaee9
+oid sha256:b002475867a6556113b7be4967ee415d9cdcc33de8158c4f48a676d97e09ee69
 size 267832560

run-5/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": "4.38.2",
+  "vocab_size": 30522
+}

run-5/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b002475867a6556113b7be4967ee415d9cdcc33de8158c4f48a676d97e09ee69
+size 267832560

run-5/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7115cece05bb3ea4b5bd37be75ffa336f5d6f0a1b48e24265f9a7949f63de0
+size 535727290

run-5/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043952d9edc00d21829eaba972db94580847d9d9cabcef696b311fc9b53d5436
+size 14244

run-5/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b95b532d27db1fa030540bd930737dcceeccaad98a5a0e110f80e514beaf37d
+size 1064

run-5/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-5/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-5/checkpoint-6414/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_metric": 0.5100838064555473,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/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,
+      "grad_norm": 6.39190673828125,
+      "learning_rate": 1.1209948118290708e-05,
+      "loss": 0.6229,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 9.500582695007324,
+      "learning_rate": 1.026220140555054e-05,
+      "loss": 0.5429,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 26.185821533203125,
+      "learning_rate": 9.314454692810372e-06,
+      "loss": 0.5158,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.5794659852981567,
+      "learning_rate": 8.366707980070203e-06,
+      "loss": 0.5486,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5384177565574646,
+      "eval_matthews_correlation": 0.47375271850377065,
+      "eval_runtime": 0.7535,
+      "eval_samples_per_second": 1384.226,
+      "eval_steps_per_second": 87.592,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 1.9103285074234009,
+      "learning_rate": 7.418961267330036e-06,
+      "loss": 0.4782,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 108.48860168457031,
+      "learning_rate": 6.471214554589867e-06,
+      "loss": 0.4572,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.3420422673225403,
+      "learning_rate": 5.5234678418497e-06,
+      "loss": 0.4584,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 16.485048294067383,
+      "learning_rate": 4.5757211291095315e-06,
+      "loss": 0.4633,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7257216572761536,
+      "eval_matthews_correlation": 0.4894919726378361,
+      "eval_runtime": 0.8153,
+      "eval_samples_per_second": 1279.261,
+      "eval_steps_per_second": 80.95,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.4752595126628876,
+      "learning_rate": 3.6279744163693633e-06,
+      "loss": 0.3977,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 84.74446105957031,
+      "learning_rate": 2.680227703629195e-06,
+      "loss": 0.3094,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 44.53423309326172,
+      "learning_rate": 1.7324809908890274e-06,
+      "loss": 0.3461,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 45.21189498901367,
+      "learning_rate": 7.847342781488592e-07,
+      "loss": 0.3176,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9411513209342957,
+      "eval_matthews_correlation": 0.5100838064555473,
+      "eval_runtime": 0.7484,
+      "eval_samples_per_second": 1393.668,
+      "eval_steps_per_second": 88.19,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 97851494093928.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2157694831030876e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 38
+  }
+}

run-5/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e7488a23871540af1a662c62183f9a7ec76213a6a302500c4aad6a29c3d9bb
+size 4984

runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709520731.78dd22f13cdf.294.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2488e3235d66a13fb55f399040e9c6f7379a0edb5bb0dfd83280658b58b32ff8
-size 7552
+oid sha256:7196594ee67a500b89c897836d51cef3c8c23adaa7fe933d694408c966307d58
+size 8452