Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e59a3a9959ed5c9ef756be9972e0a308d6775bc0b2d9bff9bd37c11f353874d1
+oid sha256:10425bd7dbfd09e13f0a50ef5d196ea0174d4383837b86a489605ae63579ade3
 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 sha256:10425bd7dbfd09e13f0a50ef5d196ea0174d4383837b86a489605ae63579ade3
+size 267832560

run-3/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492aa69c406d6536b51d0a488c60ae5f9ec6ff83632f35ccd2c04ce009286471
+size 535727290

run-3/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54da1dccf9a24b2161ec0efa4e8615ce7d84d52d4247839fc92b002eb16c7b4e
+size 14244

run-3/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048c306aba5a3f264f28908d6db2cdeed5debe2d77d8f66a50d54dc8a4b840e6
+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": 0.5165560626605169,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-4276",
+  "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": 2.2593712965969752e-05,
+      "loss": 0.6136,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.068352417953335e-05,
+      "loss": 0.5687,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.877333539309695e-05,
+      "loss": 0.5475,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.686314660666055e-05,
+      "loss": 0.5604,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5529224276542664,
+      "eval_matthews_correlation": 0.4471137769925502,
+      "eval_runtime": 0.7648,
+      "eval_samples_per_second": 1363.699,
+      "eval_steps_per_second": 86.293,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4952957820224147e-05,
+      "loss": 0.4684,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.3042769033787746e-05,
+      "loss": 0.4493,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.1132580247351345e-05,
+      "loss": 0.4875,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 9.222391460914944e-06,
+      "loss": 0.4503,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8003203272819519,
+      "eval_matthews_correlation": 0.5165560626605169,
+      "eval_runtime": 0.748,
+      "eval_samples_per_second": 1394.336,
+      "eval_steps_per_second": 88.232,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 7.3122026744785425e-06,
+      "loss": 0.3587,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 5.402013888042142e-06,
+      "loss": 0.279,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 3.4918251016057417e-06,
+      "loss": 0.2666,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.5816363151693402e-06,
+      "loss": 0.2792,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0243171453475952,
+      "eval_matthews_correlation": 0.4896234097252215,
+      "eval_runtime": 0.8044,
+      "eval_samples_per_second": 1296.561,
+      "eval_steps_per_second": 82.045,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 97694965234188.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.4503901752406154e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-3/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08bfc3d7f49a884fc330f138c816e06fded64aa61c9f76b393d7e45663a9d61
+size 4792

runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703299109.39bac3413ec0.1762.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9fa787cdd51b924b48e9535a362b382f1bf47afd127395c315d28773fd1e84
-size 6748
+oid sha256:483543e75767da8eaa5f66ebd92b3552972e9318a511325a2284d56570635792
+size 7594