Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca4374e298ab6236f543d322fa77d6680dd59f2963474c95c8cf28606e0d245
+oid sha256:1251e9ce05d2003185cdcf1685f4baf349e0b762148f67f20eaf859af76ba823
 size 267832560

run-2/checkpoint-8552/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": "4.41.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1251e9ce05d2003185cdcf1685f4baf349e0b762148f67f20eaf859af76ba823
+size 267832560

run-2/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76309e806b8e9767ed01ceb5ebde62a3b4ecac0a90413af377ec789fb0bf5ea7
+size 535727290

run-2/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e045e82e93d9055d857764b5860c82d59187eb9b8d62c054e239387a096e84d
+size 14308

run-2/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f6369565df8a1e24a09e2a69bbe09a9749587e4896b2d46087a57686932dab3
+size 1064

run-2/checkpoint-8552/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-8552/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-8552/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": 0.4276963144473042,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-8552",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 3.80633282661438,
+      "learning_rate": 1.4038087770081304e-06,
+      "loss": 0.6287,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 5.112864017486572,
+      "learning_rate": 1.3349270902069464e-06,
+      "loss": 0.5844,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 16.39091682434082,
+      "learning_rate": 1.2660454034057625e-06,
+      "loss": 0.5781,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 7.839633464813232,
+      "learning_rate": 1.1971637166045783e-06,
+      "loss": 0.5482,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5578071475028992,
+      "eval_matthews_correlation": 0.25376727839543856,
+      "eval_runtime": 1.0111,
+      "eval_samples_per_second": 1031.593,
+      "eval_steps_per_second": 129.567,
+      "step": 2138
+    },
+    {
+      "epoch": 1.1693171188026192,
+      "grad_norm": 17.102230072021484,
+      "learning_rate": 1.1282820298033944e-06,
+      "loss": 0.5349,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 14.366960525512695,
+      "learning_rate": 1.0594003430022104e-06,
+      "loss": 0.5129,
+      "step": 3000
+    },
+    {
+      "epoch": 1.637043966323667,
+      "grad_norm": 26.894271850585938,
+      "learning_rate": 9.905186562010263e-07,
+      "loss": 0.482,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 9.88732624053955,
+      "learning_rate": 9.216369693998422e-07,
+      "loss": 0.4997,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5702487230300903,
+      "eval_matthews_correlation": 0.4033061591161787,
+      "eval_runtime": 1.0209,
+      "eval_samples_per_second": 1021.619,
+      "eval_steps_per_second": 128.315,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1047708138447145,
+      "grad_norm": 10.997356414794922,
+      "learning_rate": 8.527552825986582e-07,
+      "loss": 0.4925,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 10.581222534179688,
+      "learning_rate": 7.838735957974742e-07,
+      "loss": 0.4627,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5724976613657624,
+      "grad_norm": 23.820741653442383,
+      "learning_rate": 7.149919089962902e-07,
+      "loss": 0.4931,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 34.82048416137695,
+      "learning_rate": 6.461102221951062e-07,
+      "loss": 0.4764,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6053777933120728,
+      "eval_matthews_correlation": 0.42419730237002035,
+      "eval_runtime": 1.0601,
+      "eval_samples_per_second": 983.872,
+      "eval_steps_per_second": 123.574,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0402245088868103,
+      "grad_norm": 14.74622917175293,
+      "learning_rate": 5.772285353939221e-07,
+      "loss": 0.4914,
+      "step": 6500
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 14.342729568481445,
+      "learning_rate": 5.083468485927381e-07,
+      "loss": 0.4473,
+      "step": 7000
+    },
+    {
+      "epoch": 3.5079513564078577,
+      "grad_norm": 49.85002517700195,
+      "learning_rate": 4.3946516179155406e-07,
+      "loss": 0.4811,
+      "step": 7500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 42.889713287353516,
+      "learning_rate": 3.705834749903701e-07,
+      "loss": 0.4755,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9756782039289056,
+      "grad_norm": 8.599506378173828,
+      "learning_rate": 3.01701788189186e-07,
+      "loss": 0.4762,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6376412510871887,
+      "eval_matthews_correlation": 0.4276963144473042,
+      "eval_runtime": 1.1398,
+      "eval_samples_per_second": 915.085,
+      "eval_steps_per_second": 114.934,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 138658697190840.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4726904638093145e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 37
+  }
+}

run-2/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0576f7d7c7a556468716db9c3a189f008e7820db6e39f98cfa101cc682a87d0c
+size 5176

runs/Jun16_07-07-37_5152ff55fb03/events.out.tfevents.1718522681.5152ff55fb03.1457.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f3e13b395fe9fec44721e6ff1f39496c8f5a3257b0413421c37ae9304390559
-size 8746
+oid sha256:e79a297a2f9ae554e718ce06983be410ff0b10c0be375c690b61a05baaf2efa8
+size 9925