Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f18ca5f2049d94fea824128466a0f1820c99900e714cb7783890e8716c29379
+oid sha256:a02434c65736d0a8fcec4a8cb7e73842f4f322531971a14d1bd7374a916d5716
 size 267832560

run-1/checkpoint-642/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d8b58ba108904902c8d387dcb0a6bf4350a259dbaf1b16d588054e50869dea
+oid sha256:f0158a5328736318f4bea170218dd448fbc5fe454e41148e354a6924a234aa0f
 size 267832560

run-1/checkpoint-642/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d335ca405505f25b2a5dfc7b1695d9c4cccc399c2a4a9031d168f48f5c7baef6
+oid sha256:c30f72a2400745e075d9422a410ea714b9f9e981beb29166757d29cf048bfb68
 size 535727290

run-1/checkpoint-642/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceee227b46406252bc9089548ea8adfefa04d16678175fb045ad155cdf268e87
-size 14244
+oid sha256:079e25fe98e876c438386c26fa1f3a80835a1958dcfdd62ee56654fb584489ea
+size 14308

run-1/checkpoint-642/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f82afd87f3e26533afba46f9901b5d05d0c439d7da2c9a135ec373b749ca6031
+oid sha256:c27c778c08a0ee449255e932bd29af80b625335429ebd56f1c112b444e5e9c84
 size 1064

run-1/checkpoint-642/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.3432921557472473,
+  "best_metric": 0.3019091863081111,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-428",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,51 +10,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5924310088157654,
-      "eval_matthews_correlation": 0.06558874629318973,
-      "eval_runtime": 0.7705,
-      "eval_samples_per_second": 1353.67,
-      "eval_steps_per_second": 85.659,
+      "eval_loss": 0.5719716548919678,
+      "eval_matthews_correlation": 0.0835915715371112,
+      "eval_runtime": 0.6978,
+      "eval_samples_per_second": 1494.771,
+      "eval_steps_per_second": 94.588,
       "step": 214
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5929568409919739,
-      "eval_matthews_correlation": 0.3432921557472473,
-      "eval_runtime": 1.2272,
-      "eval_samples_per_second": 849.906,
-      "eval_steps_per_second": 53.781,
+      "eval_loss": 1.0430289506912231,
+      "eval_matthews_correlation": 0.3019091863081111,
+      "eval_runtime": 0.7554,
+      "eval_samples_per_second": 1380.773,
+      "eval_steps_per_second": 87.374,
       "step": 428
     },
     {
       "epoch": 2.34,
-      "grad_norm": 10.632513999938965,
-      "learning_rate": 6.962872544536971e-06,
-      "loss": 0.48,
+      "grad_norm": 75.47649383544922,
+      "learning_rate": 7.747466282949623e-06,
+      "loss": 0.4411,
       "step": 500
     },
     {
       "epoch": 3.0,
-      "eval_loss": 1.0858466625213623,
-      "eval_matthews_correlation": 0.3319729838669631,
-      "eval_runtime": 0.8034,
-      "eval_samples_per_second": 1298.204,
-      "eval_steps_per_second": 82.149,
+      "eval_loss": 1.2935222387313843,
+      "eval_matthews_correlation": 0.2953592953626779,
+      "eval_runtime": 0.7793,
+      "eval_samples_per_second": 1338.334,
+      "eval_steps_per_second": 84.688,
       "step": 642
     }
   ],
   "logging_steps": 500,
-  "max_steps": 856,
+  "max_steps": 642,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 8373388457232.0,
+  "total_flos": 8286715452252.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.674218791607766e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 3.5027277138406044e-05,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 4,
-    "seed": 16
+    "seed": 29
   }
 }

run-1/checkpoint-642/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36613bcef60bcf7fd2c5bce911434f81154fc143b65a8b57de2003769014ca00
+oid sha256:824c97682d0b5180a58b29aad975f1f670351c62a61736d4bcfd4286ecc497ee
 size 4984

run-2/checkpoint-14/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": "4.38.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-14/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a02434c65736d0a8fcec4a8cb7e73842f4f322531971a14d1bd7374a916d5716
+size 267832560

run-2/checkpoint-14/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1cbad42ba0fba6e6e9cf4ba262182405e1bb9eef9299daba146e449d568487b
+size 535727290

run-2/checkpoint-14/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:019c8a68e8084a0e71169f3880888079a18b4bfa89554bf419abeeee742f787e
+size 14244

run-2/checkpoint-14/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3671ed9e87140387533c4dc756d54af9edf8bef52c4179770c17cc6dbccd301a
+size 1064

run-2/checkpoint-14/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-14/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-14/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-14",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 14,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6130949854850769,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8143,
+      "eval_samples_per_second": 1280.789,
+      "eval_steps_per_second": 81.047,
+      "step": 14
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 56,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.734214749417639e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 19
+  }
+}

run-2/checkpoint-14/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cb90bd1c8e46e5757d6712e23ef509a5498348487b496f7195b93b5b09254f
+size 4984

runs/Feb28_19-52-39_5620ed9b2fff/events.out.tfevents.1709150879.5620ed9b2fff.209.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d687e5b855c4f348d2aeaf2047dba5cec43d8c3952ca9106a19d3491d0ba06
+size 6206

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824c97682d0b5180a58b29aad975f1f670351c62a61736d4bcfd4286ecc497ee
+oid sha256:29cb90bd1c8e46e5757d6712e23ef509a5498348487b496f7195b93b5b09254f
 size 4984