Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3b2e217d650a9480acbe329b45f8b141de34bd539a476b4531d454d764da17
+oid sha256:85c9db6b304cec82199c794dc856ace06a931e2bf6d224a19996ad692e9dd528
 size 267832560

run-3/checkpoint-268/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-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2592b8c29caf392be7f7f475e1d615bf6e161a1feea9aad896662f96c4c1abb0
+size 267832560

run-3/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ecd3b895093175f3a73dba4768d7604cd3e5b3a397bde94a1f7e9f42b4f58dd
+size 535727290

run-3/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede6b03a2600d287b2b7af9fcd02ae6f3ddd8e32d2e292bf231ffdd642ae9eeb
+size 14308

run-3/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e4cbff64374187a0427418723fc6956acde83c37ddd0e481309e2455b8d6b3
+size 1064

run-3/checkpoint-268/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-268/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-268/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-134",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6148698329925537,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.768,
+      "eval_samples_per_second": 1358.112,
+      "eval_steps_per_second": 85.94,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6106393337249756,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7777,
+      "eval_samples_per_second": 1341.086,
+      "eval_steps_per_second": 84.863,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1733425766035844e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64,
+    "seed": 32
+  }
+}

run-3/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99eb940aa1c1d981227783c76591ca444ab02b2a22829ce4fbdfce9e668bb16c
+size 4792

run-4/checkpoint-134/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:949408d61d5ac6b2653a74d309ab26cdd3be09b79060ae6c3894e67ad1e97068
+oid sha256:85c9db6b304cec82199c794dc856ace06a931e2bf6d224a19996ad692e9dd528
 size 267832560

run-4/checkpoint-134/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df5c326146b9f46ec0c075009734a7fdcc33e443f607ffa52d3473271f54437
+oid sha256:ed057952dadc8551213e49cf4868490fcd1b56bc9266575efb1cc9af78ba7be8
 size 535727290

run-4/checkpoint-134/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d58e82f2ee7a032b0b5398225e6e82ec00cc018b7d78794d6e570470038097
+oid sha256:56a86fffc2bf2835432cce2f692113fe3df57ced71234f9929276224ee1a1cc9
 size 14308

run-4/checkpoint-134/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77136fe6a7094a4cb5cc83cb5201f3ba4a89761186c3850a980cc44fa8495c96
+oid sha256:b4b58bbaa9526a55ca1b10ffcb9a70bbdb675d6fc15549a682f95e36348e39ea
 size 1064

run-4/checkpoint-134/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4130889956247439,
+  "best_metric": 0.3489031724545359,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-134",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.4921027719974518,
-      "eval_matthews_correlation": 0.4130889956247439,
-      "eval_runtime": 0.7437,
-      "eval_samples_per_second": 1402.413,
-      "eval_steps_per_second": 88.743,
+      "eval_loss": 0.5429930686950684,
+      "eval_matthews_correlation": 0.3489031724545359,
+      "eval_runtime": 0.7377,
+      "eval_samples_per_second": 1413.869,
+      "eval_steps_per_second": 89.468,
       "step": 134
     }
   ],
@@ -27,9 +27,9 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.3070930848457665e-05,
+    "learning_rate": 2.829056514710492e-05,
     "num_train_epochs": 3,
     "per_device_train_batch_size": 64,
-    "seed": 17
+    "seed": 21
   }
 }

run-4/checkpoint-134/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36bde66e6449e9c1f7e73eb4952b2d02cf91a055154e256af6d28a1a6c8f7d0c
+oid sha256:61b56e5f82cc951887c4c01ff028e462450cb914b81691299dbf652a64752f11
 size 4792

runs/Dec23_05-05-39_584c28cbb8bb/events.out.tfevents.1703308880.584c28cbb8bb.195.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a7e60dcde06cad56ab19deb2b06a35670302789cef7d12ab4d78bdadb4dc72
+size 5710

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99eb940aa1c1d981227783c76591ca444ab02b2a22829ce4fbdfce9e668bb16c
+oid sha256:61b56e5f82cc951887c4c01ff028e462450cb914b81691299dbf652a64752f11
 size 4792