Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a3c914b179bdfc905fe174157f511969a2e052858dc34bf83f632d02f9a5853
+oid sha256:e8c8a388e36e0bf6ad2319a1bef8deb3da83e87730116e7d0d4866a53317ad9e
 size 267832560

run-3/checkpoint-27/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-3/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3c914b179bdfc905fe174157f511969a2e052858dc34bf83f632d02f9a5853
+size 267832560

run-3/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59eec27909f3297f35b5f97a894d96d24cf87d5ca9fdac2247a39a561854a1e
+size 535724410

run-3/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4ca19e853a3459b79b53f2df57a71e0ae961da57ac656ecf8e5510594b419f
+size 13990

run-3/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0b664165499c7b913febd28c1fd3ab6454e183dd79654dd98a6b7a2e8a9589
+size 1064

run-3/checkpoint-27/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-27/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-27/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-27",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6020533442497253,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 9.537,
+      "eval_samples_per_second": 109.364,
+      "eval_steps_per_second": 6.92,
+      "step": 27
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 27,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.180477976197639e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 32,
+    "seed": 10
+  }
+}

run-3/checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f871f4c45d8ee71ff481529e1268a5e036899d3683aef7c022425ba007cc4651
+size 4984

run-4/checkpoint-14/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:277e869931432944b230640c18d6f80856a865ae6e6d176aabfdaef3544d4792
+oid sha256:e8c8a388e36e0bf6ad2319a1bef8deb3da83e87730116e7d0d4866a53317ad9e
 size 267832560

run-4/checkpoint-14/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc8782561965b069b6a2542d3764f359381163aa9353733a66fdccb1c0cdabb
-size 535727290
+oid sha256:db89def4da1e39555b7d62e45d6e7180726eff40d9c8d1aa6bc426ca111e94c8
+size 535724410

run-4/checkpoint-14/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f5464af7614d6c639d0c1eba053042043244ebd6c4976966283ba707d189e9
-size 14244
+oid sha256:49e5617ee18262a7900400658a63a9f3b7734297827e4ac11c51b096629faf6b
+size 13990

run-4/checkpoint-14/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a3dfa588e4e2a3cdd636034aa70517e4fb8176050615af27d2fb6d94c347b53
+oid sha256:378bbe24a37e5818f54b7f3f993f85a3d3b5985b6ea651315f1eb6de0608471e
 size 1064

run-4/checkpoint-14/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": -0.02339059069282274,
+  "best_metric": 0.0463559874942472,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-14",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6748577952384949,
-      "eval_matthews_correlation": -0.02339059069282274,
-      "eval_runtime": 0.5175,
-      "eval_samples_per_second": 2015.397,
-      "eval_steps_per_second": 127.532,
+      "eval_loss": 0.6544817686080933,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 9.8012,
+      "eval_samples_per_second": 106.416,
+      "eval_steps_per_second": 6.734,
       "step": 14
     }
   ],
@@ -27,9 +27,9 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 9.275459477508523e-06,
+    "learning_rate": 6.226187573987636e-06,
     "num_train_epochs": 2,
     "per_device_train_batch_size": 64,
-    "seed": 19
+    "seed": 27
   }
 }

run-4/checkpoint-14/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f215b8d0a2d3f4dfd3304f2a727dab785e1a5bd6316594447c1595a03c7703c
+oid sha256:b4c0d3a0c467db322c0006765e467b1f7b3e3b026673cc6b57936f072d505de9
 size 4984

runs/Mar06_18-56-30_6942db43b48a/events.out.tfevents.1709753908.6942db43b48a.1479.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd449f0b576fdd2fd939d53d4f97de790a7cbcd483b3c6b64ee877373ffe39db
+size 4871

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f871f4c45d8ee71ff481529e1268a5e036899d3683aef7c022425ba007cc4651
+oid sha256:b4c0d3a0c467db322c0006765e467b1f7b3e3b026673cc6b57936f072d505de9
 size 4984