Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc5f212905dfcc20e573fb9830873dc2806f2fcd8c5bc9bfdb64bf832d24b9c
+oid sha256:5bf8ecb69b6e0b966635d55febf8fc98caa0f60b91db45ee8520770c7120e2d4
 size 267832560

run-0/checkpoint-1069/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-0/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf8ecb69b6e0b966635d55febf8fc98caa0f60b91db45ee8520770c7120e2d4
+size 267832560

run-0/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:033a502df8b6a0d1b930b66d0fadc5d72ed70d78e9103c8fa2efc4d5bc99f263
+size 535727290

run-0/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d2a3968a19704d5b6eb2bc1993585e0eefc93c8a0404b2dbe20523a2511dc6
+size 14244

run-0/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f303d3a20e824d276d873d84f46baa9f17a4900dfcc1e09ddfd4513118423580
+size 1064

run-0/checkpoint-1069/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-1069/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-0/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.4299032759161841,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.9693511172311064e-05,
+      "loss": 0.5777,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.7577054770506707e-05,
+      "loss": 0.5164,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4963381886482239,
+      "eval_matthews_correlation": 0.4299032759161841,
+      "eval_runtime": 0.7359,
+      "eval_samples_per_second": 1417.305,
+      "eval_steps_per_second": 89.686,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 37571065943808.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.180996757411542e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 27
+  }
+}

run-0/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63ac474f3d09802334bfe3221e5805678f75d0d7a031b794d5096e76dc1197b
+size 4792

runs/Dec23_05-05-39_584c28cbb8bb/events.out.tfevents.1703308289.584c28cbb8bb.195.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816c4f88f52cb64fbbbd11ff40189cb2cd353339683bef304fc8c7dbef59b2e3
+size 4999

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026cc7cbd9e89669ae6744e42ea5dd60967427e6f7c95410234ca26e7a4e0e4b
+oid sha256:d63ac474f3d09802334bfe3221e5805678f75d0d7a031b794d5096e76dc1197b
 size 4792