Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7780a4334e62d09a00a541aae4beb670d24ef3f23e32622bd79d307e774c81f
+oid sha256:ae807426dad2f395aeb9c2adad56885671a3c0c3f80fa9edd1509a5bad86663f
 size 267832560

run-1/checkpoint-2138/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-1/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae807426dad2f395aeb9c2adad56885671a3c0c3f80fa9edd1509a5bad86663f
+size 267832560

run-1/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f290b4a3396e7fe1fbed23943a7bd2bfe46b1c7e347f343f5ec7b093a7371ec9
+size 535727290

run-1/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d76d65c77fb186c3fbdb64b847b3ef8df5bf266edca1ab06703355dea9e0c222
+size 14308

run-1/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:867caf2f7c24220745c92957ca30a6b53a59cf978fb02efe8572d8791f4044a5
+size 1064

run-1/checkpoint-2138/special_tokens_map.json

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

run-1/checkpoint-2138/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-1/checkpoint-2138/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.2593416356162653,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.4228813326982605e-06,
+      "loss": 0.6042,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.885463715571553e-07,
+      "loss": 0.5805,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5644888281822205,
+      "eval_matthews_correlation": 0.06558874629318973,
+      "eval_runtime": 0.8416,
+      "eval_samples_per_second": 1239.243,
+      "eval_steps_per_second": 78.418,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 5.542114104160501e-07,
+      "loss": 0.54,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.1987644927494504e-07,
+      "loss": 0.5271,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5480139851570129,
+      "eval_matthews_correlation": 0.2593416356162653,
+      "eval_runtime": 0.767,
+      "eval_samples_per_second": 1359.757,
+      "eval_steps_per_second": 86.044,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 75364635721296.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.8572162938393657e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 20
+  }
+}

run-1/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5286ae5c124969f543741c8eea680a105cde45d2f1a78671f4aaf17df54fadce
+size 4792

runs/Dec23_01-44-29_cab255cafe95/events.out.tfevents.1703296264.cab255cafe95.13310.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f83074b5ecb76aceb3d2869deabf84238d761db141d77d499895d9f83ba16a
-size 4993
+oid sha256:501792bc0556692c95661588e7cfc5115ff1d1f18fda62cf89490d3a61bd915b
+size 5996