Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cac1960a2b6cb21296bfd0a005b0b9f5341a695a2ad3fe900b8e53094bcf848
+oid sha256:4c9257e43b9ed6b0f7936bdd524e3c9c5d32c713737011dcfa27f78d968bf006
 size 267835644

run-5/checkpoint-1006/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.35.2",
+  "vocab_size": 30522
+}

run-5/checkpoint-1006/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9257e43b9ed6b0f7936bdd524e3c9c5d32c713737011dcfa27f78d968bf006
+size 267835644

run-5/checkpoint-1006/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c20115d16f822212b3340da847ff0923f632b58bd5609540addc95a6e6eddb0
+size 535733434

run-5/checkpoint-1006/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5144b763018d5ac016007bd7a830d88f389d50630842432e7b89c4e6c0120aa6
+size 14244

run-5/checkpoint-1006/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:061a65b1a21cfacace9de09f891afd7057177789b1129e5ea8b9db692bdfd671
+size 1064

run-5/checkpoint-1006/special_tokens_map.json

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

run-5/checkpoint-1006/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-5/checkpoint-1006/trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1006,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 3.539544804843382e-06,
+      "loss": 0.8997,
+      "step": 500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.3690604117073428e-06,
+      "loss": 0.7285,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2012,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 529879044096000.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.7100291979794205e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-5/checkpoint-1006/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21bad4b530a777dc526ff23f84ef2b80d571bbba09119e7bcf67d31e6bdd172b
+size 4600

runs/Dec31_10-05-31_c2a715ec62ca/events.out.tfevents.1704019984.c2a715ec62ca.647.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0bede7edfce62f0d88dfc8c274348e68edd5fd350876a4200ac0384f618d73
+size 5452

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec07b46c94e0e9008994b97eaea5b651d507bb577eae3a86bf603d60553c307a
+oid sha256:21bad4b530a777dc526ff23f84ef2b80d571bbba09119e7bcf67d31e6bdd172b
 size 4600