Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30314671d012a77b10d14423adcb085d63617df8e090acad568c586c6a5000de
+oid sha256:a36417434268f4fc31a89d3e84df49407e40cca1d23c29db70aae54a16f6277e
 size 267835644

run-1/checkpoint-2012/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-1/checkpoint-2012/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36417434268f4fc31a89d3e84df49407e40cca1d23c29db70aae54a16f6277e
+size 267835644

run-1/checkpoint-2012/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5afdfcc9ddf6d57cddba0589eea8f28b2f10e7d5c2892d859fa9a8d08c7433c4
+size 535733434

run-1/checkpoint-2012/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3144b7b62a8feaa92ecb79d324e297c2c08227124d4ae03ad37c0234e22f37e2
+size 14244

run-1/checkpoint-2012/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0019cf318cbeb1884f164264c56df52516e559fff59b5badf82021761efcb4
+size 1064

run-1/checkpoint-2012/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-2012/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-2012/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2012,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.137186621867392e-06,
+      "loss": 0.8553,
+      "step": 500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.438381522043518e-06,
+      "loss": 0.7017,
+      "step": 1000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.7395764222196454e-06,
+      "loss": 0.6315,
+      "step": 1500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 4.077132239577295e-08,
+      "loss": 0.628,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2012,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1059559383550464.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.835991721691264e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-1/checkpoint-2012/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a1fe2197625adb3375c9bcc8aecf7a0110a20a4d9dced9c6ee724e52db31c8a
+size 4600

runs/Dec31_10-05-31_c2a715ec62ca/events.out.tfevents.1704018062.c2a715ec62ca.647.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83410539fc4583af90722d87b13942a92aa79dbdfd87f3c056d04921c43facf5
-size 5451
+oid sha256:1f42738cd788b6aacb44156f9026685c52822a7e7579a44ba785da557f30cbea
+size 6119