Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeacb971215ed069e0428526aafe228ad66e54b5ff75753195f9182fd57551cb
+oid sha256:2c25d7081d642af00fda64e03ac9ac56800ca6dc6fac5e0a30573f8f989ced1c
 size 267835644

run-0/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-0/checkpoint-1006/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c25d7081d642af00fda64e03ac9ac56800ca6dc6fac5e0a30573f8f989ced1c
+size 267835644

run-0/checkpoint-1006/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fbc79a1ba4a575ab103414e94efa6ebbd9738f9ce85f4753df1ed02c4e87226
+size 535733434

run-0/checkpoint-1006/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a6b57a2c579e7e8d28bae7183aa7ad8e4b8d2fe5fb8685f87203742427160c
+size 14244

run-0/checkpoint-1006/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd6a52a1246b06cfc6dd434cd9e2b00a03e58d926419e023a7691c02ffc0258
+size 1064

run-0/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-0/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-0/checkpoint-1006/trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1006,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.582615760696608e-06,
+      "loss": 0.7539,
+      "step": 500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 8.991243985015741e-08,
+      "loss": 0.5852,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1006,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1059559383550464.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5075319081543059e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-0/checkpoint-1006/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6164c7e047aecfbade9d8183e80e68eedbb9572d846e98e50ba9c2cb33c835
+size 4600

runs/Dec31_10-05-31_c2a715ec62ca/events.out.tfevents.1704017611.c2a715ec62ca.647.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef6f591201b9b7c7beb60f876728fea075e79077d88444b4f651bc03e1ab412
-size 4447
+oid sha256:d771f7f2d9c27f8cce99d4a1552faa0d7f2a2503a22a181d52993bc8430d5d84
+size 4958