Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:812b93a42b3064ce2a9bfd3b8b85b57add2aef32136f3e25f2349599152ce3fc
+oid sha256:50e9f11885310af60d31ab71116011e0969149e399c12a46703d0167f399453e
 size 267835644

run-2/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-2/checkpoint-1006/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e9f11885310af60d31ab71116011e0969149e399c12a46703d0167f399453e
+size 267835644

run-2/checkpoint-1006/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319b90d0ad9f4621b1c8724ffbcfbd08e9e72b4ac1591b4a56ea2d558f496e23
+size 535733434

run-2/checkpoint-1006/rng_state.pth

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

run-2/checkpoint-1006/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e16c129487f61541f42107add67eb37489fdeb02be75b19b01193e7419bf24f7
+size 1064

run-2/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-2/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-2/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": 1.113638924561454e-06,
+      "loss": 0.9618,
+      "step": 500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.3205204639068626e-08,
+      "loss": 0.8244,
+      "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": 2.2140726444838396e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-2/checkpoint-1006/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55dd5d39e994469c7ea6adee77efaab8666563b9eaefd8a7a5d34917e6c7dd4b
+size 4600

runs/Dec31_10-05-31_c2a715ec62ca/events.out.tfevents.1704018555.c2a715ec62ca.647.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9ec03dc50526030f1f2fe228bd51fca215b3398a72a91965a35f3c2948030e3
-size 5295
+oid sha256:c3337e8b0551b3fb88ebbf6700966f359dbfec09fcfdcee3333526588f95ecb1
+size 5806