Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a01f0da45b11a5f96ec450d8b2f7143b430f0a9ce2ec856ea71a259936e918
+oid sha256:a12b02757d857db48bd5c8daec5a85ce97f9b614039f6f3c5c823b38c26c32c6
 size 267838720

run-33tpx14s/checkpoint-125/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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,
+  "transformers_version": "4.56.1",
+  "vocab_size": 30522
+}

run-33tpx14s/checkpoint-125/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12b02757d857db48bd5c8daec5a85ce97f9b614039f6f3c5c823b38c26c32c6
+size 267838720

run-33tpx14s/checkpoint-125/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56908b76c9a67e2895387d7755494a93e965f20418e480d79f7c698a7a9f10aa
+size 535737163

run-33tpx14s/checkpoint-125/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70c8fb6befb3bcd223ffe3efcf58014f4eb6359b6c8708b3e9f1367b4e4ac1a
+size 14391

run-33tpx14s/checkpoint-125/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b585a33b1d1357d1a47108265f3d29140c3441c7c550d485165b86f3c373f4
+size 1465

run-33tpx14s/checkpoint-125/special_tokens_map.json

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

run-33tpx14s/checkpoint-125/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-33tpx14s/checkpoint-125/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_global_step": 125,
+  "best_metric": 0.4858984351158142,
+  "best_model_checkpoint": "topic_classifier_model/run-33tpx14s/checkpoint-125",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 125,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.87,
+      "eval_loss": 0.4858984351158142,
+      "eval_runtime": 157.7699,
+      "eval_samples_per_second": 6.338,
+      "eval_steps_per_second": 0.399,
+      "step": 125
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {
+      "cli_version": "0.21.3",
+      "m": [],
+      "python_version": "3.12.11",
+      "t": {
+        "1": [
+          1,
+          2,
+          3,
+          5,
+          11,
+          12,
+          41,
+          49,
+          51,
+          53,
+          71,
+          98,
+          100,
+          105
+        ],
+        "12": "0.21.3",
+        "13": "linux-x86_64",
+        "3": [
+          14
+        ],
+        "4": "3.12.11",
+        "5": "0.21.3",
+        "6": "4.56.1",
+        "8": [
+          1,
+          12
+        ]
+      }
+    },
+    "assignments": {},
+    "learning_rate": 5.791706128698021e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 3
+  }
+}

run-33tpx14s/checkpoint-125/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a39848412b97fe857dade1b2e88fbdb3ba986d0186e4ea1a9e7466c2be59d6
+size 5777

runs/Sep19_06-20-34_ea3a691caa9c/events.out.tfevents.1758263992.ea3a691caa9c.6934.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1043c4dca4b821b00e8dcec433abf9ac053e5975789f23a16a5fa9502c95430
+size 5381

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34232a23c78b6f6755534d991bb12a02754ce44599c5431c24d5ddf1e8870af0
+oid sha256:74a39848412b97fe857dade1b2e88fbdb3ba986d0186e4ea1a9e7466c2be59d6
 size 5777