Training in progress, epoch 3

logs/events.out.tfevents.1721967656.98acc6742512.15262.43

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb8234e9021bbc7c9236ee9e6fc22b74c1d9536fddf718b8a728b4d50deef78
-size 6433
+oid sha256:f2bfe2125bbb2e2bc264b7ee3b565ca9f97a92cd9f8e1550885beccb17d52a42
+size 7158

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a04e13a6d1303a5342bf46779e7cb559fee2da5702b86ab8dd685be34eca4a
+oid sha256:ac56326fc5657aa5a2ee82be508c8c8bfd5b5a54b903f49273d0a035d715428a
 size 17549312

run-42/checkpoint-516/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-42/checkpoint-516/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac56326fc5657aa5a2ee82be508c8c8bfd5b5a54b903f49273d0a035d715428a
+size 17549312

run-42/checkpoint-516/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c1894c72773c8941711db3968e70ed91c278a4db186652f4aed7425084306b
+size 35123898

run-42/checkpoint-516/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e559bd010dfad806644ec9950fc1246348c344f69faad3d9fcd91973ca8dae1e
+size 14308

run-42/checkpoint-516/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0d055adf89c4ca2d4f1a7dfc6a2d5927c3c1c63aa5973161710fd9ad9aaac7
+size 1064

run-42/checkpoint-516/special_tokens_map.json

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

run-42/checkpoint-516/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-42/checkpoint-516/trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": 0.8066666666666666,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-42/checkpoint-516",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 516,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7573084831237793,
+      "learning_rate": 0.000305006369799479,
+      "loss": 0.4693,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8182613333333333,
+      "eval_BAC": 0.7513333333333333,
+      "eval_MCC": 0.5152913712924717,
+      "eval_PR_AUC": 0.7722575860284886,
+      "eval_accuracy": 0.7513333333333333,
+      "eval_loss": 0.42800581455230713,
+      "eval_runtime": 6.2417,
+      "eval_samples_per_second": 240.319,
+      "eval_steps_per_second": 7.53,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3580737113952637,
+      "learning_rate": 0.0002541719748328992,
+      "loss": 0.4408,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8542542222222222,
+      "eval_BAC": 0.782,
+      "eval_MCC": 0.5907158713484734,
+      "eval_PR_AUC": 0.809219961633705,
+      "eval_accuracy": 0.782,
+      "eval_loss": 0.40324756503105164,
+      "eval_runtime": 6.2606,
+      "eval_samples_per_second": 239.595,
+      "eval_steps_per_second": 7.507,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3590539693832397,
+      "learning_rate": 0.00020333757986631934,
+      "loss": 0.4252,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8693333333333334,
+      "eval_BAC": 0.8066666666666666,
+      "eval_MCC": 0.6195523600437505,
+      "eval_PR_AUC": 0.8436352184846998,
+      "eval_accuracy": 0.8066666666666666,
+      "eval_loss": 0.3929729461669922,
+      "eval_runtime": 6.25,
+      "eval_samples_per_second": 239.999,
+      "eval_steps_per_second": 7.52,
+      "step": 516
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 1351133190000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7141253736150909,
+    "learning_rate": 0.00035584076476605887,
+    "num_train_epochs": 7,
+    "temperature": 8
+  }
+}

run-42/checkpoint-516/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a69b9f95471c755661ba788d0f28bc3b9a005b3ef503c12409bca07c7ecbf3
+size 5240