Training in progress, epoch 2

logs/events.out.tfevents.1709749716.d65e8524b0f6.5185.25

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f187e238c6ba3d24e2f27c0579dd6c52e08ba5e3529940759f8171530eb623
-size 5313
+oid sha256:5d67a345139fc4e4894cc1d16c493eeb293e6d64e01c22e4500e9b7024836154
+size 5983

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edafe680ee105a780da215db840715e1f2e53321763f62593789834ddafa3959
+oid sha256:68ce37c1edb5d5fe478441b388ee25edbaa3173488cbca6575779968d227d9f8
 size 17549312

run-25/checkpoint-122/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-25/checkpoint-122/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ce37c1edb5d5fe478441b388ee25edbaa3173488cbca6575779968d227d9f8
+size 17549312

run-25/checkpoint-122/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f24128725bfb0e268529a8ac5139012d06ffecaa63161feb594cfef21c0ddc2
+size 35122746

run-25/checkpoint-122/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f742357f37751682c807a8bc7a379385df7a49c8ddf68695fc57d3a9f54cd1a7
+size 14054

run-25/checkpoint-122/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a41dbcb0b4e31ed3a4f9e43da90a72dba9bbe8f9cd5ec203b9866fec0b092be
+size 1064

run-25/checkpoint-122/special_tokens_map.json

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

run-25/checkpoint-122/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-25/checkpoint-122/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.5283757338551859,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-25/checkpoint-122",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 122,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9454018473625183,
+      "learning_rate": 3.055872843210697e-05,
+      "loss": 0.5488,
+      "step": 61
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.0,
+      "eval_loss": 0.5419712662696838,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 28.2925,
+      "eval_samples_per_second": 36.123,
+      "eval_steps_per_second": 1.131,
+      "step": 61
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.9724020957946777,
+      "learning_rate": 2.037248562140465e-05,
+      "loss": 0.537,
+      "step": 122
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5283757338551859,
+      "eval_f1": 0.16319444444444445,
+      "eval_loss": 0.5242463946342468,
+      "eval_precision": 0.7230769230769231,
+      "eval_recall": 0.09197651663405088,
+      "eval_runtime": 28.1822,
+      "eval_samples_per_second": 36.264,
+      "eval_steps_per_second": 1.135,
+      "step": 122
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 244,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 51,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7333782587426976,
+    "learning_rate": 4.07449712428093e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 51,
+    "temperature": 17
+  }
+}

run-25/checkpoint-122/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6521a8dc29cb693a8a19b2a26c2720bee7cef77f795a03d3120e313dbb2f26d
+size 4920