Training in progress, epoch 2

logs/events.out.tfevents.1709456138.49ae8f4e8e7b.1647.17

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a22fa903660fdc625d8c0757f138805831987136b8c10552223d5687d850cdb
-size 5180
+oid sha256:5f193fd882e70d2c7b17680e3e4c742d22d7094e1c8b9673dce821a000167d46
+size 5714

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42fd1789b8f66804806aaf7e8c89d46f34b6bda9937d7312b10257634acdab74
+oid sha256:baae0e2599ccc722a13e80c6e9258f193ca99257a480a583837d1858c2e1d357
 size 17549312

run-16/checkpoint-1054/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-16/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baae0e2599ccc722a13e80c6e9258f193ca99257a480a583837d1858c2e1d357
+size 17549312

run-16/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b78b81385703c16e8f75fb72e67845bef551cd027d684a661260536b0a953d
+size 35123898

run-16/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b242219066ee20691234b53c3eb9b8da10cd3bc00e333f52e39e5b4d6628c98
+size 14308

run-16/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb02758e6bcaadc7a29ad006cc6a032eab3dc043a67bc768c924da2cf2b5b70e
+size 1064

run-16/checkpoint-1054/special_tokens_map.json

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

run-16/checkpoint-1054/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-16/checkpoint-1054/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.8291284403669725,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-1054",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1054,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 15.605107307434082,
+      "learning_rate": 0.00011351736809377586,
+      "loss": 1.2624,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 1.1314730644226074,
+      "eval_runtime": 2.8139,
+      "eval_samples_per_second": 309.89,
+      "eval_steps_per_second": 2.488,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.443777084350586,
+      "learning_rate": 7.567824539585057e-05,
+      "loss": 0.6363,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 1.1333012580871582,
+      "eval_runtime": 2.8147,
+      "eval_samples_per_second": 309.801,
+      "eval_steps_per_second": 2.487,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 16141525436100.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5930583577377427,
+    "learning_rate": 0.00015135649079170115,
+    "num_train_epochs": 4,
+    "temperature": 20
+  }
+}

run-16/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a57fdeab65524293cd0d615294bcf49a03ea5ac5a67936255d0dead2ac2a4c51
+size 4984