Training in progress, epoch 2

logs/events.out.tfevents.1723127354.621b935b3e3f.593.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b319ba7b28af00f1311d9090014a5f88fbb07e6be562fdfec9e1a1d9b4d803
-size 5452
+oid sha256:0f8d1477eefa0127670d0e873728e16fb6349f2dbe8ba2ef0599ae224d09acd3
+size 5986

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a9f75f0f120bd5b6d6e19c699abb5423fcb1e644dadd5fc3d02bec80aece0d
+oid sha256:a2de728810e04a7b9524a9a75ede5aa044e3cc2632f36a7135d3d3d47d8e8aff
 size 17549312

run-3/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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2de728810e04a7b9524a9a75ede5aa044e3cc2632f36a7135d3d3d47d8e8aff
+size 17549312

run-3/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903ceac8f56fb08ae41e599929805b3ca3e457e07c2c960ce417e5c4941f1f4f
+size 35123898

run-3/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cd26c18bd73de03f23efd45b2b9c4ed2da8b8be6f5803534539d3670c38edc
+size 14308

run-3/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657dcc5511aaffe1166ddc57abe3ac6377fb8bf3f2dd625a5e4db7835aaf0b6c
+size 1064

run-3/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-3/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-3/checkpoint-1054/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.7775229357798165,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/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": 4.747544288635254,
+      "learning_rate": 8.421921303617797e-06,
+      "loss": 1.1824,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7259174311926605,
+      "eval_loss": 1.0221459865570068,
+      "eval_runtime": 2.6361,
+      "eval_samples_per_second": 330.793,
+      "eval_steps_per_second": 2.655,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.284089088439941,
+      "learning_rate": 6.737537042894237e-06,
+      "loss": 0.974,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7775229357798165,
+      "eval_loss": 0.8609867095947266,
+      "eval_runtime": 2.6102,
+      "eval_samples_per_second": 334.074,
+      "eval_steps_per_second": 2.682,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 16141525436100.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8183970243354497,
+    "learning_rate": 1.0106305564341356e-05,
+    "num_train_epochs": 6,
+    "temperature": 4
+  }
+}

run-3/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19b3d1ab98759ce4a3c2a3b1b6c08002a84c81483690b1cbe27bc016b13e374
+size 5176