Training in progress, epoch 2

logs/events.out.tfevents.1719241205.f94f01b9b918.2392.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84da5ed8de8ecc290a0d041069d2d9c15ebe11dd6c8ef83483f4c3442d033d9
-size 5428
+oid sha256:03f2ac80e7ceb55213ceff350a7b0bf1568ac9cd852372cf58254eb374e6e6fb
+size 5962

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f38b9ea491ce667f59ded0ccfbdfe75281aee028ae8d5466c274041caf164206
+oid sha256:a04314b749d4acea219b75473b7159304fd15abbb0749b74b9a72dc41ad508ee
 size 17549312

run-1/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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04314b749d4acea219b75473b7159304fd15abbb0749b74b9a72dc41ad508ee
+size 17549312

run-1/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:423e71317f9893f34e82137928e32e1c64e9bfc71f968a12029e3756d7667ebc
+size 35123898

run-1/checkpoint-1054/rng_state.pth

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

run-1/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f3e3377f11bafe7b5302825b91f3a273d3263332c198caed974a11f7c0d037
+size 1064

run-1/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-1/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-1/checkpoint-1054/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.8176605504587156,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/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": 30.242748260498047,
+      "learning_rate": 0.000111895725910844,
+      "loss": 2.3991,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 1.9181628227233887,
+      "eval_runtime": 2.3714,
+      "eval_samples_per_second": 367.708,
+      "eval_steps_per_second": 2.952,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 76.58197784423828,
+      "learning_rate": 8.95250705409598e-05,
+      "loss": 1.1199,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 1.8561229705810547,
+      "eval_runtime": 2.3966,
+      "eval_samples_per_second": 363.855,
+      "eval_steps_per_second": 2.921,
+      "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": 0.051381532356201576,
+    "learning_rate": 0.0001342239322193053,
+    "num_train_epochs": 6,
+    "temperature": 23
+  }
+}

run-1/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6a7f7b16042aa90d6a482b54cde9c8a264f21ae121942f35d43fb01c1ae0eb
+size 5176