Training in progress, epoch 1

logs/events.out.tfevents.1721409638.f39e781deb18.907.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e6183ff4a8ac50d59616a72587191e3d3bf517f9263a105cb2045df9701c3e
-size 8105
+oid sha256:c705ec755ff170691b4fa23900992d06a98819c2d95e2089e3a49151a17a259d
+size 8993

logs/events.out.tfevents.1721411579.f39e781deb18.907.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:765584e76386e5f00e5c6205d13a98b17cf9840ad98b2ce31e242ea6b2adf96b
+size 5453

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cfdf481b8cc4fa49bac35f68fccd51065822ca926fe1c52db4d910636e98890
+oid sha256:30a832b2bc5a46165de925f94b0c1dd3f7f8ac25d1638d582ab1547bb4a3b99f
 size 17549312

run-0/checkpoint-527/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-0/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a832b2bc5a46165de925f94b0c1dd3f7f8ac25d1638d582ab1547bb4a3b99f
+size 17549312

run-0/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489c9fdbebbf30fac2b37d17c4a6b6a0e567773f2660f296619144a0bbb40f1c
+size 35123898

run-0/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9733f27bb728718f7284348156186daf975855376673d9de7e218a8cff476307
+size 14308

run-0/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145e03370ffae820427ff75d7ffd0b11daf97bef9df67f2447bb56200bbea65e
+size 1064

run-0/checkpoint-527/special_tokens_map.json

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

run-0/checkpoint-527/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-0/checkpoint-527/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8245412844036697,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 25.944990158081055,
+      "learning_rate": 0.0001902833119739952,
+      "loss": 1.3021,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 1.3208283185958862,
+      "eval_runtime": 2.3956,
+      "eval_samples_per_second": 363.993,
+      "eval_steps_per_second": 2.922,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5044754522393149,
+    "learning_rate": 0.00021142590219332797,
+    "num_train_epochs": 10,
+    "temperature": 21
+  }
+}

run-0/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ee3b8fabdace7b3b360bef47288e304ce46d525841a5824231251db0d68f07
+size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c6430dc1910f9997216ab9d035226026b6fb590da8a06afe605cfb5d01dafcf
+oid sha256:71ee3b8fabdace7b3b360bef47288e304ce46d525841a5824231251db0d68f07
 size 5176