Training in progress, epoch 4

logs/events.out.tfevents.1719239773.f94f01b9b918.2392.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff3e9e6776e57f1298af04c3a8c14db36f1fb58731e637638e2a2a79f6a6375
-size 6496
+oid sha256:39ef25b1cc26d8fb84d9c2984080f42916fbb4f50b030dc65d38d13c57005fef
+size 7030

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d6f0e2214ce09dc211d998069eb98b5432e4531fbba06af7e853a06ef6117f7
+oid sha256:52e23161d13c2c0074293d23c46bb546af70686a45a81739153b9141d5aee932
 size 17549312

run-0/checkpoint-2108/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-0/checkpoint-2108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e23161d13c2c0074293d23c46bb546af70686a45a81739153b9141d5aee932
+size 17549312

run-0/checkpoint-2108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b231c0660c8389832990d020279e7e6bed45f149f650c87707b64d90e7e759f
+size 35123898

run-0/checkpoint-2108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37554b2d10e31eaeff51183dc670fea3e7982972d731e9e9b6dff48f2395e37d
+size 14308

run-0/checkpoint-2108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cff89e4666999e97f90d1645b64057419c7dc0028c34edc93cf14e1576ac0da
+size 1064

run-0/checkpoint-2108/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-2108/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-2108/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.8256880733944955,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-2108",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 16.55626678466797,
+      "learning_rate": 5.1383294230414005e-05,
+      "loss": 1.5907,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8061926605504587,
+      "eval_loss": 1.2464169263839722,
+      "eval_runtime": 2.4007,
+      "eval_samples_per_second": 363.232,
+      "eval_steps_per_second": 2.916,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": Infinity,
+      "learning_rate": 4.405675241279466e-05,
+      "loss": 0.9038,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 1.1235342025756836,
+      "eval_runtime": 2.3533,
+      "eval_samples_per_second": 370.54,
+      "eval_steps_per_second": 2.975,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 48.55740737915039,
+      "learning_rate": 3.67162818084498e-05,
+      "loss": 0.6946,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 1.1027159690856934,
+      "eval_runtime": 2.3719,
+      "eval_samples_per_second": 367.637,
+      "eval_steps_per_second": 2.951,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 16.267213821411133,
+      "learning_rate": 2.9375811204104943e-05,
+      "loss": 0.595,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 1.0700539350509644,
+      "eval_runtime": 2.3638,
+      "eval_samples_per_second": 368.893,
+      "eval_steps_per_second": 2.961,
+      "step": 2108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 32337743850420.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5167874928728581,
+    "learning_rate": 5.872376483475886e-05,
+    "num_train_epochs": 8,
+    "temperature": 5
+  }
+}

run-0/checkpoint-2108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f28149fe21091b257234d7cbe1611ee6ca88e3a7cef675e40e6d90410e6fc1a6
+size 5176