Training in progress, epoch 2

logs/events.out.tfevents.1713975353.a9ae8da52b57.4950.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b34d9bd51abb61bd8c9d73b7258e7665f4bab04ce0eba3bd94e141b225fcfa97
-size 5287
+oid sha256:f179eff56d085286e5144c320b1cb6b4943eb9436c4b6d3b679a7e2604cb85a1
+size 5821

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f62a77fc748cbccd1e5bc6df151f11af87401735f9b1cf222023246515a6a3f
+oid sha256:46d72db152cefc2018e5e9a155840e1863b5f54292af4e45d55809b2328944dc
 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": "4.40.1",
+  "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 sha256:46d72db152cefc2018e5e9a155840e1863b5f54292af4e45d55809b2328944dc
+size 17549312

run-3/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798c31fa58d18692da6f66c94f63159c43c70ea050e3158c45708131ddca15b3
+size 35123898

run-3/checkpoint-1054/rng_state.pth

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

run-3/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc6c0c7b1a612589a8c4474a265fee8de704a7a2b3be739f89ce536749823e2
+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 +1,58 @@
+{
+  "best_metric": 0.8291284403669725,
+  "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": 9.870479583740234,
+      "learning_rate": 8.893046706823292e-05,
+      "loss": 1.9749,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.805045871559633,
+      "eval_loss": 1.55028235912323,
+      "eval_runtime": 2.6975,
+      "eval_samples_per_second": 323.263,
+      "eval_steps_per_second": 2.595,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 21.232213973999023,
+      "learning_rate": 7.622611462991393e-05,
+      "loss": 0.97,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 1.449020266532898,
+      "eval_runtime": 2.6822,
+      "eval_samples_per_second": 325.106,
+      "eval_steps_per_second": 2.61,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 16141525436100.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.31543852233103564,
+    "learning_rate": 0.0001016348195065519,
+    "num_train_epochs": 8,
+    "temperature": 11
+  }
+}

run-3/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da24167155160cf44b77d966c48df19607917d58321b47eb6a2d952430ef1c52
+size 5048