Training in progress, epoch 2

logs/events.out.tfevents.1700284300.bdba95a6283e.570.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab7a1c81614d3f2a9c26261dd20dc889145308adf06620b3f9953d3c5e5ed68
-size 4809
+oid sha256:74461ffff0bafda97b49bb6f62ea3ffa629c742dca66dfcdae16afed1f796a99
+size 5289

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4179ffda3d0d979a96ef2f1ec97eb5b11debae9610d1ee38c1e4eb18502b1a
+oid sha256:8c278a628352fb8bf5850dde4f4b4d6cdb6dc073b5418cf5b21ca7cc9dfca83c
 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": "4.35.2",
+  "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 sha256:8c278a628352fb8bf5850dde4f4b4d6cdb6dc073b5418cf5b21ca7cc9dfca83c
+size 17549312

run-3/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baed069e5522145e4c975f16e355d574cdafd6f7fc30631e45dbe815558a59f3
+size 35123898

run-3/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257145d19710cbf39344544002ce35377faa97e289b8c6f1104c9033e98d4161
+size 14308

run-3/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ee6528448a9b065a12d758647638e6ccb4f1c6ebd50cc2ed64041bce3436d5
+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 +1,54 @@
+{
+  "best_metric": 0.8176605504587156,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/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,
+      "learning_rate": 0.00041526386683348685,
+      "loss": 0.4613,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.805045871559633,
+      "eval_loss": 0.6051546335220337,
+      "eval_runtime": 2.7198,
+      "eval_samples_per_second": 320.613,
+      "eval_steps_per_second": 2.574,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00031144790012511514,
+      "loss": 0.2397,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 0.7534372806549072,
+      "eval_runtime": 2.6979,
+      "eval_samples_per_second": 323.215,
+      "eval_steps_per_second": 2.595,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 16194449161860.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9238940809632088,
+    "learning_rate": 0.0005190798335418586,
+    "num_train_epochs": 5,
+    "temperature": 22
+  }
+}

run-3/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7347a6a4d2a64a7d635c666aa8a0b2a3bdfe634a3e64aa55460c04f9d49a1f45
+size 4664