Training in progress, epoch 2

logs/events.out.tfevents.1700095978.0ef7b67c0c07.8576.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eee106136eb5466f78acab3e448624d0eed4c39e55761ebb445e01268305c81
-size 4775
+oid sha256:b911cbb28d3511ac6711102c19b0e62fd9e9e03a5a4817c20ec00d8d9874ea0d
+size 5255

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564b0d3d3bc49e0f26406d5c354b5e2e45d23f2841875d6fd1d432f83c6c5353
+oid sha256:7e128015dfbfb176427716c0541dbc468b06e6421a1bf76c0943eb0b50d1f194
 size 17549312

run-0/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-0/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e128015dfbfb176427716c0541dbc468b06e6421a1bf76c0943eb0b50d1f194
+size 17549312

run-0/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f7adeabde2a9a98613ee84338300d1479cb69a5c5ea04808a777ffb75685c9
+size 35123898

run-0/checkpoint-1054/rng_state.pth

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

run-0/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3654833f7b4a1dcc077332c6c06be07de5c0901075ce14ab4b3177e48184fcaa
+size 1064

run-0/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-0/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-0/checkpoint-1054/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8222477064220184,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/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": 0.00014790853024760983,
+      "loss": 1.5038,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 1.3256508111953735,
+      "eval_runtime": 2.6523,
+      "eval_samples_per_second": 328.767,
+      "eval_steps_per_second": 2.639,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001314742491089865,
+      "loss": 0.7133,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.4129838943481445,
+      "eval_runtime": 2.6313,
+      "eval_samples_per_second": 331.391,
+      "eval_steps_per_second": 2.66,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 16194449161860.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4020095097837325,
+    "learning_rate": 0.00016434281138623312,
+    "num_train_epochs": 10,
+    "temperature": 12
+  }
+}

run-0/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65178f463aeaf39a13d8ba13438e7d131c26a92476a5b5cf1d59944b12ddd026
+size 4664