Training in progress, epoch 1

logs/events.out.tfevents.1713588697.1376c752d37a.9760.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e945c0f2fdb66ae38fc8789d81e90578ca2ef4074b904e924ef3d456f1f1da54
+size 5481

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404de65cdd7691f306d50180539717cc57c18a9bac9f576469a43018145f12bd
+oid sha256:1670957d1398e57e59448081f74fcbfe9a0bc7369bd016fd3e24d7d964099d00
 size 17549312

run-20/checkpoint-214/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-20/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1670957d1398e57e59448081f74fcbfe9a0bc7369bd016fd3e24d7d964099d00
+size 17549312

run-20/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16081d92b9f3a7c672f60b735bc277175a0a3d74235c5c0ac88d1abd318020b
+size 35123898

run-20/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
+size 14308

run-20/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4c1098a83cdeb1a533a6f9305a2b731fc4079ffe8d0f27a87c9ca521dab973
+size 1064

run-20/checkpoint-214/special_tokens_map.json

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

run-20/checkpoint-214/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-20/checkpoint-214/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.6848271821909784,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-214",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.5011236667633057,
+      "learning_rate": 0.00029874954647137283,
+      "loss": 0.4553,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6848271821909784,
+      "eval_f1": 0.1567398119122257,
+      "eval_loss": 0.4299508333206177,
+      "eval_mcc": 0.17036819686661997,
+      "eval_precision": 0.7246376811594203,
+      "eval_recall": 0.08787346221441125,
+      "eval_runtime": 3.1578,
+      "eval_samples_per_second": 540.559,
+      "eval_steps_per_second": 17.1,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 524775664440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7240883100721838,
+    "learning_rate": 0.000348541137549935,
+    "num_train_epochs": 7,
+    "temperature": 12
+  }
+}

run-20/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:662fbb84d6147f48949a6a39f3cf513cb104e69e1490a40da8e05519999e4ddb
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79259e8667f6126db030c79e3d1cae036f86d375a1728e30f86348e33184df86
+oid sha256:662fbb84d6147f48949a6a39f3cf513cb104e69e1490a40da8e05519999e4ddb
 size 5048