Training in progress, epoch 2

logs/events.out.tfevents.1701755822.joseph_legion.10272.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f0f665121009a64c378af95dbeb3b7a64d83276d47fb127f031321d3b83cbc
-size 4775
+oid sha256:a36f570f7942581439ec63d6cf32d89fcc76a5b2d6625b01969a7164aaea1eb0
+size 5255

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f6c110fbb84cc7d7c7c259636e8a75f200c0067c45c38b1b5ff34d5e6eda8c1
+oid sha256:5df5144e754f7a58b976245da0545d19246a7ef9a10c3c407636847993ba0546
 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 sha256:5df5144e754f7a58b976245da0545d19246a7ef9a10c3c407636847993ba0546
+size 17549312

run-3/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96a07eefb61baf613153b65f3433a2d4f19547767b9d12e5fb007b541ef4a72
+size 35123898

run-3/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489216a25d2622ca3b315e4e88f8c885e691f9c5ad39ced5eb9e28b9922a940a
+size 14308

run-3/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8047a5cf9b470d4cc2b8e6c3589dd5ede207d2d106686a994537629b033b04ba
+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": 0.8291284403669725,
+  "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,
+      "learning_rate": 0.00011471098822404043,
+      "loss": 1.0348,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 0.9528604745864868,
+      "eval_runtime": 1.7841,
+      "eval_samples_per_second": 488.773,
+      "eval_steps_per_second": 3.924,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.603324116803032e-05,
+      "loss": 0.5427,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 0.9413569569587708,
+      "eval_runtime": 1.7948,
+      "eval_samples_per_second": 485.839,
+      "eval_steps_per_second": 3.9,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 16141525436100.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7068839484125146,
+    "learning_rate": 0.00014338873528005054,
+    "num_train_epochs": 5,
+    "temperature": 15
+  }
+}

run-3/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe67709d5eb30b28dd7eb636d81e8b8f85c61db2e94841ea11c7912a79ea510
+size 4664