Training in progress, epoch 4

logs/events.out.tfevents.1701756498.joseph_legion.10272.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83bfc1163609b3ac6542ab2cd040eeb164b9823b68016de059f4630e8d5e9b1
-size 5734
+oid sha256:be5507338f5c260068a103e54315aa4080d47a8a6b012a879dd61b81fcce6bdc
+size 6214

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa7c7b3bf5a3d164ed72c0fb3e270b4df6ac693c2f7c264a2d521bf47538b9c
+oid sha256:932e557dea2096a222c0702b836fce6c8048b6ea4e193bf471be3620e49ffb37
 size 17549312

run-4/checkpoint-2108/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-4/checkpoint-2108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932e557dea2096a222c0702b836fce6c8048b6ea4e193bf471be3620e49ffb37
+size 17549312

run-4/checkpoint-2108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7aad043494776b85c992eed7fcc061d2ff2c44e4a4fb2b4874d740e25871e9b
+size 35123898

run-4/checkpoint-2108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a020c8677f8fadfc307a6b0f0852435c8b675caad3b164c3943e9e61d914105
+size 14308

run-4/checkpoint-2108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dda4ab56467e155373084c3c069fb9b273dde9914136e02aca5a3fbbed0a416
+size 1064

run-4/checkpoint-2108/special_tokens_map.json

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

run-4/checkpoint-2108/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-4/checkpoint-2108/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.8153669724770642,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-4\\checkpoint-2108",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0007279643676825285,
+      "loss": 0.7513,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8027522935779816,
+      "eval_loss": 1.170225977897644,
+      "eval_runtime": 1.6351,
+      "eval_samples_per_second": 533.298,
+      "eval_steps_per_second": 4.281,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0006066369730687738,
+      "loss": 0.3531,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8073394495412844,
+      "eval_loss": 1.2287049293518066,
+      "eval_runtime": 1.6382,
+      "eval_samples_per_second": 532.308,
+      "eval_steps_per_second": 4.273,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00048530957845501903,
+      "loss": 0.2311,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.801605504587156,
+      "eval_loss": 1.2833977937698364,
+      "eval_runtime": 1.6336,
+      "eval_samples_per_second": 533.802,
+      "eval_steps_per_second": 4.285,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00036398218384126426,
+      "loss": 0.1731,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 1.3028004169464111,
+      "eval_runtime": 1.6323,
+      "eval_samples_per_second": 534.225,
+      "eval_steps_per_second": 4.288,
+      "step": 2108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3689,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 32351505805740.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7163008839410834,
+    "learning_rate": 0.0008492917622962833,
+    "num_train_epochs": 7,
+    "temperature": 30
+  }
+}

run-4/checkpoint-2108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52591f5d5a3100d6426c6ce052a4bb3e4ef93d3bc30c7e439e88ae3e16fc53de
+size 4664