Training in progress, epoch 5

logs/events.out.tfevents.1699910730.b18f42e49ba4.3021.23

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0153df28c9ca57fc709b56f590c7c58b4a49c4365e79c5cfcdff4f26dd0ac9b1
-size 6213
+oid sha256:00593bab0b01087120a54465222cb0c85ce0e447ef8ddce00d56469f138caee1
+size 6693

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:655aa086901645245a8ed242512a2593b20b64be82691ac025aec8c54268ca82
+oid sha256:d4e89a23c26f51cd4e2d208f2320fc06e2d28bcb3c5f48f3768a573e02041ca0
 size 17549312

run-22/checkpoint-2635/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-22/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e89a23c26f51cd4e2d208f2320fc06e2d28bcb3c5f48f3768a573e02041ca0
+size 17549312

run-22/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f09da30e3181298edc7be80697f65d47df461941edefbdfc57486b9b95b8cada
+size 35123898

run-22/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6495712c0480e33150a9e840df89cfbd7359c197e00213528d6031351fe6bf56
+size 14308

run-22/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63348f1101162e10dbc2fbe61eb0e71e7c7cfd8c09b3ad0ea8c0ad7998b21d9b
+size 1064

run-22/checkpoint-2635/special_tokens_map.json

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

run-22/checkpoint-2635/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-22/checkpoint-2635/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 0.8268348623853211,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-1054",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2635,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0002438746383718142,
+      "loss": 1.5658,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 1.591517686843872,
+      "eval_runtime": 0.8322,
+      "eval_samples_per_second": 1047.812,
+      "eval_steps_per_second": 8.411,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00020324171569652296,
+      "loss": 0.7138,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 1.745030403137207,
+      "eval_runtime": 0.8442,
+      "eval_samples_per_second": 1032.901,
+      "eval_steps_per_second": 8.292,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00016260879302123178,
+      "loss": 0.4995,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8038990825688074,
+      "eval_loss": 2.1336724758148193,
+      "eval_runtime": 0.9178,
+      "eval_samples_per_second": 950.09,
+      "eval_steps_per_second": 7.627,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00012197587034594056,
+      "loss": 0.3901,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 1.7912118434906006,
+      "eval_runtime": 0.8439,
+      "eval_samples_per_second": 1033.248,
+      "eval_steps_per_second": 8.294,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 8.134294767064937e-05,
+      "loss": 0.3134,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8165137614678899,
+      "eval_loss": 1.9351019859313965,
+      "eval_runtime": 0.8444,
+      "eval_samples_per_second": 1032.647,
+      "eval_steps_per_second": 8.29,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3689,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 40418309418180.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.24619262739255549,
+    "learning_rate": 0.0002844304587270384,
+    "num_train_epochs": 7,
+    "temperature": 30
+  }
+}

run-22/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:514dd10b819ed437f80437be6fb00aa001e9247d6260b3e65ea536a793f87a5d
+size 4600