Training in progress, epoch 2

logs/events.out.tfevents.1709751609.d65e8524b0f6.5185.30

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cdde1c4d226c4bafe0b0d770467c5b0030d944445a11713ebfc832a77fbffa3
-size 5313
+oid sha256:a5811b07f071f9b03c2db5bf9663868aa6e5eb38491833582d12b128dfa1ce0c
+size 5983

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5d1c3dba9b8eccb675a72e964e5bed1e51b824d26030700c2aa6012d880cd09
+oid sha256:ce241373183918d6ad27e7af40ca5934a857c49664e85bbdb7eacf2f106f064f
 size 17549312

run-30/checkpoint-112/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-30/checkpoint-112/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce241373183918d6ad27e7af40ca5934a857c49664e85bbdb7eacf2f106f064f
+size 17549312

run-30/checkpoint-112/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e546cc56aebc40e9fe0efe9b662863635a0c02a3cb3b589400547bae6a18036
+size 35122746

run-30/checkpoint-112/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080ae48d8ecc5ab8ff9230f17d81c774b595aaa4069446590c2aad241d37b276
+size 14054

run-30/checkpoint-112/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bb8c738e00d214bb72cbf8bb02a3a61494bbdbe1bef630fb5bb2ddf9b2c3b1
+size 1064

run-30/checkpoint-112/special_tokens_map.json

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

run-30/checkpoint-112/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-30/checkpoint-112/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.8062622309197651,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-30/checkpoint-112",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.488581895828247,
+      "learning_rate": 0.00035374495201026426,
+      "loss": 0.5645,
+      "step": 56
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7847358121330724,
+      "eval_f1": 0.8049645390070922,
+      "eval_loss": 0.4679928421974182,
+      "eval_precision": 0.7358184764991896,
+      "eval_recall": 0.8884540117416829,
+      "eval_runtime": 28.8427,
+      "eval_samples_per_second": 35.434,
+      "eval_steps_per_second": 1.109,
+      "step": 56
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.869302749633789,
+      "learning_rate": 0.00029478746000855357,
+      "loss": 0.4598,
+      "step": 112
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8062622309197651,
+      "eval_f1": 0.8047337278106508,
+      "eval_loss": 0.4556478261947632,
+      "eval_precision": 0.8111332007952287,
+      "eval_recall": 0.7984344422700587,
+      "eval_runtime": 28.6037,
+      "eval_samples_per_second": 35.73,
+      "eval_steps_per_second": 1.119,
+      "step": 112
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 392,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 55,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9318712276013821,
+    "learning_rate": 0.000412702444011975,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 55,
+    "temperature": 27
+  }
+}

run-30/checkpoint-112/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c31c0ff5ab5419b10c4b045c98d73f4009f0b63f2ceac81514144c885ecd65
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89efecad9561cc854d69fd70f328f321f6dd5b5b818174094a406c3a368090ff
+oid sha256:87c31c0ff5ab5419b10c4b045c98d73f4009f0b63f2ceac81514144c885ecd65
 size 4920