Training in progress, epoch 2

logs/events.out.tfevents.1709460206.49ae8f4e8e7b.1647.25

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4d1b0f2ddfe581b4ed0e95f3387fbce80265ff11ebfe49966fc82bbc2ec3d9
-size 5180
+oid sha256:9a56544a23b6494e4ef54a2fe57bf6ba4091e1703bb942a9f19d16677e3eea72
+size 5714

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8f374cf06af1becedf5e2131acdc5bacc84757b1430d749e6be53f5fa38836b
+oid sha256:67ce49a130b17131a9bcc1cda679c6d84bd259fd1053e2479e0c548721d66eee
 size 17549312

run-24/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-24/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce49a130b17131a9bcc1cda679c6d84bd259fd1053e2479e0c548721d66eee
+size 17549312

run-24/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608bc185c1586fbd62cba57f61793f58a6e23b9bc17e0a6e057962e4ee0785c1
+size 35123898

run-24/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b242219066ee20691234b53c3eb9b8da10cd3bc00e333f52e39e5b4d6628c98
+size 14308

run-24/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685cd7a35ae8e0ad9d11eda2d6975042756f758ae9b33682016e336bcc53f842
+size 1064

run-24/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-24/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-24/checkpoint-1054/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.8337155963302753,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-527",
+  "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,
+      "grad_norm": 17.628143310546875,
+      "learning_rate": 0.00018567149458255904,
+      "loss": 1.3968,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8337155963302753,
+      "eval_loss": 1.3282397985458374,
+      "eval_runtime": 2.8214,
+      "eval_samples_per_second": 309.061,
+      "eval_steps_per_second": 2.481,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.100229263305664,
+      "learning_rate": 0.00013925362093691925,
+      "loss": 0.6522,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 1.401127576828003,
+      "eval_runtime": 2.8077,
+      "eval_samples_per_second": 310.572,
+      "eval_steps_per_second": 2.493,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 16141525436100.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4205009910693592,
+    "learning_rate": 0.00023208936822819877,
+    "num_train_epochs": 5,
+    "temperature": 21
+  }
+}

run-24/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22b334783d23b2099fc16003e87298409a4c3cae8698d8fc8241196e2543e45
+size 4984