Training in progress, epoch 2

logs/events.out.tfevents.1709748697.d65e8524b0f6.5185.21

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:367e3bfae5596776d752fe9bba4cf7d826229e29f56c5f4e6a4bd44d72bba494
-size 5315
+oid sha256:ef590dead44772f2ee831d4bc41d013aa2689aa54b55765ef13016a1f6685cd9
+size 5985

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a10116ea0c3979b32bb5bcc815845160ba872bf87131acc62d51c9b7003827a
+oid sha256:b78f73b8b1568f6b3be28d7d82825dcb0f7d62ce1ef82252a6f107043ff61424
 size 17549312

run-21/checkpoint-104/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-21/checkpoint-104/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78f73b8b1568f6b3be28d7d82825dcb0f7d62ce1ef82252a6f107043ff61424
+size 17549312

run-21/checkpoint-104/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d81800ccc0f4467c3350dbaeb1ba324e214aab1e00aa4634666b98ae8ec77ac
+size 35122746

run-21/checkpoint-104/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:079d0d6a3b1a86f8046efea5703ffb676a7484f8956ac89a79e8e73a28e86390
+size 14054

run-21/checkpoint-104/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:209b6503a931fab37bb05e74fa4d1e21975a2984a919d7e621a1fa688cf4a1ed
+size 1064

run-21/checkpoint-104/special_tokens_map.json

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

run-21/checkpoint-104/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-21/checkpoint-104/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.7504892367906066,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-104",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 104,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.939810276031494,
+      "learning_rate": 0.00013471680923458288,
+      "loss": 0.5033,
+      "step": 52
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7152641878669276,
+      "eval_f1": 0.712166172106825,
+      "eval_loss": 0.4479813575744629,
+      "eval_precision": 0.72,
+      "eval_recall": 0.7045009784735812,
+      "eval_runtime": 28.0693,
+      "eval_samples_per_second": 36.41,
+      "eval_steps_per_second": 1.14,
+      "step": 52
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.902515411376953,
+      "learning_rate": 8.981120615638859e-05,
+      "loss": 0.4475,
+      "step": 104
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7504892367906066,
+      "eval_f1": 0.7578347578347578,
+      "eval_loss": 0.42175495624542236,
+      "eval_precision": 0.7361623616236163,
+      "eval_recall": 0.7808219178082192,
+      "eval_runtime": 27.9965,
+      "eval_samples_per_second": 36.505,
+      "eval_steps_per_second": 1.143,
+      "step": 104
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 60,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7020704368642945,
+    "learning_rate": 0.00017962241231277718,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 60,
+    "temperature": 19
+  }
+}

run-21/checkpoint-104/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe829315cd1ce1b368ca5aa1539a6e655572843d060f6af981de772385e9701
+size 4920