Training in progress, epoch 2

logs/events.out.tfevents.1709743292.d65e8524b0f6.5185.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:974c8e28cd5a814e2e8b5c3a7ed42267703088960f88935171ac6d2eba21489e
-size 5315
+oid sha256:9a8215936550970f249d5858156ccc7d5b01e7457e30dae6e90af8a7b169e3cc
+size 5998

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbe2163fd46cf9e7cc5286f800c209705f03baf04ac0ebb445340b728688718
+oid sha256:c322dcb4b59626a920d30f5e070ff3482b649d4a14b4fbe008217caa06675be7
 size 17549312

run-8/checkpoint-132/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-8/checkpoint-132/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c322dcb4b59626a920d30f5e070ff3482b649d4a14b4fbe008217caa06675be7
+size 17549312

run-8/checkpoint-132/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a0875223b76b0bfe835fbcf826ef03b9b341974f4cb21e3157d878709d1f918
+size 35122746

run-8/checkpoint-132/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b205435899a5b4ffe689ce7b6dfda09a57322559e84119029c0ca8738631e6a5
+size 14054

run-8/checkpoint-132/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f33d564179cb26c3bf49e9f70a9c57b80938f807c4d4326d905ddd811a0683e
+size 1064

run-8/checkpoint-132/special_tokens_map.json

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

run-8/checkpoint-132/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-8/checkpoint-132/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.576320939334638,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-132",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 132,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.3361287117004395,
+      "learning_rate": 1.2926171014641113e-05,
+      "loss": 0.6798,
+      "step": 66
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5078277886497065,
+      "eval_f1": 0.16583747927031509,
+      "eval_loss": 0.6719066500663757,
+      "eval_precision": 0.5434782608695652,
+      "eval_recall": 0.09784735812133072,
+      "eval_runtime": 27.922,
+      "eval_samples_per_second": 36.602,
+      "eval_steps_per_second": 1.146,
+      "step": 66
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.002190589904785,
+      "learning_rate": 1.0771809178867594e-05,
+      "loss": 0.6711,
+      "step": 132
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.576320939334638,
+      "eval_f1": 0.412483039348711,
+      "eval_loss": 0.667403519153595,
+      "eval_precision": 0.672566371681416,
+      "eval_recall": 0.2974559686888454,
+      "eval_runtime": 28.4397,
+      "eval_samples_per_second": 35.936,
+      "eval_steps_per_second": 1.125,
+      "step": 132
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 462,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 47,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9637337898381267,
+    "learning_rate": 1.5080532850414631e-05,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 47,
+    "temperature": 3
+  }
+}

run-8/checkpoint-132/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b90b715629d1e5783934b5c99dd80382e6f66756c0da609362121ae001b883
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c39a4a57a6152c8ee182f392094f81926b25a2790f096406761336357b2e5950
+oid sha256:64b90b715629d1e5783934b5c99dd80382e6f66756c0da609362121ae001b883
 size 4920