Training in progress, epoch 2

logs/events.out.tfevents.1713588236.1376c752d37a.9760.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fcf86b97c94672f7f394431a0bf6dd87262bca74991e0e86b325cdaa8be15ad
-size 5482
+oid sha256:c92d3f5f9f448b2eef640e18d8abf4cd35d15a284e72b7fb605e0d981b8a6789
+size 6212

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f755ff6559590f70dd60b4ffbb2384922811a13ff87015f5c38d21ef3718aa32
+oid sha256:635da64a58870edd4e4b471c6ef5fd3150a3da6a7f079ad028658ac5ab8d2ade
 size 17549312

run-14/checkpoint-428/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-14/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635da64a58870edd4e4b471c6ef5fd3150a3da6a7f079ad028658ac5ab8d2ade
+size 17549312

run-14/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a69bb1b9d1a3db9dacd06912af0b3b06b68a447855024a1586e35c26605f232
+size 35123898

run-14/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0c3b463a8fb08b95f5c77916114776bad3339b633df010e4ffd9b5ddabab1e
+size 14308

run-14/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c004c32ffe86684a14ee496a850848ee6c6c9ef42f9ac657cce693ed513004
+size 1064

run-14/checkpoint-428/special_tokens_map.json

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

run-14/checkpoint-428/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-14/checkpoint-428/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6994727592267135,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-428",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.930738925933838,
+      "learning_rate": 5.414014250397772e-05,
+      "loss": 0.6091,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6865846514352666,
+      "eval_f1": 0.37572928821470253,
+      "eval_loss": 0.564587414264679,
+      "eval_mcc": 0.2156910734882714,
+      "eval_precision": 0.5590277777777778,
+      "eval_recall": 0.28295254833040423,
+      "eval_runtime": 3.1483,
+      "eval_samples_per_second": 542.201,
+      "eval_steps_per_second": 17.152,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.107285499572754,
+      "learning_rate": 4.64058364319809e-05,
+      "loss": 0.5591,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6994727592267135,
+      "eval_f1": 0.5535248041775457,
+      "eval_loss": 0.5493428111076355,
+      "eval_mcc": 0.3271000794140795,
+      "eval_precision": 0.5482758620689655,
+      "eval_recall": 0.5588752196836555,
+      "eval_runtime": 3.1416,
+      "eval_samples_per_second": 543.358,
+      "eval_steps_per_second": 17.189,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1712,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 1049551328880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9740992948842065,
+    "learning_rate": 6.187444857597454e-05,
+    "num_train_epochs": 8,
+    "temperature": 3
+  }
+}

run-14/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7957c24fcc5f109d1242da58460e07cf4b6b3343538fd03977a240662bdcface
+size 5048