Training in progress, epoch 2

logs/events.out.tfevents.1713437920.ec9626078864.14834.21

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca44b71382a7788149556d573c1a2bd5a4db505ec2d14c32d0fdca4c1d61d591
-size 5406
+oid sha256:81e666284c5e5efacfe21d0dcb8550a87ea1a3d402b984a52551acdea2731002
+size 6136

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:440e4e3d69ce39c36a7f0dacd7a850f3842602d50c6d9ccbe441a4dca564738e
+oid sha256:35c8123f3383f26fa739512a334974cbb23bcfa0a390237f5773f25a5993c260
 size 17549312

run-20/checkpoint-1290/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": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-20/checkpoint-1290/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c8123f3383f26fa739512a334974cbb23bcfa0a390237f5773f25a5993c260
+size 17549312

run-20/checkpoint-1290/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e04dba8e4c9c8946299f665d263cf76389974631cbf10d53edba55f85dd428
+size 35123898

run-20/checkpoint-1290/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7f2a5e16989d9df1a9f119f3a022ead0c31636524de5ea431eca109ab65358
+size 14308

run-20/checkpoint-1290/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc8c308436e6042485b177cd96685dd5bb83860aa6f73c64b451109d7de7903a
+size 1064

run-20/checkpoint-1290/special_tokens_map.json

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

run-20/checkpoint-1290/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-20/checkpoint-1290/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.8964715005816207,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-1290",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1290,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6259269714355469,
+      "learning_rate": 0.0003431069228198171,
+      "loss": 0.3055,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8889104303993796,
+      "eval_f1": 0.19409282700421943,
+      "eval_loss": 0.2940736413002014,
+      "eval_mcc": 0.20172457395808635,
+      "eval_precision": 0.4859154929577465,
+      "eval_recall": 0.12126537785588752,
+      "eval_runtime": 9.9362,
+      "eval_samples_per_second": 519.111,
+      "eval_steps_per_second": 16.304,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.638690710067749,
+      "learning_rate": 0.00028592243568318097,
+      "loss": 0.2894,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8964715005816207,
+      "eval_f1": 0.18844984802431614,
+      "eval_loss": 0.2831971049308777,
+      "eval_mcc": 0.24798827118495087,
+      "eval_precision": 0.6966292134831461,
+      "eval_recall": 0.10896309314586995,
+      "eval_runtime": 9.9132,
+      "eval_samples_per_second": 520.316,
+      "eval_steps_per_second": 16.342,
+      "step": 1290
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4515,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 3173885065200.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8743805278290786,
+    "learning_rate": 0.0004002914099564533,
+    "num_train_epochs": 7,
+    "temperature": 27
+  }
+}

run-20/checkpoint-1290/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe36ec58db211b259b67da56dd68bab1173e0379eb4df2b16394348319aa391
+size 4984