Training in progress, epoch 2

logs/events.out.tfevents.1710450098.4cb0d5d7fb51.5918.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb2e755da146a3a5807917382a93ccbcb9b982534cb66d79e539f13cfe3c3ce
-size 5178
+oid sha256:1b4616708596dec45dcce35850205975e8d1c89f78c54eb5eb1208851804f163
+size 5712

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797fb608d01311d980f9ff200e68eb77fca8ad07f337148d391cb6ff59dacb3f
+oid sha256:9a9f5899de3a13fc33628c62536f81bcc454491bdf7c8dff370e0c1f67285da1
 size 17549312

run-4/checkpoint-594/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-4/checkpoint-594/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9f5899de3a13fc33628c62536f81bcc454491bdf7c8dff370e0c1f67285da1
+size 17549312

run-4/checkpoint-594/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f225cbcf4be011db2b36b3c5f7f4a441e936b4532a87e4873bb53ef3102373
+size 35122746

run-4/checkpoint-594/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6866d0dff400085edf68783c4718d94e08dcfa8f0d23f9d94ad3e230de2def
+size 14054

run-4/checkpoint-594/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d2dccd940bec011857c38259860d9eb722df804caef6710c785d20e0ebb647
+size 1064

run-4/checkpoint-594/special_tokens_map.json

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

run-4/checkpoint-594/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-4/checkpoint-594/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.500990099009901,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-297",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 594,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3486188650131226,
+      "learning_rate": 0.0008534021470265506,
+      "loss": 0.5548,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.500990099009901,
+      "eval_loss": 0.5633774399757385,
+      "eval_runtime": 55.4108,
+      "eval_samples_per_second": 9.114,
+      "eval_steps_per_second": 0.289,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8194136023521423,
+      "learning_rate": 0.0007467268786482318,
+      "loss": 0.5553,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.500990099009901,
+      "eval_loss": 0.5545336604118347,
+      "eval_runtime": 54.9924,
+      "eval_samples_per_second": 9.183,
+      "eval_steps_per_second": 0.291,
+      "step": 594
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2673,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 1555686566280.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7480049651920854,
+    "learning_rate": 0.0009600774154048695,
+    "num_train_epochs": 9,
+    "temperature": 2
+  }
+}

run-4/checkpoint-594/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9362332d8be73fdeb508a202d9b7c32cc7427a6a4b9b0d6128331394ce376267
+size 4984