Training in progress, epoch 2

logs/events.out.tfevents.1701752681.joseph_legion.10272.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3045ad86a35de0db0e0f5a5b0e337b47ff80523e6e2da26812081990345bc8d5
-size 4775
+oid sha256:812e92dfd17c640c73bf7aef37ac0bbbfeb9eba865feff202e773377953b9e4b
+size 5255

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8045071fd7ce775807243eaa915fc60a3be554095a0cfa3cda77059577a9f73
+oid sha256:1887f4d12f6b3bfa197a8a3a39c850c7b780d5afade88594e19d48e273c54e51
 size 17549312

run-0/checkpoint-1054/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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1887f4d12f6b3bfa197a8a3a39c850c7b780d5afade88594e19d48e273c54e51
+size 17549312

run-0/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a6ade4397ebfd621a2f9e6e8df8575357afac39ecc3c937972312cbf878796
+size 35123898

run-0/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489216a25d2622ca3b315e4e88f8c885e691f9c5ad39ced5eb9e28b9922a940a
+size 14308

run-0/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9af2bd3fb036e963782dddee25adc69fc0ebe3ebe58b6af51ad10c1e2930b8
+size 1064

run-0/checkpoint-1054/special_tokens_map.json

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

run-0/checkpoint-1054/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-0/checkpoint-1054/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8096330275229358,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-0\\checkpoint-1054",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1054,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0006568555243553003,
+      "loss": 0.9823,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.3724825382232666,
+      "eval_runtime": 1.7972,
+      "eval_samples_per_second": 485.194,
+      "eval_steps_per_second": 3.895,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0005838715772047113,
+      "loss": 0.4476,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 1.3287416696548462,
+      "eval_runtime": 1.7495,
+      "eval_samples_per_second": 498.417,
+      "eval_steps_per_second": 4.001,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 16141525436100.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5351224538156584,
+    "learning_rate": 0.0007298394715058892,
+    "num_train_epochs": 10,
+    "temperature": 24
+  }
+}

run-0/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8a46880b57d8b0b9e418b052abbb3948b438121f71f7c4ea0a153d96e30889
+size 4664