Training in progress, epoch 2

logs/events.out.tfevents.1701812778.joseph_legion.26688.24

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3d0b411c9b5edc0393cd30de60502559a235bd765e8b3412bcbbb9b1e55e88c
-size 4835
+oid sha256:290005d80766b7ed6aa6322f49e950a681f91c2bd48ca315c71aeeda7663ae3f
+size 5669

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef4ba0709837bb91634c7e1f7235f721d1ce17a92a444a4478062b69911a259f
+oid sha256:807844ac062a21e5d3bf0017063adb33cea696fd6b2399e5fec97d7b1fb74dc3
 size 17550344

run-23/checkpoint-240/config.json

@@ -0,0 +1,38 @@
+{
+  "_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": "noHate",
+    "1": "hate",
+    "2": "idk/skip",
+    "3": "relation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "hate": "1",
+    "idk/skip": "2",
+    "noHate": "0",
+    "relation": "3"
+  },
+  "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-23/checkpoint-240/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807844ac062a21e5d3bf0017063adb33cea696fd6b2399e5fec97d7b1fb74dc3
+size 17550344

run-23/checkpoint-240/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adc467a298062527583e1d7e9443fff427a0960350a384275c38772827b9010d
+size 35125946

run-23/checkpoint-240/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f12e3fe829dac81abf3826de8315392623f8852d9e52ff70d9d71547e7aef99
+size 14244

run-23/checkpoint-240/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8694e8db1436cb344bcfec5b781a4cd5a3acd56dd5363aaff389f1cf6b4976
+size 1064

run-23/checkpoint-240/special_tokens_map.json

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

run-23/checkpoint-240/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-23/checkpoint-240/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8555758683729433,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-23\\checkpoint-120",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 240,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.438032668126527e-05,
+      "loss": 0.5043,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.4868743121623993,
+      "eval_runtime": 24.2025,
+      "eval_samples_per_second": 90.404,
+      "eval_steps_per_second": 0.744,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.4746,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.47973644733428955,
+      "eval_runtime": 24.0573,
+      "eval_samples_per_second": 90.95,
+      "eval_steps_per_second": 0.748,
+      "step": 240
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 240,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 4273326974208.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.876065336253054e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64,
+    "seed": 4
+  }
+}

run-23/checkpoint-240/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d12c4a71ad7e1d67c331139799b936012ee5e9b9a0bbe0802ead08b2f27a0e
+size 4664