Training in progress, epoch 2

logs/events.out.tfevents.1701811605.joseph_legion.26688.11

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e124d6415c8a882378afd298f8b9047968350bd57b50ec134d07c1e71eda3086
-size 4843
+oid sha256:4a2a4a9c9ce8a9d0a823724092ac8f3c1e76250be576eb9d3e3f638a2c623dd4
+size 5677

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eaa198a3c3532c43fa2ae8bbe880dce1c1d3d51fa929f704a16a635f6e1f47f
+oid sha256:43ea92fa3346dab6a028545c5aad19861bb1fce30a4ec1b8df8fd72631ba5548
 size 17550344

run-10/checkpoint-1916/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-10/checkpoint-1916/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ea92fa3346dab6a028545c5aad19861bb1fce30a4ec1b8df8fd72631ba5548
+size 17550344

run-10/checkpoint-1916/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f21c90ea57f7c164f6f3f36a574d1ee97b02c05ec69a17d13d44122973e22f
+size 35125946

run-10/checkpoint-1916/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348febaa4ad634d69e4d0cb87534904f9c66ee7cc71ee5b94788eba0566de8f8
+size 14244

run-10/checkpoint-1916/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca8cbc4c4b4648dccf1ae420904afdad9b37fd25a90d240654173e9b8033cb1
+size 1064

run-10/checkpoint-1916/special_tokens_map.json

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

run-10/checkpoint-1916/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-10/checkpoint-1916/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8729433272394881,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-10\\checkpoint-1916",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1916,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.959730561951787e-05,
+      "loss": 0.4733,
+      "step": 958
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8610603290676416,
+      "eval_loss": 0.47912609577178955,
+      "eval_runtime": 26.8567,
+      "eval_samples_per_second": 81.47,
+      "eval_steps_per_second": 0.67,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.449,
+      "step": 1916
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8729433272394881,
+      "eval_loss": 0.46745508909225464,
+      "eval_runtime": 27.5383,
+      "eval_samples_per_second": 79.453,
+      "eval_steps_per_second": 0.654,
+      "step": 1916
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1916,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1999712904096.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.919461123903574e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 1
+  }
+}

run-10/checkpoint-1916/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b02917711da760ae5e24809199aea8e5e2fece4505221ba531518da290aef349
+size 4664