Training in progress, epoch 2

logs/events.out.tfevents.1701815144.joseph_legion.26688.32

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d23eaed282673aacbe7cfca07716bb7e34716378f35888c9c096537274c722
-size 4844
+oid sha256:d577d20a12b0b341731b3fa35fd4b8f737db2648d393e1e441d996616a9f70af
+size 5678

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1ca3b10c3ff12add8455ed9035984e80c3520213d014746fcd751446a64eaa
+oid sha256:6b632fa2cd89a01e0a003702141d88eae4aaa752c00241337563724ae5b5d9ff
 size 17550344

run-31/checkpoint-3830/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-31/checkpoint-3830/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b632fa2cd89a01e0a003702141d88eae4aaa752c00241337563724ae5b5d9ff
+size 17550344

run-31/checkpoint-3830/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a5fa4f8dc461cb8e036484090f2a256a4c3cb4c405a65aeaff264460167cf0
+size 35125946

run-31/checkpoint-3830/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306b0598b99034fdf58d9ce6b5993c14d67b6fa3407f979ef31a485863fd3d0c
+size 14308

run-31/checkpoint-3830/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6daaf734a7d078d54a86797792733e57e843ed0fa6599649cf083aabae8acb
+size 1064

run-31/checkpoint-3830/special_tokens_map.json

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

run-31/checkpoint-3830/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-31/checkpoint-3830/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8715722120658135,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-31\\checkpoint-3830",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3830,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.9016795034974554e-05,
+      "loss": 0.4746,
+      "step": 1915
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8647166361974405,
+      "eval_loss": 0.4731423556804657,
+      "eval_runtime": 30.4202,
+      "eval_samples_per_second": 71.926,
+      "eval_steps_per_second": 0.592,
+      "step": 1915
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.4495,
+      "step": 3830
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8715722120658135,
+      "eval_loss": 0.47356462478637695,
+      "eval_runtime": 28.5683,
+      "eval_samples_per_second": 76.588,
+      "eval_steps_per_second": 0.63,
+      "step": 3830
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3830,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1561339937760.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.803359006994911e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 24
+  }
+}

run-31/checkpoint-3830/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601d4e8a08418a1c9e63b4c0c409a5e8d30904372ce8c4b7738accc268239a13
+size 4664