Training in progress, epoch 1

logs/events.out.tfevents.1701811186.joseph_legion.26688.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880ae53e8649e0e3f6c3ae5d0b3f60d2235f6bcad0358eb8250bd643beb4f47d
+size 5198

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a8fa5ab43e0a2b256a48cfd9517e704a62a7066ffc24514bbd17297a3e9504
+oid sha256:374b7d14a98c5913003954a334fa0e7df1d81aec0510cff0431945c9fbc2a6cc
 size 17550344

run-7/checkpoint-1915/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-7/checkpoint-1915/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374b7d14a98c5913003954a334fa0e7df1d81aec0510cff0431945c9fbc2a6cc
+size 17550344

run-7/checkpoint-1915/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03835a80ea8eb1a045885271f2d192fb080b56c6d3bea3aa44ffbcdf3cf2b889
+size 35125946

run-7/checkpoint-1915/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d22b75a83932e2e0b44b5715e3acb5415afb159891c1afee9c211ff6ee6840
+size 14308

run-7/checkpoint-1915/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f308dae67cdffa9c5153859a2c2e417d7ed3cd0fd06fda010ea06dcb353b5f9
+size 1064

run-7/checkpoint-1915/special_tokens_map.json

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

run-7/checkpoint-1915/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-7/checkpoint-1915/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.8555758683729433,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-7\\checkpoint-1915",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1915,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.4996,
+      "step": 1915
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.49375271797180176,
+      "eval_runtime": 28.2962,
+      "eval_samples_per_second": 77.325,
+      "eval_steps_per_second": 0.636,
+      "step": 1915
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1915,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 780029363136.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.843663642501477e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 20
+  }
+}

run-7/checkpoint-1915/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1dd75692959a6df5864a591353c7a55b2be7dfc214a3d4dfcc6228265a2704
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb1f8919b0fbf98cbd747452fa46cf77b5ca271a6186ffe6c612006dc9a186a
+oid sha256:3d1dd75692959a6df5864a591353c7a55b2be7dfc214a3d4dfcc6228265a2704
 size 4664