Training in progress, epoch 2

logs/events.out.tfevents.1701810876.joseph_legion.26688.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37fb7d0947ec4ed16d73a01fca4b193d5d9d7b4dfc30f1287f10fabc8697203
-size 4846
+oid sha256:6d0b0ce5de953b5bff5b9ed83143fd0106ab793bfaed2d89f86b0b850e043d56
+size 5680

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d929338da9363602935c4d25de2578d3631fa690c3c714dff40ccde49f9f99a9
+oid sha256:78e52206f628d4473e4d2a54670bdb382f9cd4cb3ec4addc845399c614ca9975
 size 17550344

run-5/checkpoint-958/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-5/checkpoint-958/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e52206f628d4473e4d2a54670bdb382f9cd4cb3ec4addc845399c614ca9975
+size 17550344

run-5/checkpoint-958/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:491f61e175b4ca0e396b0c5f368f5bfceb3cf4e0388c6401ea2e0d2b4d7685ce
+size 35125946

run-5/checkpoint-958/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:760305488f0c5f96bf6a4938d8a030381ed36fcabd079ffbb7eae8df9e6b968a
+size 14308

run-5/checkpoint-958/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0040b74a6931dc6a97976ad93d0e4afd61fb362eeabc11b8d866c20f60db54a5
+size 1064

run-5/checkpoint-958/special_tokens_map.json

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

run-5/checkpoint-958/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-5/checkpoint-958/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8555758683729433,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-5\\checkpoint-479",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 958,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.596085086530314e-07,
+      "loss": 0.6358,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.5956268310546875,
+      "eval_runtime": 26.0018,
+      "eval_samples_per_second": 84.148,
+      "eval_steps_per_second": 0.692,
+      "step": 479
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.5852,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.5728661417961121,
+      "eval_runtime": 27.1814,
+      "eval_samples_per_second": 80.496,
+      "eval_steps_per_second": 0.662,
+      "step": 958
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 958,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 2552471240256.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1192170173060629e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 33
+  }
+}

run-5/checkpoint-958/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a585f476f2d08a1adbceb9b1a22db001bf2a46daaa81cc34c63bc4b3d4dab2bc
+size 4664