Training in progress, epoch 2

logs/events.out.tfevents.1701812152.joseph_legion.26688.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda85fe2c1f681957580c8d586970bfe02b87873b02f9216fd4b57b442c3f460
-size 4845
+oid sha256:4e86e60d42ed09e6b0a7bc8636c37756750e1615c46afe73b10789c2cfb13b0c
+size 5679

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d3593fd712cb995b9dbdaa7a9045c7625b44e95b346eb8123715f3a4eab5a9e
+oid sha256:25a0a87f5fffdc117759bfd1d363b224ca11398088363131fb2d7fa247dd3d84
 size 17550344

run-15/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-15/checkpoint-958/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a0a87f5fffdc117759bfd1d363b224ca11398088363131fb2d7fa247dd3d84
+size 17550344

run-15/checkpoint-958/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10eb78b22e5dfa59e0d690b0b6951b89c9eb470ee524574d8cc9c165c1ef64ae
+size 35125946

run-15/checkpoint-958/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d5b5538e0d753b6747399c6d630980848419d369b2da6879666372d505df8c0
+size 14308

run-15/checkpoint-958/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db149bdefd8a878af2b1764db7d90497938af7f0404d1f343328ba53b8eeeae
+size 1064

run-15/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-15/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-15/checkpoint-958/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8729433272394881,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-15\\checkpoint-958",
+  "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": 4.773651812593411e-05,
+      "loss": 0.4786,
+      "step": 479
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8638025594149908,
+      "eval_loss": 0.47031012177467346,
+      "eval_runtime": 24.7024,
+      "eval_samples_per_second": 88.574,
+      "eval_steps_per_second": 0.729,
+      "step": 479
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.4545,
+      "step": 958
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8729433272394881,
+      "eval_loss": 0.4671659767627716,
+      "eval_runtime": 27.2898,
+      "eval_samples_per_second": 80.176,
+      "eval_steps_per_second": 0.66,
+      "step": 958
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 958,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 2560168441056.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.547303625186822e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 24
+  }
+}

run-15/checkpoint-958/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6839d576a24769c173d03f70d09e23a2fbf5233156d55a7a71bfb77295fc6c
+size 4664