Training in progress, epoch 1

config.json

@@ -9,14 +9,18 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 128,
   "id2label": {
-    "0": "negative",
-    "1": "positive"
+    "0": "noHate",
+    "1": "hate",
+    "2": "idk/skip",
+    "3": "relation"
   },
   "initializer_range": 0.02,
   "intermediate_size": 512,
   "label2id": {
-    "negative": "0",
-    "positive": "1"
+    "hate": "1",
+    "idk/skip": "2",
+    "noHate": "0",
+    "relation": "3"
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

logs/events.out.tfevents.1701760669.joseph_legion.10272.19

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eacea7a19fcc2631e457b3cf03b4ab72e98d56e1573110a93189a5de9bcbedac
-size 7655
+oid sha256:33be438e57fdbd5fbbe2ec8a310b8a128ebe97e4b971a73d5d795f0ef6e82025
+size 8135

logs/events.out.tfevents.1701808154.joseph_legion.26688.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24db62f399ee6ec75a5d437eb51049ad15af0e6f041c31797eb0d449117961b
+size 4821

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ed9c78ec1f0e088f447238bfad612262522e2912abe0a54c53e99e2bd60cfd4
-size 17549312
+oid sha256:1f18e0f727a059c290944ba4ae49479ff90d9c94ee33eaaa9a7c51eb4ab502db
+size 17550344

run-18/checkpoint-4216/config.json

@@ -0,0 +1,34 @@
+{
+  "_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": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "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-18/checkpoint-4216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ea2f5352818f198209fc2ccbd978b7ea40a9340868101fb8ab8b66c64fc903
+size 17549312

run-18/checkpoint-4216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c2ce957bf226bcb88890ea6d010ede962d627603e300a65b447b1c1a514d7e
+size 35123898

run-18/checkpoint-4216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12de8190467594bcda6db6baf5e47b872afce5bc861e0eae6823ccbf8ac69b21
+size 14308

run-18/checkpoint-4216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4efe300efde79a99e971ad60ddf9a3c889d74b3f89ff1487e0304ed948c26e76
+size 1064

run-18/checkpoint-4216/special_tokens_map.json

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

run-18/checkpoint-4216/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-18/checkpoint-4216/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.8325688073394495,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-18\\checkpoint-1054",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 4216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00011463680857374876,
+      "loss": 1.2587,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.819954128440367,
+      "eval_loss": 1.0965343713760376,
+      "eval_runtime": 1.7615,
+      "eval_samples_per_second": 495.026,
+      "eval_steps_per_second": 3.974,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00010030720750203018,
+      "loss": 0.6372,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8325688073394495,
+      "eval_loss": 1.0634759664535522,
+      "eval_runtime": 1.8008,
+      "eval_samples_per_second": 484.238,
+      "eval_steps_per_second": 3.887,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.597760643031157e-05,
+      "loss": 0.481,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 1.1469666957855225,
+      "eval_runtime": 1.806,
+      "eval_samples_per_second": 482.838,
+      "eval_steps_per_second": 3.876,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.164800535859298e-05,
+      "loss": 0.3938,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 1.240983009338379,
+      "eval_runtime": 1.7946,
+      "eval_samples_per_second": 485.909,
+      "eval_steps_per_second": 3.901,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5.731840428687438e-05,
+      "loss": 0.3439,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 1.2216026782989502,
+      "eval_runtime": 1.7815,
+      "eval_samples_per_second": 489.477,
+      "eval_steps_per_second": 3.929,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.2988803215155787e-05,
+      "loss": 0.3056,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8279816513761468,
+      "eval_loss": 1.2263576984405518,
+      "eval_runtime": 1.7901,
+      "eval_samples_per_second": 487.134,
+      "eval_steps_per_second": 3.91,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.865920214343719e-05,
+      "loss": 0.2772,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 1.2873445749282837,
+      "eval_runtime": 1.8403,
+      "eval_samples_per_second": 473.833,
+      "eval_steps_per_second": 3.804,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.4329601071718595e-05,
+      "loss": 0.2594,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 1.2680649757385254,
+      "eval_runtime": 1.8481,
+      "eval_samples_per_second": 471.828,
+      "eval_steps_per_second": 3.788,
+      "step": 4216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 64695033846180.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.612333452003034,
+    "learning_rate": 0.00012896640964546737,
+    "num_train_epochs": 9,
+    "temperature": 21
+  }
+}

run-18/checkpoint-4216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11ae7f69a6836e22ab7ce08bf09b6029ed79c5f0a056488527f9d7fd818e4b8
+size 4664

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d11ae7f69a6836e22ab7ce08bf09b6029ed79c5f0a056488527f9d7fd818e4b8
+oid sha256:ebef841f41057cfd2c17275da05bf4137fc9fb9d87a24c5f6bcb0a0491c66452
 size 4664