Training in progress, epoch 2

logs/events.out.tfevents.1701815378.joseph_legion.26688.33

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0995559bb00bcf8ca5cd180040e013abb113737470afb30367980bd5198a7c82
-size 4845
+oid sha256:f977068295bc400c27a4e2c2e73758e2cd0252509bc6b2613e2f6868272ce583
+size 5679

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b50e7fa5e5363789b0a79450f14a753965c612fdfc146127d88e988dfd6f5d0
+oid sha256:ac7af7638e4cb2baa9d2c827f2cbc652b083802b8eaa737864cc38dc769d9b36
 size 17550344

run-32/checkpoint-480/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-32/checkpoint-480/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7af7638e4cb2baa9d2c827f2cbc652b083802b8eaa737864cc38dc769d9b36
+size 17550344

run-32/checkpoint-480/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c2be452e88971bf3f68ac15d53a55f5847eeac265faee7a9a8f0b53ae3c0c5
+size 35125946

run-32/checkpoint-480/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c3ca48e9dedef0092757c5be35db71c4ac4a9aec640b6e516bf811a77eb08b8
+size 14308

run-32/checkpoint-480/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5814d01bd6703b2ae5a0d98c2fa308518bc89453fa3512ab43f2798cd0aef647
+size 1064

run-32/checkpoint-480/special_tokens_map.json

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

run-32/checkpoint-480/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-32/checkpoint-480/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8665447897623401,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-32\\checkpoint-480",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 480,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.9769735662189624e-05,
+      "loss": 0.488,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8555758683729433,
+      "eval_loss": 0.47589612007141113,
+      "eval_runtime": 23.6779,
+      "eval_samples_per_second": 92.407,
+      "eval_steps_per_second": 0.76,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.4637,
+      "step": 480
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8665447897623401,
+      "eval_loss": 0.47022923827171326,
+      "eval_runtime": 28.1827,
+      "eval_samples_per_second": 77.636,
+      "eval_steps_per_second": 0.639,
+      "step": 480
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 480,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 3241653770208.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.953947132437925e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32,
+    "seed": 24
+  }
+}

run-32/checkpoint-480/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8339fbd991adff502d5f69d41d2d3a5c8b22a26d030bc8aac59e693399fa063
+size 4664