Training in progress, epoch 6

logs/events.out.tfevents.1702280530.joseph_legion.22340.19

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e40808edd4800a9f6e3cd6d1fd5464b07d64ec5120984b152023562f71733bbb
-size 6846
+oid sha256:00c4aef8bfe2fa6cf09a95237ab6d91977c273f9ebb8a3f436f98584d3dd165b
+size 7326

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f7b134640460498270051937ece1c46ce16a24b88435068a9864566799ec61
+oid sha256:dd1a3bece42063489d522b268eacf8a8fdbcb5f40a282878eaf7c1250703a0dc
 size 44692608

run-6/checkpoint-1182/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-6/checkpoint-1182/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1a3bece42063489d522b268eacf8a8fdbcb5f40a282878eaf7c1250703a0dc
+size 44692608

run-6/checkpoint-1182/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5a6763c55a85465b0338b090c6108eb52b94a6ec0adf38c5fd11975fc01aa7
+size 89430010

run-6/checkpoint-1182/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9511e5e4163d669edd4526e0777794d8936c52493f7e77dc7be042cfeed886
+size 14308

run-6/checkpoint-1182/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3b69c5c766fc9f2234cac440dba1114e5dca164a7a4b855456331a967607d7
+size 1064

run-6/checkpoint-1182/special_tokens_map.json

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

run-6/checkpoint-1182/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-6/checkpoint-1182/trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.7896053362979433,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-6\\checkpoint-1182",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1182,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0611700032566007e-05,
+      "loss": 0.1259,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7536131183991106,
+      "eval_loss": 0.12161022424697876,
+      "eval_runtime": 125.6824,
+      "eval_samples_per_second": 57.255,
+      "eval_steps_per_second": 0.454,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.095742885056578e-06,
+      "loss": 0.1236,
+      "step": 394
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7745969983324069,
+      "eval_loss": 0.12096704542636871,
+      "eval_runtime": 125.4944,
+      "eval_samples_per_second": 57.341,
+      "eval_steps_per_second": 0.454,
+      "step": 394
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.579785737547148e-06,
+      "loss": 0.1229,
+      "step": 591
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7848804891606448,
+      "eval_loss": 0.12066732347011566,
+      "eval_runtime": 125.5947,
+      "eval_samples_per_second": 57.295,
+      "eval_steps_per_second": 0.454,
+      "step": 591
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.063828590037718e-06,
+      "loss": 0.1224,
+      "step": 788
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7804335742078933,
+      "eval_loss": 0.12036041915416718,
+      "eval_runtime": 125.5933,
+      "eval_samples_per_second": 57.296,
+      "eval_steps_per_second": 0.454,
+      "step": 788
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.547871442528289e-06,
+      "loss": 0.1221,
+      "step": 985
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7887715397443024,
+      "eval_loss": 0.12023670971393585,
+      "eval_runtime": 125.4555,
+      "eval_samples_per_second": 57.359,
+      "eval_steps_per_second": 0.454,
+      "step": 985
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.031914295018859e-06,
+      "loss": 0.1218,
+      "step": 1182
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7896053362979433,
+      "eval_loss": 0.12014192342758179,
+      "eval_runtime": 125.3237,
+      "eval_samples_per_second": 57.419,
+      "eval_steps_per_second": 0.455,
+      "step": 1182
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 265501203931764.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.18717092492624732,
+    "learning_rate": 1.2127657180075437e-05,
+    "num_train_epochs": 8,
+    "temperature": 5
+  }
+}

run-6/checkpoint-1182/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40dcaec467c321bbd4ff99afc7a2ae4bf90159a9a099a7339cfff83b49ccfbc6
+size 4792