Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dedc386c970676237e201031761e505a7af788284f7935682e6eb63b424ca08d
+oid sha256:8d587d579142d324dbb466b96ff6ea6aa2164515a8bd678c0df1742178105989
 size 437958648

run-8/checkpoint-78/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d587d579142d324dbb466b96ff6ea6aa2164515a8bd678c0df1742178105989
+size 437958648

run-8/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f6d09eaba3c2b39a2c6c67b233d9e45a3f8f10832c939565883436450d0037
+size 876038394

run-8/checkpoint-78/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd53c5c3dd7d411230f105bda2473d2a3923ae5b6e14f965bb99d91f5a28c9b2
+size 14244

run-8/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a197c8bec22d7e182b65d9549e75f549277efb37d641d16a9d4346473fec05
+size 1064

run-8/checkpoint-78/special_tokens_map.json

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

run-8/checkpoint-78/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-78/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.5884476534296029,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_2/run-8/checkpoint-78",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 78,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5884476534296029,
+      "eval_loss": 0.6868922710418701,
+      "eval_runtime": 0.6839,
+      "eval_samples_per_second": 405.02,
+      "eval_steps_per_second": 13.16,
+      "step": 78
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.43799578402011274,
+    "learning_rate": 1.5413125073588876e-05,
+    "max_seq_length": 32,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
+  }
+}

run-8/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2218c3f3fca2a465e964820902d7fcc8841d350bf14bf95da8fc47ff93f26610
+size 5240

run-9/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92059dfc756ff7d9119c289e1ae46a62ff0b18781864362315ca1f219d8e78d3
+oid sha256:c769cf8ed6e0679cf3728954624f17edd05ca2ed4423f9242cefaa086ae1206a
 size 437958648

run-9/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938964d76cc1018676a44ce025e300c5c9d26b3d6e8bd2788a2c7eaf6f7d709b
+oid sha256:a3d3125dc932756abeae08fb8efa303d8ebc0593dd98ca3577a378eb01f3417f
 size 876038394

run-9/checkpoint-78/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd53c5c3dd7d411230f105bda2473d2a3923ae5b6e14f965bb99d91f5a28c9b2
+oid sha256:d42b4d1d3fdb43560c10df0f207c94a592a056695beb330e55f00d60d5eb856c
 size 14244

run-9/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35210a66a6168d6671450fdc4af4dd8fc58b2c576e15a27a7b9b62733e96c4da
+oid sha256:7c8692f812d7e13ff51eb7fcc4ca558c6c578b6eea5d3281d72567ff52c790a4
 size 1064

run-9/checkpoint-78/tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 128
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

run-9/checkpoint-78/trainer_state.json

@@ -1,23 +1,13 @@
 {
-  "best_metric": 0.5776173285198556,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_2/run-9/checkpoint-78",
+  "best_metric": null,
+  "best_model_checkpoint": null,
   "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 78,
   "is_hyper_param_search": true,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.5776173285198556,
-      "eval_loss": 0.6691069602966309,
-      "eval_runtime": 0.7326,
-      "eval_samples_per_second": 378.129,
-      "eval_steps_per_second": 12.286,
-      "step": 78
-    }
-  ],
+  "log_history": [],
   "logging_steps": 500,
   "max_steps": 78,
   "num_input_tokens_seen": 0,
@@ -39,9 +29,9 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.3313515942213683,
-    "learning_rate": 3.746778217633429e-05,
-    "max_seq_length": 128,
+    "dropout_rate": 0.3955022206405828,
+    "learning_rate": 1.440937238835823e-06,
+    "max_seq_length": 64,
     "num_train_epochs": 1,
     "per_device_train_batch_size": 32
   }

run-9/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c39da1304eee07eee65f5bedb39903599d91732f3162db5b1ed23b312ec0240d
+oid sha256:69a0f06d1a14b1a722325f9be16a250a0c37fe6c11cc4c80b7f6141fe2d2c874
 size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e4be23426d067f88ba8f5c404f35e8c04dc914aaa791f2d9c323aa3d892bb9
+oid sha256:2218c3f3fca2a465e964820902d7fcc8841d350bf14bf95da8fc47ff93f26610
 size 5240