Training in progress, epoch 1, checkpoint

checkpoint-7/config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "MobileBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
+  "id2label": {
+    "LABEL_0": "negative",
+    "LABEL_1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
+  "vocab_size": 30522
+}

checkpoint-7/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136f376ae8b3568a5384dd2d0ed7746f242fc6bdb65bab79e3e540894d0e4cb4
+size 98470112

checkpoint-7/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e821d3bde33cca939b3da702c510b695fac7dea0507bf683139ba8b935bb8e85
+size 197593757

checkpoint-7/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d6eca64aa942b1fb6242ccacdb356b249b16a5213116b7a463df59ba8a0592
+size 14244

checkpoint-7/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2391582f1d2f37358d8db9bfe311a9c5e2c30e533fe35e4dc988b71f7bce594
+size 1064

checkpoint-7/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_global_step": 7,
+  "best_metric": 0.30054421768707484,
+  "best_model_checkpoint": "./results\\checkpoint-7",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 7,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.47,
+      "eval_f1": 0.30054421768707484,
+      "eval_loss": 385655.125,
+      "eval_runtime": 3.9911,
+      "eval_samples_per_second": 25.055,
+      "eval_steps_per_second": 1.754,
+      "step": 7
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 7,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6270852096000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-7/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44f69621aecf7a08f867fee0043d9ee8f500abe3775060b6b17f40f3cfc9663f
+size 5304