Training in progress, epoch 1, checkpoint

checkpoint-1108/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "facebook/bart-large-mnli",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "normalize_before": false,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-1108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd6ddf13536a177e62124bc5d12fe1bc83909bde215fc77acc2a74ab5fc70d9
+size 1629432864

checkpoint-1108/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.996845425867508,
+  "eval_steps": 500,
+  "global_step": 1108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_f1": 0.13882567137005006,
+      "eval_loss": 0.8569005727767944,
+      "eval_precision": 0.07566360704539817,
+      "eval_recall": 0.8402203856749312,
+      "eval_runtime": 50.8375,
+      "eval_samples_per_second": 91.92,
+      "eval_steps_per_second": 11.507,
+      "step": 0
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 18.535512924194336,
+      "learning_rate": 2.4954873646209387e-05,
+      "loss": 0.1595,
+      "step": 555
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.7377049180327869,
+      "eval_loss": 0.11871597915887833,
+      "eval_precision": 0.6415478615071283,
+      "eval_recall": 0.8677685950413223,
+      "eval_runtime": 52.321,
+      "eval_samples_per_second": 89.314,
+      "eval_steps_per_second": 11.181,
+      "step": 555
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 3.852428271545549e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fec65d435d82330639f2254c3c8dd619ceaf78855b73ed7360d46e29c00bb91
+size 5368