Training in progress, epoch 4, checkpoint

checkpoint-2770/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-2770/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a41a1c3e47c0f5fd131425cb87704cfeb7776292e1a5bb5bdfed29615e1391e
+size 1629432864

checkpoint-2770/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.991437584497522,
+  "eval_steps": 500,
+  "global_step": 2770,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_f1": 0.018691588785046728,
+      "eval_loss": 0.8330444097518921,
+      "eval_precision": 0.009461009174311927,
+      "eval_recall": 0.7674418604651163,
+      "eval_runtime": 51.6093,
+      "eval_samples_per_second": 90.546,
+      "eval_steps_per_second": 11.335,
+      "step": 0
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4809592068195343,
+      "learning_rate": 3.998194945848376e-05,
+      "loss": 0.0586,
+      "step": 555
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.059180792421102524,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 52.6196,
+      "eval_samples_per_second": 88.807,
+      "eval_steps_per_second": 11.118,
+      "step": 555
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 14.132050514221191,
+      "learning_rate": 2.996389891696751e-05,
+      "loss": 0.0557,
+      "step": 1110
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.05642171949148178,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 40.9562,
+      "eval_samples_per_second": 114.097,
+      "eval_steps_per_second": 14.284,
+      "step": 1110
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.548943996429443,
+      "learning_rate": 1.9945848375451266e-05,
+      "loss": 0.0553,
+      "step": 1665
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.05951603502035141,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 40.9175,
+      "eval_samples_per_second": 114.205,
+      "eval_steps_per_second": 14.297,
+      "step": 1665
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.44529011845588684,
+      "learning_rate": 9.927797833935018e-06,
+      "loss": 0.0558,
+      "step": 2220
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.059898294508457184,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 40.5657,
+      "eval_samples_per_second": 115.196,
+      "eval_steps_per_second": 14.421,
+      "step": 2220
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2770,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 9.629766539300045e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2770/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea9167d8b6370173c68e6f09f8843c64f409d8664d8f7638ae1d6884df7db73
+size 5432