Training in progress, step 500, checkpoint

last-checkpoint/config.json

@@ -1,16 +1,15 @@
 {
-  "_name_or_path": "vblagoje/bart_lfqa",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
   "activation_function": "gelu",
   "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
+  "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
@@ -19,12 +18,15 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
+  "early_stopping": true,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
+  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -39,22 +41,30 @@
   },
   "max_position_embeddings": 1024,
   "model_type": "bart",
+  "no_repeat_ngram_size": 3,
   "normalize_before": false,
-  "normalize_embedding": true,
+  "num_beams": 4,
   "num_hidden_layers": 12,
-  "output_past": false,
   "pad_token_id": 1,
-  "prefix": " ",
   "scale_embedding": false,
-  "static_position_embeddings": false,
   "task_specific_params": {
     "summarization": {
-      "early_stopping": true,
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
       "length_penalty": 2.0,
       "max_length": 142,
       "min_length": 56,
-      "no_repeat_ngram_size": 3,
       "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
     }
   },
   "torch_dtype": "float32",

last-checkpoint/generation_config.json

@@ -2,8 +2,12 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
+  "early_stopping": true,
   "eos_token_id": 2,
+  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
   "pad_token_id": 1,
   "transformers_version": "4.35.2"
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6a3997803eebdd2cab8b05d3e11fc7b1b5e72b059d14b88afbc5e9d2e960a2
+oid sha256:394dfb894024b92bbbfb1b862531d2d6e28d88e7bc8c60fa638c57e06c43164d
 size 1625426996

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0659d84d42f67f7d0614c9db8ed7e1b90dc5467ce646c45a244117e0d8b281e6
+oid sha256:607419ad1882e0f53d766a3b9cffcab6b6f72e0bd0f8052ca50a35e39f90a005
 size 3250759951

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d14f7de59f48f4ade3e9464aacd8c0fa09164a39807a7c587e8743b637b06e
+oid sha256:3e7af7a01e94a9a7176c2bbdf2cb9b8139105cfe65528853ec5a27025100d6bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6032f9ebe8c8c14bc64b0775131b92bc24d785e7deee32c5a13741aeca0eff6f
+oid sha256:8f0d839853e90ea69a9baf4e612b78a79239aebb94a6d3f22225e1b04a009e92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09818253223659809,
+  "epoch": 0.010909170248510899,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,63 +11,15 @@
     {
       "epoch": 0.01,
       "learning_rate": 1.992872157045291e-05,
-      "loss": 0.6371,
+      "loss": 0.5416,
       "step": 500
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 1.9855988479078326e-05,
-      "loss": 0.2287,
-      "step": 1000
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 1.9783255387703745e-05,
-      "loss": 0.1475,
-      "step": 1500
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 1.971052229632916e-05,
-      "loss": 0.1033,
-      "step": 2000
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 1.963778920495458e-05,
-      "loss": 0.1562,
-      "step": 2500
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 1.9565056113579996e-05,
-      "loss": 0.107,
-      "step": 3000
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 1.9492323022205415e-05,
-      "loss": 0.0692,
-      "step": 3500
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 1.941958993083083e-05,
-      "loss": 0.0909,
-      "step": 4000
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 1.934685683945625e-05,
-      "loss": 0.1167,
-      "step": 4500
     }
   ],
   "logging_steps": 500,
   "max_steps": 137499,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 7618727116800000.0,
+  "total_flos": 846525235200000.0,
   "trial_name": null,
   "trial_params": null
 }