Training in progress, epoch 1, checkpoint

checkpoint-81/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c387a25e4b00bd8cd7fa816321356f94c130c150563bb32e5f173abfddbaa7e
+oid sha256:081c2ef41ab09e428be3abf42fe6b940422819d1de460da39cf13185ce13fd5c
 size 592318676

checkpoint-81/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be01019aa5d358abf203d5f0c0ad0ce50e7a0f3e182476dd5c4a75be9820c050
+oid sha256:04be85650238dc1a273e204437d4286ace2eadafbdc6fe6d813f47f51409f779
 size 1014645498

checkpoint-81/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:153cfd77c5ddcff6dcd449eda1e20921f085ad496090dd7960aa7943b2fa3326
+oid sha256:a10709715b57c56c4e889a17baa14c8e503a7581e52966680626f29eada9d5ae
 size 1064

checkpoint-81/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
+  "best_metric": 0.2619660496711731,
+  "best_model_checkpoint": "longformer-spans/checkpoint-81",
   "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 81,
@@ -11,47 +11,47 @@
     {
       "epoch": 1.0,
       "eval_B": {
-        "f1-score": 0.8331822302810515,
-        "precision": 0.7901977644024075,
-        "recall": 0.8811121764141898,
-        "support": 1043.0
+        "f1-score": 0.816,
+        "precision": 0.7461594732991953,
+        "recall": 0.9002647837599294,
+        "support": 1133.0
       },
       "eval_I": {
-        "f1-score": 0.9471294753175105,
-        "precision": 0.9443616777446711,
-        "recall": 0.9499135446685879,
-        "support": 17350.0
+        "f1-score": 0.9321376763813793,
+        "precision": 0.9024103768767235,
+        "recall": 0.9638902525500463,
+        "support": 18333.0
       },
       "eval_O": {
-        "f1-score": 0.8992868897421833,
-        "precision": 0.9103731674811195,
-        "recall": 0.8884673748103187,
-        "support": 9226.0
+        "f1-score": 0.8560784528570645,
+        "precision": 0.931782945736434,
+        "recall": 0.7917511147142278,
+        "support": 9868.0
       },
-      "eval_accuracy": 0.9267895289474637,
-      "eval_loss": 0.20478281378746033,
+      "eval_accuracy": 0.9035249198881844,
+      "eval_loss": 0.2619660496711731,
       "eval_macro avg": {
-        "f1-score": 0.8931995317802484,
-        "precision": 0.8816442032093993,
-        "recall": 0.9064976986310321,
-        "support": 27619.0
+        "f1-score": 0.8680720430794812,
+        "precision": 0.860117598637451,
+        "recall": 0.8853020503414012,
+        "support": 29334.0
       },
-      "eval_runtime": 4.6128,
-      "eval_samples_per_second": 17.343,
-      "eval_steps_per_second": 2.168,
+      "eval_runtime": 5.5032,
+      "eval_samples_per_second": 14.537,
+      "eval_steps_per_second": 1.817,
       "eval_weighted avg": {
-        "f1-score": 0.9268447919078652,
-        "precision": 0.9271861479533134,
-        "recall": 0.9267895289474637,
-        "support": 27619.0
+        "f1-score": 0.9020655278480035,
+        "precision": 0.9062562975065145,
+        "recall": 0.9035249198881844,
+        "support": 29334.0
       },
       "step": 81
     }
   ],
   "logging_steps": 500,
-  "max_steps": 4050,
+  "max_steps": 1620,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 50,
+  "num_train_epochs": 20,
   "save_steps": 500,
   "total_flos": 143786652735600.0,
   "train_batch_size": 4,

checkpoint-81/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821ca433db9ddb761291ab61fc06d651ad248cd9d560cdb25f7f905e5aaff14e
+oid sha256:1094850123635c13193a80398a7bb1e351dd871416d3ce265431b259bf603290
 size 4856