Training in progress, epoch 1, checkpoint

checkpoint-41/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0322de88e68075fee8b02629bca3f45ca571fb807f88148840a44c440d5aae74
+oid sha256:138942c8f4356011d76a3a29cef1fcfe36ed60d9640d9cc91ca5f0c3d61957cf
 size 592330980

checkpoint-41/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a85222387191164719fc5416d435601d4a9b0dc37aa70502965b91f816d7a5a9
+oid sha256:9a4408a3ce9f54e3b82993c0eeca8d47b25ea144ed63e3793861dbd04f8f2088
 size 1014670074

checkpoint-41/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b75d0f85c6e5f43bda08f24453a869f5d0b5d0d33d936ef1b542f406f081347
+oid sha256:4a939982f711c8a91f0893b4f281f0db4fd89d7ca52de2aed82098ef9ff76ea2
 size 14244

checkpoint-41/trainer_state.json

@@ -14,60 +14,60 @@
         "f1-score": 0.0,
         "precision": 0.0,
         "recall": 0.0,
-        "support": 295.0
+        "support": 317.0
       },
       "eval_B-MajorClaim": {
         "f1-score": 0.0,
         "precision": 0.0,
         "recall": 0.0,
-        "support": 156.0
+        "support": 155.0
       },
       "eval_B-Premise": {
-        "f1-score": 0.1227621483375959,
-        "precision": 0.8727272727272727,
-        "recall": 0.06602475928473177,
-        "support": 727.0
+        "f1-score": 0.030989272943980926,
+        "precision": 0.8125,
+        "recall": 0.015795868772782502,
+        "support": 823.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.35051546391752586,
-        "precision": 0.5111008325624422,
-        "recall": 0.26671494086410813,
-        "support": 4143.0
+        "f1-score": 0.4085060273601517,
+        "precision": 0.4962158604804212,
+        "recall": 0.34714548802946593,
+        "support": 4344.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.2476060191518468,
-        "precision": 0.4952120383036936,
-        "recall": 0.16507067943456452,
-        "support": 2193.0
+        "f1-score": 0.4814916369618864,
+        "precision": 0.5727332028701891,
+        "recall": 0.4153263954588458,
+        "support": 2114.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8531195999852935,
-        "precision": 0.7927029242962558,
-        "recall": 0.9235055321181247,
-        "support": 12563.0
+        "f1-score": 0.8524337025847599,
+        "precision": 0.7845887659890008,
+        "recall": 0.9331226574557213,
+        "support": 13607.0
       },
       "eval_O": {
-        "f1-score": 0.8310506279263117,
-        "precision": 0.7493095557484416,
-        "recall": 0.9328094302554027,
-        "support": 10180.0
+        "f1-score": 0.8266195658367045,
+        "precision": 0.7997794928335171,
+        "recall": 0.855323664662186,
+        "support": 8481.0
       },
-      "eval_accuracy": 0.7473642462901147,
-      "eval_loss": 0.6794929504394531,
+      "eval_accuracy": 0.748969538554338,
+      "eval_loss": 0.6934605836868286,
       "eval_macro avg": {
-        "f1-score": 0.34357912275979624,
-        "precision": 0.48872180337687227,
-        "recall": 0.3363036202795617,
-        "support": 30257.0
+        "f1-score": 0.3714343150982119,
+        "precision": 0.49511676031044694,
+        "recall": 0.36667343919700024,
+        "support": 29841.0
       },
-      "eval_runtime": 1.4284,
-      "eval_samples_per_second": 56.707,
-      "eval_steps_per_second": 7.701,
+      "eval_runtime": 1.4147,
+      "eval_samples_per_second": 56.549,
+      "eval_steps_per_second": 7.069,
       "eval_weighted avg": {
-        "f1-score": 0.7027223642713039,
-        "precision": 0.7080894203665903,
-        "recall": 0.7473642462901147,
-        "support": 30257.0
+        "f1-score": 0.7180574915034598,
+        "precision": 0.7202786906044678,
+        "recall": 0.748969538554338,
+        "support": 29841.0
       },
       "step": 41
     }
@@ -77,7 +77,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 16,
   "save_steps": 500,
-  "total_flos": 143344257399000.0,
+  "total_flos": 143790812718000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

checkpoint-41/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f1dc302eca5129fec8b02daa92ee1b99cab9ac1f7862cc767c288e09ad4b9f2
+oid sha256:5626137ff44175bb256e7d272052a295ab9ae4c6895813ac192564aaad939cff
 size 4664