Training in progress, epoch 1, checkpoint

checkpoint-41/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138942c8f4356011d76a3a29cef1fcfe36ed60d9640d9cc91ca5f0c3d61957cf
+oid sha256:cd33ff53c0edd4d359980f27f4afa194ec5b807febef7f4cbaefde162b633c4b
 size 592330980

checkpoint-41/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4408a3ce9f54e3b82993c0eeca8d47b25ea144ed63e3793861dbd04f8f2088
+oid sha256:ab3510262bc219de46e870072b2a617000c0c57c3d0baaaf87394856c91f5477
 size 1014670074

checkpoint-41/rng_state.pth

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

checkpoint-41/trainer_state.json

@@ -14,60 +14,60 @@
         "f1-score": 0.0,
         "precision": 0.0,
         "recall": 0.0,
-        "support": 317.0
+        "support": 339.0
       },
       "eval_B-MajorClaim": {
         "f1-score": 0.0,
         "precision": 0.0,
         "recall": 0.0,
-        "support": 155.0
+        "support": 160.0
       },
       "eval_B-Premise": {
-        "f1-score": 0.030989272943980926,
-        "precision": 0.8125,
-        "recall": 0.015795868772782502,
-        "support": 823.0
+        "f1-score": 0.22426470588235295,
+        "precision": 0.8299319727891157,
+        "recall": 0.12964930924548354,
+        "support": 941.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.4085060273601517,
-        "precision": 0.4962158604804212,
-        "recall": 0.34714548802946593,
-        "support": 4344.0
+        "f1-score": 0.38247663551401867,
+        "precision": 0.423873640600725,
+        "recall": 0.348446147296722,
+        "support": 4698.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.4814916369618864,
-        "precision": 0.5727332028701891,
-        "recall": 0.4153263954588458,
-        "support": 2114.0
+        "f1-score": 0.3634627625716104,
+        "precision": 0.5125673249551167,
+        "recall": 0.28155818540433925,
+        "support": 2028.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8524337025847599,
-        "precision": 0.7845887659890008,
-        "recall": 0.9331226574557213,
-        "support": 13607.0
+        "f1-score": 0.8298935191271198,
+        "precision": 0.8110747093209996,
+        "recall": 0.8496063521970257,
+        "support": 14861.0
       },
       "eval_O": {
-        "f1-score": 0.8266195658367045,
-        "precision": 0.7997794928335171,
-        "recall": 0.855323664662186,
-        "support": 8481.0
+        "f1-score": 0.8121805609242796,
+        "precision": 0.7380952380952381,
+        "recall": 0.9027976701995608,
+        "support": 10473.0
       },
-      "eval_accuracy": 0.748969538554338,
-      "eval_loss": 0.6934605836868286,
+      "eval_accuracy": 0.7286865671641791,
+      "eval_loss": 0.763540506362915,
       "eval_macro avg": {
-        "f1-score": 0.3714343150982119,
-        "precision": 0.49511676031044694,
-        "recall": 0.36667343919700024,
-        "support": 29841.0
+        "f1-score": 0.3731825977170545,
+        "precision": 0.47364898368017067,
+        "recall": 0.3588653806204473,
+        "support": 33500.0
       },
-      "eval_runtime": 1.4147,
-      "eval_samples_per_second": 56.549,
-      "eval_steps_per_second": 7.069,
+      "eval_runtime": 1.4539,
+      "eval_samples_per_second": 55.714,
+      "eval_steps_per_second": 7.566,
       "eval_weighted avg": {
-        "f1-score": 0.7180574915034598,
-        "precision": 0.7202786906044678,
-        "recall": 0.748969538554338,
-        "support": 29841.0
+        "f1-score": 0.7040007584084623,
+        "precision": 0.7043362259324342,
+        "recall": 0.7286865671641791,
+        "support": 33500.0
       },
       "step": 41
     }
@@ -77,7 +77,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 16,
   "save_steps": 500,
-  "total_flos": 143790812718000.0,
+  "total_flos": 143344257399000.0,
   "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 sha256:5626137ff44175bb256e7d272052a295ab9ae4c6895813ac192564aaad939cff
+oid sha256:920ab155975bf66f694757fefb246b73b0d1489bdf4f03eda383fa028f5d083a
 size 4664