Training in progress, epoch 1, checkpoint

checkpoint-81/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65618f3f9cfec94ec5419ec3f26de6d66f6b632af08bab6de028ee72c2976b61
+oid sha256:8d80c71b857b58fe58cdad6972e7e855fbadaef60a059964e6269e3dc8310bcf
 size 592330980

checkpoint-81/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e202b0194fb86789b10e0eb394537896506c34c08d5959bdb7c008e5c750498a
+oid sha256:ca33247ef09026eb2108fa36f95ec07a85a7d78204f7d43fa1dfec194677b15c
 size 1014670074

checkpoint-81/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f758e297e56d3179fd6a3cc50e906a5d9c55cb43ac701f13c34165b11c1aae
+oid sha256:bdb4b9e39f26364dd12b4935d341c9c41df1f0d9ec688c6ea55c6a3c16f98050
 size 14244

checkpoint-81/trainer_state.json

@@ -11,63 +11,63 @@
     {
       "epoch": 1.0,
       "eval_B-Claim": {
-        "f1-score": 0.18764302059496568,
-        "precision": 0.3416666666666667,
-        "recall": 0.12933753943217666,
-        "support": 317.0
+        "f1-score": 0.17153996101364524,
+        "precision": 0.25287356321839083,
+        "recall": 0.12979351032448377,
+        "support": 339.0
       },
       "eval_B-MajorClaim": {
-        "f1-score": 0.19540229885057472,
-        "precision": 0.8947368421052632,
-        "recall": 0.10967741935483871,
-        "support": 155.0
+        "f1-score": 0.08383233532934131,
+        "precision": 1.0,
+        "recall": 0.04375,
+        "support": 160.0
       },
       "eval_B-Premise": {
-        "f1-score": 0.8476339053562143,
-        "precision": 0.740909090909091,
-        "recall": 0.9902794653705954,
-        "support": 823.0
+        "f1-score": 0.8469620831429876,
+        "precision": 0.7427884615384616,
+        "recall": 0.9851222104144527,
+        "support": 941.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.4315998169894769,
-        "precision": 0.6394035246272028,
-        "recall": 0.3257366482504604,
-        "support": 4344.0
+        "f1-score": 0.5420081967213116,
+        "precision": 0.6803858520900321,
+        "recall": 0.4504044274159217,
+        "support": 4698.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.7779799818016379,
-        "precision": 0.7493426818580193,
-        "recall": 0.8088930936613056,
-        "support": 2114.0
+        "f1-score": 0.8343351767251743,
+        "precision": 0.8141717503519474,
+        "recall": 0.8555226824457594,
+        "support": 2028.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8948683715038855,
-        "precision": 0.8376057421174058,
-        "recall": 0.9605350187403542,
-        "support": 13607.0
+        "f1-score": 0.9004323458767015,
+        "precision": 0.8590809093131264,
+        "recall": 0.9459659511472983,
+        "support": 14861.0
       },
       "eval_O": {
-        "f1-score": 0.9980147987727848,
-        "precision": 0.9970251509961237,
-        "recall": 0.9990064131514769,
-        "support": 11071.0
+        "f1-score": 0.9988389078242631,
+        "precision": 0.9991008541885209,
+        "recall": 0.9985770987793006,
+        "support": 13353.0
       },
-      "eval_accuracy": 0.8673183065585397,
-      "eval_loss": 0.3193369209766388,
+      "eval_accuracy": 0.8856789444749863,
+      "eval_loss": 0.28347474336624146,
       "eval_macro avg": {
-        "f1-score": 0.6190203134099342,
-        "precision": 0.7429556713256817,
-        "recall": 0.6176379425658869,
-        "support": 32431.0
+        "f1-score": 0.6254212866619178,
+        "precision": 0.76405734152864,
+        "recall": 0.629876554361031,
+        "support": 36380.0
       },
-      "eval_runtime": 4.9083,
-      "eval_samples_per_second": 16.299,
-      "eval_steps_per_second": 2.037,
+      "eval_runtime": 5.0448,
+      "eval_samples_per_second": 16.056,
+      "eval_steps_per_second": 2.18,
       "eval_weighted avg": {
-        "f1-score": 0.8489527906249091,
-        "precision": 0.8526967051825685,
-        "recall": 0.8673183065585397,
-        "support": 32431.0
+        "f1-score": 0.8748148382495958,
+        "precision": 0.8768575102351055,
+        "recall": 0.8856789444749863,
+        "support": 36380.0
       },
       "step": 81
     }
@@ -77,7 +77,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 500,
-  "total_flos": 143790812718000.0,
+  "total_flos": 143344257399000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

checkpoint-81/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f0bdafd19c0347fe87a3f27a2ea54a847df1f75da4e3bbd7bf587c614e2949
+oid sha256:db3de2ea286aed4cce53d86abf84d503faba79a292e98a5c89e444e2125b5ea5
 size 4920