Training in progress, epoch 1, checkpoint

checkpoint-81/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6316247580c0a9b3201c131d5e0e0f50f496b20655183575101a6128abc29fb8
+oid sha256:65618f3f9cfec94ec5419ec3f26de6d66f6b632af08bab6de028ee72c2976b61
 size 592330980

checkpoint-81/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae3ca5878fa360abcc17b680824120433061c0c1f7aea3abd0ef52e7c595c5b1
+oid sha256:e202b0194fb86789b10e0eb394537896506c34c08d5959bdb7c008e5c750498a
 size 1014670074

checkpoint-81/rng_state.pth

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

checkpoint-81/trainer_state.json

@@ -11,63 +11,63 @@
     {
       "epoch": 1.0,
       "eval_B-Claim": {
-        "f1-score": 0.32421052631578945,
-        "precision": 0.42777777777777776,
-        "recall": 0.26101694915254237,
-        "support": 295.0
+        "f1-score": 0.18764302059496568,
+        "precision": 0.3416666666666667,
+        "recall": 0.12933753943217666,
+        "support": 317.0
       },
       "eval_B-MajorClaim": {
-        "f1-score": 0.192090395480226,
-        "precision": 0.8095238095238095,
-        "recall": 0.10897435897435898,
-        "support": 156.0
+        "f1-score": 0.19540229885057472,
+        "precision": 0.8947368421052632,
+        "recall": 0.10967741935483871,
+        "support": 155.0
       },
       "eval_B-Premise": {
-        "f1-score": 0.8566265060240965,
-        "precision": 0.7620578778135049,
-        "recall": 0.9779917469050894,
-        "support": 727.0
+        "f1-score": 0.8476339053562143,
+        "precision": 0.740909090909091,
+        "recall": 0.9902794653705954,
+        "support": 823.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.5001390820584144,
-        "precision": 0.5900886117492615,
-        "recall": 0.43398503499879315,
-        "support": 4143.0
+        "f1-score": 0.4315998169894769,
+        "precision": 0.6394035246272028,
+        "recall": 0.3257366482504604,
+        "support": 4344.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.776470588235294,
-        "precision": 0.6649333766655834,
-        "recall": 0.93296853625171,
-        "support": 2193.0
+        "f1-score": 0.7779799818016379,
+        "precision": 0.7493426818580193,
+        "recall": 0.8088930936613056,
+        "support": 2114.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8861458374413376,
-        "precision": 0.8781460059402845,
-        "recall": 0.8942927644670858,
-        "support": 12563.0
+        "f1-score": 0.8948683715038855,
+        "precision": 0.8376057421174058,
+        "recall": 0.9605350187403542,
+        "support": 13607.0
       },
       "eval_O": {
-        "f1-score": 0.9987647926046939,
-        "precision": 0.9977708781147998,
-        "recall": 0.9997606892150607,
-        "support": 12536.0
+        "f1-score": 0.9980147987727848,
+        "precision": 0.9970251509961237,
+        "recall": 0.9990064131514769,
+        "support": 11071.0
       },
-      "eval_accuracy": 0.8713396498328887,
-      "eval_loss": 0.3092103600502014,
+      "eval_accuracy": 0.8673183065585397,
+      "eval_loss": 0.3193369209766388,
       "eval_macro avg": {
-        "f1-score": 0.647778246879979,
-        "precision": 0.732899762512146,
-        "recall": 0.6584271542806628,
-        "support": 32613.0
+        "f1-score": 0.6190203134099342,
+        "precision": 0.7429556713256817,
+        "recall": 0.6176379425658869,
+        "support": 32431.0
       },
-      "eval_runtime": 4.965,
-      "eval_samples_per_second": 16.314,
-      "eval_steps_per_second": 2.215,
+      "eval_runtime": 4.9083,
+      "eval_samples_per_second": 16.299,
+      "eval_steps_per_second": 2.037,
       "eval_weighted avg": {
-        "f1-score": 0.8639627599323451,
-        "precision": 0.8662078389010613,
-        "recall": 0.8713396498328887,
-        "support": 32613.0
+        "f1-score": 0.8489527906249091,
+        "precision": 0.8526967051825685,
+        "recall": 0.8673183065585397,
+        "support": 32431.0
       },
       "step": 81
     }
@@ -77,7 +77,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 500,
-  "total_flos": 143344257399000.0,
+  "total_flos": 143790812718000.0,
   "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 sha256:5eff186592c44100b7fd5c301c21b9eebfc7f8bd335567cdc6ffe4a4d32ec927
+oid sha256:f2f0bdafd19c0347fe87a3f27a2ea54a847df1f75da4e3bbd7bf587c614e2949
 size 4920