Training in progress, epoch 2, checkpoint

checkpoint-162/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e9f279f770d7c2213c11dec51f9da8ada899f6effaec0e09418bcce0dafc76
+oid sha256:34a0820e3b044a280c131b473ed2f7edc6cd0eccecf71f77e36c944f35ed0d73
 size 592318676

checkpoint-162/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ebe8665073b004b5306e8fa2aa68b9f5edfdcd67109cb61e29597590cb4a2b0
+oid sha256:ba4a9d382629f35839011fa7ba13d6fbbf8fe0f0616c56116dc5777a49f168f7
 size 1014645498

checkpoint-162/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88e210ec99a19f026e2def82a9c5587c47c7771d7dd08d2e2ba3261c169c79d9
+oid sha256:6613e657dfa5c91f076329239ba74e9bccea696a05690b1f35a5faffc85df4aa
 size 14244

checkpoint-162/trainer_state.json

@@ -11,78 +11,78 @@
     {
       "epoch": 1.0,
       "eval_B": {
-        "f1-score": 0.8266764382557715,
-        "precision": 0.7866108786610879,
-        "recall": 0.871042471042471,
-        "support": 1295.0
+        "f1-score": 0.7905866302864938,
+        "precision": 0.7768096514745308,
+        "recall": 0.8048611111111111,
+        "support": 1440.0
       },
       "eval_I": {
-        "f1-score": 0.9410658617447671,
-        "precision": 0.9344077040239768,
-        "recall": 0.9478195863443808,
-        "support": 20065.0
+        "f1-score": 0.9005331227169513,
+        "precision": 0.9637593111099372,
+        "recall": 0.8450919534905267,
+        "support": 21587.0
       },
       "eval_O": {
-        "f1-score": 0.8562443302086484,
-        "precision": 0.8789421405512788,
-        "recall": 0.8346893055064262,
-        "support": 8481.0
+        "f1-score": 0.8288892663043479,
+        "precision": 0.7463108800367001,
+        "recall": 0.9320156593144275,
+        "support": 10473.0
       },
-      "eval_accuracy": 0.912335377500754,
-      "eval_loss": 0.2450982630252838,
+      "eval_accuracy": 0.8705373134328358,
+      "eval_loss": 0.32930415868759155,
       "eval_macro avg": {
-        "f1-score": 0.8746622100697291,
-        "precision": 0.8666535744121145,
-        "recall": 0.8845171209644261,
-        "support": 29841.0
+        "f1-score": 0.8400030064359308,
+        "precision": 0.8289599475403894,
+        "recall": 0.8606562413053552,
+        "support": 33500.0
       },
-      "eval_runtime": 4.6269,
-      "eval_samples_per_second": 17.29,
-      "eval_steps_per_second": 2.161,
+      "eval_runtime": 4.7349,
+      "eval_samples_per_second": 17.107,
+      "eval_steps_per_second": 2.323,
       "eval_weighted avg": {
-        "f1-score": 0.9119949287205363,
-        "precision": 0.9122301519092053,
-        "recall": 0.912335377500754,
-        "support": 29841.0
+        "f1-score": 0.8734092702599646,
+        "precision": 0.8877430445874,
+        "recall": 0.8705373134328358,
+        "support": 33500.0
       },
       "step": 81
     },
     {
       "epoch": 2.0,
       "eval_B": {
-        "f1-score": 0.8833395452851286,
-        "precision": 0.8537463976945245,
-        "recall": 0.915057915057915,
-        "support": 1295.0
+        "f1-score": 0.8656218739579861,
+        "precision": 0.8325849903784477,
+        "recall": 0.9013888888888889,
+        "support": 1440.0
       },
       "eval_I": {
-        "f1-score": 0.9549518227873249,
-        "precision": 0.9516903430183636,
-        "recall": 0.958235733864939,
-        "support": 20065.0
+        "f1-score": 0.9547168948727912,
+        "precision": 0.9423736462093862,
+        "recall": 0.9673877796822161,
+        "support": 21587.0
       },
       "eval_O": {
-        "f1-score": 0.88924750463212,
-        "precision": 0.9016969696969697,
-        "recall": 0.877137130055418,
-        "support": 8481.0
+        "f1-score": 0.9013528191962081,
+        "precision": 0.9332379102341274,
+        "recall": 0.8715745249689678,
+        "support": 10473.0
       },
-      "eval_accuracy": 0.9333132267685399,
-      "eval_loss": 0.20076116919517517,
+      "eval_accuracy": 0.9345970149253732,
+      "eval_loss": 0.2162298709154129,
       "eval_macro avg": {
-        "f1-score": 0.9091796242348579,
-        "precision": 0.9023779034699526,
-        "recall": 0.916810259659424,
-        "support": 29841.0
+        "f1-score": 0.9072305293423284,
+        "precision": 0.902732182273987,
+        "recall": 0.9134503978466909,
+        "support": 33500.0
       },
-      "eval_runtime": 4.6524,
-      "eval_samples_per_second": 17.195,
-      "eval_steps_per_second": 2.149,
+      "eval_runtime": 4.753,
+      "eval_samples_per_second": 17.042,
+      "eval_steps_per_second": 2.314,
       "eval_weighted avg": {
-        "f1-score": 0.9331705077630417,
-        "precision": 0.9332314707173981,
-        "recall": 0.9333132267685399,
-        "support": 29841.0
+        "f1-score": 0.9342040950316517,
+        "precision": 0.9347982961417612,
+        "recall": 0.9345970149253732,
+        "support": 33500.0
       },
       "step": 162
     }
@@ -92,7 +92,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 500,
-  "total_flos": 287573305471200.0,
+  "total_flos": 286680220671600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

checkpoint-162/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d229d7bc9127d222c880edfd3fa9418a9ccede656fe27f7f0aa04990c9605be4
+oid sha256:b8ca363922308e3892528dd031742ffedc372734b464a042d09444af9700901e
 size 4856