Training in progress, epoch 2, checkpoint

checkpoint-162/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba20684845ee5d7c93b29cb326da21782b61396c6ddded1fe325bfd9cf920613
+oid sha256:a2e9f279f770d7c2213c11dec51f9da8ada899f6effaec0e09418bcce0dafc76
 size 592318676

checkpoint-162/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d93b4686e10cfbb51d0770108bd285a5e41cf0945f62440958b624394ad1f8
+oid sha256:5ebe8665073b004b5306e8fa2aa68b9f5edfdcd67109cb61e29597590cb4a2b0
 size 1014645498

checkpoint-162/rng_state.pth

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

checkpoint-162/trainer_state.json

@@ -11,78 +11,78 @@
     {
       "epoch": 1.0,
       "eval_B": {
-        "f1-score": 0.8087666523420713,
-        "precision": 0.8189730200174065,
-        "recall": 0.7988115449915111,
-        "support": 1178.0
+        "f1-score": 0.8266764382557715,
+        "precision": 0.7866108786610879,
+        "recall": 0.871042471042471,
+        "support": 1295.0
       },
       "eval_I": {
-        "f1-score": 0.9374597034171502,
-        "precision": 0.9521418826739427,
-        "recall": 0.9232234509762421,
-        "support": 18899.0
+        "f1-score": 0.9410658617447671,
+        "precision": 0.9344077040239768,
+        "recall": 0.9478195863443808,
+        "support": 20065.0
       },
       "eval_O": {
-        "f1-score": 0.8881362400419788,
-        "precision": 0.863303347862376,
-        "recall": 0.9144400785854617,
-        "support": 10180.0
+        "f1-score": 0.8562443302086484,
+        "precision": 0.8789421405512788,
+        "recall": 0.8346893055064262,
+        "support": 8481.0
       },
-      "eval_accuracy": 0.9154245298608586,
-      "eval_loss": 0.2228638380765915,
+      "eval_accuracy": 0.912335377500754,
+      "eval_loss": 0.2450982630252838,
       "eval_macro avg": {
-        "f1-score": 0.8781208652670669,
-        "precision": 0.8781394168512416,
-        "recall": 0.8788250248510717,
-        "support": 30257.0
+        "f1-score": 0.8746622100697291,
+        "precision": 0.8666535744121145,
+        "recall": 0.8845171209644261,
+        "support": 29841.0
       },
-      "eval_runtime": 4.7167,
-      "eval_samples_per_second": 17.173,
-      "eval_steps_per_second": 2.332,
+      "eval_runtime": 4.6269,
+      "eval_samples_per_second": 17.29,
+      "eval_steps_per_second": 2.161,
       "eval_weighted avg": {
-        "f1-score": 0.9158543469268937,
-        "precision": 0.9170673807540184,
-        "recall": 0.9154245298608586,
-        "support": 30257.0
+        "f1-score": 0.9119949287205363,
+        "precision": 0.9122301519092053,
+        "recall": 0.912335377500754,
+        "support": 29841.0
       },
       "step": 81
     },
     {
       "epoch": 2.0,
       "eval_B": {
-        "f1-score": 0.8401515151515152,
-        "precision": 0.7585499316005472,
-        "recall": 0.9414261460101867,
-        "support": 1178.0
+        "f1-score": 0.8833395452851286,
+        "precision": 0.8537463976945245,
+        "recall": 0.915057915057915,
+        "support": 1295.0
       },
       "eval_I": {
-        "f1-score": 0.9568235603470944,
-        "precision": 0.9510219016256338,
-        "recall": 0.9626964389650247,
-        "support": 18899.0
+        "f1-score": 0.9549518227873249,
+        "precision": 0.9516903430183636,
+        "recall": 0.958235733864939,
+        "support": 20065.0
       },
       "eval_O": {
-        "f1-score": 0.9185648054827655,
-        "precision": 0.9430877483443708,
-        "recall": 0.8952848722986247,
-        "support": 10180.0
+        "f1-score": 0.88924750463212,
+        "precision": 0.9016969696969697,
+        "recall": 0.877137130055418,
+        "support": 8481.0
       },
-      "eval_accuracy": 0.9391876260038999,
-      "eval_loss": 0.16692574322223663,
+      "eval_accuracy": 0.9333132267685399,
+      "eval_loss": 0.20076116919517517,
       "eval_macro avg": {
-        "f1-score": 0.905179960327125,
-        "precision": 0.8842198605235172,
-        "recall": 0.9331358190912787,
-        "support": 30257.0
+        "f1-score": 0.9091796242348579,
+        "precision": 0.9023779034699526,
+        "recall": 0.916810259659424,
+        "support": 29841.0
       },
-      "eval_runtime": 4.7116,
-      "eval_samples_per_second": 17.192,
-      "eval_steps_per_second": 2.335,
+      "eval_runtime": 4.6524,
+      "eval_samples_per_second": 17.195,
+      "eval_steps_per_second": 2.149,
       "eval_weighted avg": {
-        "f1-score": 0.9394089523635119,
-        "precision": 0.9408589092241132,
-        "recall": 0.9391876260038999,
-        "support": 30257.0
+        "f1-score": 0.9331705077630417,
+        "precision": 0.9332314707173981,
+        "recall": 0.9333132267685399,
+        "support": 29841.0
       },
       "step": 162
     }
@@ -92,7 +92,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 500,
-  "total_flos": 286680220671600.0,
+  "total_flos": 287573305471200.0,
   "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:a9f81281de988dbf2616f1c96e725c00f6e4415b289b670a7cb21136eb66e95f
+oid sha256:d229d7bc9127d222c880edfd3fa9418a9ccede656fe27f7f0aa04990c9605be4
 size 4856