Training in progress, epoch 2, checkpoint

checkpoint-536/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569c8ea8008cf6b629b89d1738bc68d7b3501ca7f1532c114180ecd0f3193bf
+oid sha256:f2198c797b79b9f5801b26fa9e8583ad612d958023d493fd5d4719df3c1a6163
 size 331462608

checkpoint-536/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc83a1e436882d6def515085048a29b7489422652b80c96d7e0ffb0258fab3f2
+oid sha256:ca1be2f4514a3b695979e2e84cb3cb2c5923e1f2d2415046dff6ba5d29796e7f
 size 662989765

checkpoint-536/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5943d2541988d800c63830fcc1621396a3222919376f4cf508316b87b8b7ce36
+oid sha256:cb3d2f990ffeebef4ac8e811bc1d1f5d4cd23f547ddb7d674706c83a46affcf4
 size 627

checkpoint-536/trainer_state.json

@@ -10,41 +10,41 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 6.508703708648682,
-      "learning_rate": 1.3333333333333333e-05,
-      "loss": 0.6101,
+      "grad_norm": 9.199758529663086,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.61,
       "step": 268
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.6032158732414246,
-      "eval_matthews_correlation": 0.1345503796973939,
-      "eval_runtime": 8.5318,
-      "eval_samples_per_second": 122.249,
-      "eval_steps_per_second": 7.736,
+      "eval_loss": 0.581834614276886,
+      "eval_matthews_correlation": 0.1605505486389139,
+      "eval_runtime": 8.5337,
+      "eval_samples_per_second": 122.221,
+      "eval_steps_per_second": 7.734,
       "step": 268
     },
     {
       "epoch": 2.0,
-      "grad_norm": 11.809653282165527,
-      "learning_rate": 6.666666666666667e-06,
-      "loss": 0.5325,
+      "grad_norm": 7.077225685119629,
+      "learning_rate": 1.2e-05,
+      "loss": 0.5265,
       "step": 536
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5451133251190186,
-      "eval_matthews_correlation": 0.3134805838230471,
-      "eval_runtime": 8.5009,
-      "eval_samples_per_second": 122.693,
-      "eval_steps_per_second": 7.764,
+      "eval_loss": 0.5488986968994141,
+      "eval_matthews_correlation": 0.3414642281150747,
+      "eval_runtime": 8.5064,
+      "eval_samples_per_second": 122.614,
+      "eval_steps_per_second": 7.759,
       "step": 536
     }
   ],
   "logging_steps": 500,
-  "max_steps": 804,
+  "max_steps": 1340,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {

checkpoint-536/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b47f572b06d3969dd1d46ea18f657c0eb324930ac4d582f1ff90c6092ca4ce
+oid sha256:d37219932d78f454fedda9dcf9514306d19f0518eab06266cbde4f0fbddf00de
 size 4667