Training in progress, epoch 3, checkpoint

checkpoint-804/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2cdf6ebafb91249b6eb869bebd78cf2e42ec335899db1a4399b8cc67055f5c
+oid sha256:37ba434c0e8ecbfb045e52bf663fe41d57171b05a5e9542ec9adcf403c799192
 size 331462608

checkpoint-804/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8612be6bcbe65a86fcc9ade9d03951daeb2eb0f7f87185ed76aacddd19af9d7
+oid sha256:f8793477e42c387209c1856305fa3bfcb60e5ccbc8a83d9a92933b3be5555d48
 size 662989765

checkpoint-804/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f1ff70fa735df419a19cd34e69105abefa9defdd7b13f96e5ad4f92e7cd5120
+oid sha256:c0a36d5073642b9212f468ac2dfd7eed2c11ab1fce8837c064ed6fea17a55b2d
 size 627

checkpoint-804/trainer_state.json

@@ -10,57 +10,57 @@
   "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
     },
     {
       "epoch": 3.0,
-      "grad_norm": 9.861120223999023,
-      "learning_rate": 0.0,
-      "loss": 0.428,
+      "grad_norm": 9.864019393920898,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4161,
       "step": 804
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.5648320913314819,
-      "eval_matthews_correlation": 0.3262988329908328,
-      "eval_runtime": 8.5202,
-      "eval_samples_per_second": 122.414,
-      "eval_steps_per_second": 7.746,
+      "eval_loss": 0.5453676581382751,
+      "eval_matthews_correlation": 0.3451229816764349,
+      "eval_runtime": 8.5021,
+      "eval_samples_per_second": 122.676,
+      "eval_steps_per_second": 7.763,
       "step": 804
     }
   ],
   "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": {
@@ -69,7 +69,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }

checkpoint-804/training_args.bin

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