Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0acc744c43a3a5795e3864bd34b19e47db0a2cc6239dc1f7dc7a989a06cc1bc2
+oid sha256:841ad96a89d71e1260cae7d399b34fa855aedbf381e3bf91bdef6df3d622a2db
 size 2610104820

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee43e4cfe23b31e259d57c5194694d18887ed3ca96c9762256c1c50a0d533d3
+oid sha256:adfdabe3f308d987b87ee605feed50a0c9b4885e232649127cb6d8c48e779034
 size 5210004271

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f75193245e65869ca07a16a2caab41ba86286fcae28542136bb36df639a39935
+oid sha256:3b62c3337c81711e31c09ac2f120ce29cc6fcb685d12b30aa21cb379686a6b98
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e7a70b99a4ca390e08d8c14e39ca3fc804d75e54a2b4300e5640fb55822343
+oid sha256:67513ae8a1eef7c889b1c7892970d644af065353df72f33912ccf373456606a8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04081197455525398,
-  "best_model_checkpoint": "mgh6/HTH_pssm/checkpoint-950",
-  "epoch": 9.0,
+  "best_metric": 0.03994766250252724,
+  "best_model_checkpoint": "mgh6/HTH_pssm/checkpoint-1050",
+  "epoch": 9.913099870298314,
   "eval_steps": 50,
-  "global_step": 981,
+  "global_step": 1080,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -292,6 +292,36 @@
       "eval_samples_per_second": 42.794,
       "eval_steps_per_second": 21.397,
       "step": 950
+    },
+    {
+      "epoch": 9.175241389249171,
+      "grad_norm": 0.09147156774997711,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.0104,
+      "step": 1000
+    },
+    {
+      "epoch": 9.175241389249171,
+      "eval_loss": 0.04029148817062378,
+      "eval_runtime": 8.5679,
+      "eval_samples_per_second": 42.718,
+      "eval_steps_per_second": 21.359,
+      "step": 1000
+    },
+    {
+      "epoch": 9.636402939904885,
+      "grad_norm": 0.09815036505460739,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.0096,
+      "step": 1050
+    },
+    {
+      "epoch": 9.636402939904885,
+      "eval_loss": 0.03994766250252724,
+      "eval_runtime": 8.5466,
+      "eval_samples_per_second": 42.824,
+      "eval_steps_per_second": 21.412,
+      "step": 1050
     }
   ],
   "logging_steps": 50,
@@ -315,7 +345,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }