Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b53944df2e0b752fbc481010fa9fd28056788987194c4a21bcc3d2f0eb10937
+oid sha256:373fdfaf0c6cf63c7a73749304a96b057753aef598727f59e5c0142d9c49f9b5
 size 2610104820

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78e12fef57719dd8f303d7baee30b5b033378e09280cca9cce651db8ae2558c
+oid sha256:80fffdee8ec9750a98c7e76024483eff8f196633106bfc6cb1642df6ffa159af
 size 5210004271

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335263bbdf55dec07c081046e09f117f40eceefa6f3b02ab74e94e4a08e084ac
+oid sha256:1bb8d68660a612d8ec9c8c416aefe8428f3513be5c4861a31d9b4fa8efd65694
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d282d44e6a12e9ca82ec6b42e7f212659678f5fe8c9a58e24a30599040d3e5
+oid sha256:c42147d2487e975dcb8b015449194c61c9350b5c1b3a114ecd6e3942d3403969
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8323967456817627,
-  "best_model_checkpoint": "mgh6/HTH_pssm/checkpoint-1100",
-  "epoch": 9.0,
+  "best_metric": 0.8310919404029846,
+  "best_model_checkpoint": "mgh6/HTH_pssm/checkpoint-1250",
+  "epoch": 9.929233772571987,
   "eval_steps": 50,
-  "global_step": 1161,
+  "global_step": 1280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -352,6 +352,36 @@
       "eval_samples_per_second": 42.175,
       "eval_steps_per_second": 21.088,
       "step": 1150
+    },
+    {
+      "epoch": 9.304538799414349,
+      "grad_norm": 0.034894853830337524,
+      "learning_rate": 6.25e-06,
+      "loss": 0.7838,
+      "step": 1200
+    },
+    {
+      "epoch": 9.304538799414349,
+      "eval_loss": 0.8314144015312195,
+      "eval_runtime": 10.2471,
+      "eval_samples_per_second": 42.158,
+      "eval_steps_per_second": 21.079,
+      "step": 1200
+    },
+    {
+      "epoch": 9.694973157637872,
+      "grad_norm": 0.03728077933192253,
+      "learning_rate": 2.3437500000000002e-06,
+      "loss": 0.7943,
+      "step": 1250
+    },
+    {
+      "epoch": 9.694973157637872,
+      "eval_loss": 0.8310919404029846,
+      "eval_runtime": 10.2435,
+      "eval_samples_per_second": 42.173,
+      "eval_steps_per_second": 21.086,
+      "step": 1250
     }
   ],
   "logging_steps": 50,
@@ -366,7 +396,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -375,7 +405,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }