Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05f3c7c0d3d1bdbf9ca73a0c6a41789456afc3bcb7425a4431960aa14a0bbfb2
+oid sha256:3b53944df2e0b752fbc481010fa9fd28056788987194c4a21bcc3d2f0eb10937
 size 2610104820

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850cde82cd0880a783d5e582811830f4f66c154f839a3ab5371cf297d34d7180
+oid sha256:d78e12fef57719dd8f303d7baee30b5b033378e09280cca9cce651db8ae2558c
 size 5210004271

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f75193245e65869ca07a16a2caab41ba86286fcae28542136bb36df639a39935
+oid sha256:335263bbdf55dec07c081046e09f117f40eceefa6f3b02ab74e94e4a08e084ac
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b9a9b66ad7c2c92d26ff031cce36ce8f9c2ebdb6be883784d837b0e0137568
+oid sha256:17d282d44e6a12e9ca82ec6b42e7f212659678f5fe8c9a58e24a30599040d3e5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8351929187774658,
-  "best_model_checkpoint": "mgh6/HTH_pssm/checkpoint-1000",
-  "epoch": 8.0,
+  "best_metric": 0.8323967456817627,
+  "best_model_checkpoint": "mgh6/HTH_pssm/checkpoint-1100",
+  "epoch": 9.0,
   "eval_steps": 50,
-  "global_step": 1032,
+  "global_step": 1161,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,6 +307,51 @@
       "eval_samples_per_second": 42.174,
       "eval_steps_per_second": 21.087,
       "step": 1000
+    },
+    {
+      "epoch": 8.140556368960468,
+      "grad_norm": 0.051104020327329636,
+      "learning_rate": 1.796875e-05,
+      "loss": 0.7866,
+      "step": 1050
+    },
+    {
+      "epoch": 8.140556368960468,
+      "eval_loss": 0.8334435820579529,
+      "eval_runtime": 10.2546,
+      "eval_samples_per_second": 42.128,
+      "eval_steps_per_second": 21.064,
+      "step": 1050
+    },
+    {
+      "epoch": 8.530990727183992,
+      "grad_norm": 0.05165121331810951,
+      "learning_rate": 1.4062500000000001e-05,
+      "loss": 0.7978,
+      "step": 1100
+    },
+    {
+      "epoch": 8.530990727183992,
+      "eval_loss": 0.8323967456817627,
+      "eval_runtime": 10.2329,
+      "eval_samples_per_second": 42.217,
+      "eval_steps_per_second": 21.108,
+      "step": 1100
+    },
+    {
+      "epoch": 8.921425085407517,
+      "grad_norm": 0.0460314117372036,
+      "learning_rate": 1.0156250000000001e-05,
+      "loss": 0.7942,
+      "step": 1150
+    },
+    {
+      "epoch": 8.921425085407517,
+      "eval_loss": 0.8324939608573914,
+      "eval_runtime": 10.243,
+      "eval_samples_per_second": 42.175,
+      "eval_steps_per_second": 21.088,
+      "step": 1150
     }
   ],
   "logging_steps": 50,
@@ -321,7 +366,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {