Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1fd46d478c847a5384385a7d5cf5144011ad16d6622bedf331a64995268c6e9
+oid sha256:c9da7df641e6cc9b724f1ccab40191cd7a5b61687caf81936b21c4de30d2719a
 size 2610104820

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d4fcf2b410d99c6594a0e12f12877c292d85b9f7c62330e7e26de864750098
+oid sha256:af7172a7f9399a24984e5933b5d8c847bf6e4c819f8b77af127d70f2d0118343
 size 5210004271

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7c781d03ce544a7aa31375ec1cce20ab821ae066d16219adab4b2436b4176d
+oid sha256:252d84a8621f0d8623f524bb8ee54bb1a386d75c0645fcaf9bbfcc4b59877fc1
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b514faa73b6e320d8ae19d93f3da594146e59f1072af645ee09b9ce747afd0a1
+oid sha256:0ebd3960ec1614497d0e6e97cebd857464e618edc4df8a50eee43da5ac2ba348
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8674399256706238,
-  "best_model_checkpoint": "mgh6/HTH_pssm/checkpoint-600",
-  "epoch": 5.0,
+  "best_metric": 0.8489540219306946,
+  "best_model_checkpoint": "mgh6/HTH_pssm/checkpoint-750",
+  "epoch": 6.0,
   "eval_steps": 50,
-  "global_step": 645,
+  "global_step": 774,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,51 @@
       "eval_samples_per_second": 42.201,
       "eval_steps_per_second": 21.101,
       "step": 600
+    },
+    {
+      "epoch": 5.039043435822352,
+      "grad_norm": 0.11801417171955109,
+      "learning_rate": 4.921875e-05,
+      "loss": 0.8173,
+      "step": 650
+    },
+    {
+      "epoch": 5.039043435822352,
+      "eval_loss": 0.8601558804512024,
+      "eval_runtime": 10.2356,
+      "eval_samples_per_second": 42.205,
+      "eval_steps_per_second": 21.103,
+      "step": 650
+    },
+    {
+      "epoch": 5.4294777940458765,
+      "grad_norm": 0.0876191258430481,
+      "learning_rate": 4.5312500000000004e-05,
+      "loss": 0.8239,
+      "step": 700
+    },
+    {
+      "epoch": 5.4294777940458765,
+      "eval_loss": 0.8553031086921692,
+      "eval_runtime": 10.2387,
+      "eval_samples_per_second": 42.193,
+      "eval_steps_per_second": 21.097,
+      "step": 700
+    },
+    {
+      "epoch": 5.819912152269399,
+      "grad_norm": 0.12102068215608597,
+      "learning_rate": 4.140625e-05,
+      "loss": 0.8205,
+      "step": 750
+    },
+    {
+      "epoch": 5.819912152269399,
+      "eval_loss": 0.8489540219306946,
+      "eval_runtime": 10.252,
+      "eval_samples_per_second": 42.138,
+      "eval_steps_per_second": 21.069,
+      "step": 750
     }
   ],
   "logging_steps": 50,