Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb58dcbbb56776c9450d3d5d2425967faeb8e7a920a1c74be5648304520f6651
+oid sha256:e0217d39fe84bf27e83c028ca7655a66383ffbc9c6e3f31536586443e6ac11fb
 size 2610104820

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a9644db278dcc894d18f9f6e0ff6e334587d6c2090a87ceb4a205a4defbcab4
+oid sha256:2157d7f3e1f6d8b9edaf83e168ba9710c8bfcdb199b5a5195072c7d0414e8536
 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": 0.8300819396972656,
-  "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-1150",
-  "epoch": 9.0,
+  "best_metric": 0.8288983106613159,
+  "best_model_checkpoint": "mgh6/HTH_prob/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": 42.043,
       "eval_steps_per_second": 21.021,
       "step": 1150
+    },
+    {
+      "epoch": 9.304538799414349,
+      "grad_norm": 0.03284334018826485,
+      "learning_rate": 6.25e-06,
+      "loss": 0.7814,
+      "step": 1200
+    },
+    {
+      "epoch": 9.304538799414349,
+      "eval_loss": 0.8290355801582336,
+      "eval_runtime": 10.2771,
+      "eval_samples_per_second": 42.035,
+      "eval_steps_per_second": 21.018,
+      "step": 1200
+    },
+    {
+      "epoch": 9.694973157637872,
+      "grad_norm": 0.03288372978568077,
+      "learning_rate": 2.3437500000000002e-06,
+      "loss": 0.7919,
+      "step": 1250
+    },
+    {
+      "epoch": 9.694973157637872,
+      "eval_loss": 0.8288983106613159,
+      "eval_runtime": 10.2676,
+      "eval_samples_per_second": 42.074,
+      "eval_steps_per_second": 21.037,
+      "step": 1250
     }
   ],
   "logging_steps": 50,
@@ -375,7 +405,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }