Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b2449d036e321d75029d8a603b7ec82ea56a1879ce0d9c7638a3dba7df98c52
+oid sha256:d4a60181abd8dd48a0aa55cde466f4e006a2b09feb9c5d451390574c934ce6f4
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1a7590c797c9f1d40294cfce6ffb400b297dc67bf1d6c158f9069f9c76d25f
+oid sha256:f0cf20bcbd53de28d17f237aeb3d333935f86a0c8c0411dcbca3f530bdb77a91
 size 52499200

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": null,
   "best_model_checkpoint": null,
-  "epoch": 9.0,
+  "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,
@@ -329,6 +329,34 @@
       "eval_samples_per_second": 21.856,
       "eval_steps_per_second": 5.464,
       "step": 1150
+    },
+    {
+      "epoch": 9.304538799414349,
+      "grad_norm": 154307.0,
+      "learning_rate": 6.25e-06,
+      "loss": 275.3413,
+      "step": 1200
+    },
+    {
+      "epoch": 9.304538799414349,
+      "eval_runtime": 19.7645,
+      "eval_samples_per_second": 21.857,
+      "eval_steps_per_second": 5.464,
+      "step": 1200
+    },
+    {
+      "epoch": 9.694973157637872,
+      "grad_norm": 77167.2265625,
+      "learning_rate": 2.3437500000000002e-06,
+      "loss": 241.9685,
+      "step": 1250
+    },
+    {
+      "epoch": 9.694973157637872,
+      "eval_runtime": 19.7657,
+      "eval_samples_per_second": 21.856,
+      "eval_steps_per_second": 5.464,
+      "step": 1250
     }
   ],
   "logging_steps": 50,
@@ -343,7 +371,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }