Training in progress, step 7015, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df2826e51a98f935c3c5415c87fc52f37c766251c87cc698369ec49bc55ef9a0
+oid sha256:48b7b37e95e8573463459e9eafa2634c5269f255d9c2093c21184049ce7c33d0
 size 990185320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ddfba947f959e1fd5557c69dff82b6379d6f60723322d56890c683b4228b58
+oid sha256:94d561e5106e621f6afe5d07bd5ae6a7df12f841e7522432fc0a0f31fde0c7cd
 size 1980545291

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95bd9ab1c7e9753273a0ae2bd30c7d78806df297d6d3cd1a8399d815d6fb0e31
+oid sha256:516a1e5655fd3398094483c2d367b35710c21f319302cb826a24808d9ea0c6fa
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84045c99ef0177b5c0a69e814a8aa10201a5fe741a2c32087ca57acb77a74474
+oid sha256:ada1c192a6b9bc32d885bd0c7a1f372448823ac58bfe13232f861966d20bf313
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.846756949394155,
+  "epoch": 5.0,
   "eval_steps": 400,
-  "global_step": 6800,
+  "global_step": 7015,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -654,6 +654,20 @@
       "eval_samples_per_second": 9.079,
       "eval_steps_per_second": 1.135,
       "step": 6800
+    },
+    {
+      "epoch": 4.918032786885246,
+      "grad_norm": 3.7019028663635254,
+      "learning_rate": 8.2679971489665e-07,
+      "loss": 0.6544,
+      "step": 6900
+    },
+    {
+      "epoch": 4.989308624376337,
+      "grad_norm": 3.0245063304901123,
+      "learning_rate": 1.1404133998574484e-07,
+      "loss": 0.7076,
+      "step": 7000
     }
   ],
   "logging_steps": 100,
@@ -668,12 +682,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.8618253924368384e+16,
+  "total_flos": 1.92057231015936e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null