Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a29143396eec77d41eb67970e181bc16a75b0dbc3fc41d874e883a617b530f
+oid sha256:66d2c365888e94adeb34ffb08be4fd0fbc6c9aaafbb0f9223c03b74badcf8549
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36523e64f00628b69639a58b0773985da9c069029b6cd768dfa76d4a8b7484ca
+oid sha256:5d173da94f057cebe46d0a1e5df31b658bc3d4959580324db25d612ea813edfc
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea48777c657ab2eaff790b1967aab8c9a1afa8e0f83ce703776ac81a04df427
+oid sha256:43b2971c682d61298ab3991ff3f259b2ef851121b7e934377ddee6fa1d983bcd
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:271b74e66e71309f5334c1d7cc17a4a6232d396cc34f548747450ef9fdb432db
+oid sha256:4d23c39b874cb2dab81b1fbd3da207d04e909b5804b67c2c64089952d7e54286
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84a0942ceea86ba4bd54997340637a60ac64ad5dfb513f2f4420905351033838
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 44.61538461538461,
+  "epoch": 46.15384615384615,
   "eval_steps": 40,
-  "global_step": 580,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -533,6 +533,28 @@
       "learning_rate": 6.069322682050516e-07,
       "loss": 9.1766,
       "step": 580
+    },
+    {
+      "epoch": 45.38461538461539,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.518483566683826e-07,
+      "loss": 9.1785,
+      "step": 590
+    },
+    {
+      "epoch": 46.15384615384615,
+      "grad_norm": 0.419921875,
+      "learning_rate": 0.0,
+      "loss": 9.1762,
+      "step": 600
+    },
+    {
+      "epoch": 46.15384615384615,
+      "eval_loss": 9.19438362121582,
+      "eval_runtime": 5.3128,
+      "eval_samples_per_second": 282.527,
+      "eval_steps_per_second": 4.517,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -547,12 +569,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 237311958712320.0,
+  "total_flos": 245495129702400.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null