Training in progress, step 45000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c3a41320d77f15c9a600c514111a9e25e4cbd36ae0205d94fa0c4cb342f789a
+oid sha256:c8a815a94d192095646a02d8b6a79105e9260920970fbe97d2aa19def46b4c90
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6c9fdfcdbc56237f182572da63342d4ff7b8e0b0e45095657eb0e743d19f6ce
+oid sha256:c02017f320f6b1caddf1618e07ec690b785b4a529ef34025e3e117b762e0fc78
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377a47bd0e88de4a26ae8d013d8cc57599e57dfed8febc9da0fea06bb8f5c79f
+oid sha256:2e270dd652a0994b32575b44314119dedc30073f859dfa0aeff422823bc4d4be
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c2f59490e3dd2b05891cf4a120f5b3dd4417dfcdb085e76dd005b201e1dc531
+oid sha256:5ee7ee57a2874715dabf5aac57b903a1055eceed18fa43649c597404d6a55c2f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.966666666666667,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 44500,
+  "global_step": 45000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3138,6 +3138,41 @@
       "learning_rate": 2.2933333333333335e-07,
       "loss": 0.0569,
       "step": 44500
+    },
+    {
+      "epoch": 2.9733333333333336,
+      "grad_norm": 0.1887609213590622,
+      "learning_rate": 1.848888888888889e-07,
+      "loss": 0.0479,
+      "step": 44600
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.19531774520874023,
+      "learning_rate": 1.4044444444444447e-07,
+      "loss": 0.0453,
+      "step": 44700
+    },
+    {
+      "epoch": 2.986666666666667,
+      "grad_norm": 0.3343108594417572,
+      "learning_rate": 9.6e-08,
+      "loss": 0.0503,
+      "step": 44800
+    },
+    {
+      "epoch": 2.993333333333333,
+      "grad_norm": 0.2250046730041504,
+      "learning_rate": 5.155555555555556e-08,
+      "loss": 0.053,
+      "step": 44900
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.10516126453876495,
+      "learning_rate": 7.111111111111112e-09,
+      "loss": 0.0502,
+      "step": 45000
     }
   ],
   "logging_steps": 100,
@@ -3152,12 +3187,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0839450451968e+17,
+  "total_flos": 1.096124203008e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null