Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697f816d0621c0d00e8e0ca9fe72e8fdd524ca12acf84d2e3bd927115c5c70e9
+oid sha256:a0bcec12c0a1fb6c8ef45fcba96ed788601918fd8ce201c4fd178411dc5bd310
 size 2433024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e1d534960590164150b98a4eca7e5d48f9e8072cfbd3c56be0575735e0c5b5
+oid sha256:86cdaaa9d7dcd5919660434789db9112aa69866e9fe9c4a368f52f5724f61694
 size 2498406

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf1f53caaa12767db3c6df563992bbf88f4b84dc57ec5080b22deb9c2c56ec6e
+oid sha256:7b204b20cdc92a140e2e21e015bdaa04af008c00e0bde30e59edf0f23817a338
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7102693104468778,
+  "epoch": 0.7398638650488311,
   "eval_steps": 200,
-  "global_step": 2400,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1791,6 +1791,76 @@
       "eval_samples_per_second": 40.85,
       "eval_steps_per_second": 10.226,
       "step": 2400
+    },
+    {
+      "epoch": 0.7132287659070731,
+      "grad_norm": 0.498046875,
+      "learning_rate": 7.078065009060941e-07,
+      "loss": 10.4885,
+      "step": 2410
+    },
+    {
+      "epoch": 0.7161882213672685,
+      "grad_norm": 0.50390625,
+      "learning_rate": 5.593931933399854e-07,
+      "loss": 10.5281,
+      "step": 2420
+    },
+    {
+      "epoch": 0.7191476768274637,
+      "grad_norm": 0.78125,
+      "learning_rate": 4.2837911263562404e-07,
+      "loss": 10.4985,
+      "step": 2430
+    },
+    {
+      "epoch": 0.7221071322876591,
+      "grad_norm": 0.6328125,
+      "learning_rate": 3.1478718246357173e-07,
+      "loss": 10.6174,
+      "step": 2440
+    },
+    {
+      "epoch": 0.7250665877478544,
+      "grad_norm": 0.99609375,
+      "learning_rate": 2.1863727812254653e-07,
+      "loss": 10.7935,
+      "step": 2450
+    },
+    {
+      "epoch": 0.7280260432080498,
+      "grad_norm": 0.51953125,
+      "learning_rate": 1.3994622306173765e-07,
+      "loss": 10.5046,
+      "step": 2460
+    },
+    {
+      "epoch": 0.730985498668245,
+      "grad_norm": 0.484375,
+      "learning_rate": 7.872778593728258e-08,
+      "loss": 10.5646,
+      "step": 2470
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.6953125,
+      "learning_rate": 3.499267820307184e-08,
+      "loss": 10.5978,
+      "step": 2480
+    },
+    {
+      "epoch": 0.7369044095886357,
+      "grad_norm": 0.6484375,
+      "learning_rate": 8.748552236603757e-09,
+      "loss": 10.6151,
+      "step": 2490
+    },
+    {
+      "epoch": 0.7398638650488311,
+      "grad_norm": 1.140625,
+      "learning_rate": 0.0,
+      "loss": 10.6938,
+      "step": 2500
     }
   ],
   "logging_steps": 10,
@@ -1805,12 +1875,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 235181703168.0,
+  "total_flos": 244972781568.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null