Training in progress, step 3750, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca1d58e2cd18a1fc09601b5143bb78b5307a273e6e2f1750228c18041d7fe77e
+oid sha256:cb01dfc1c2e8ff7808bbee052468667857cd0cc81291988921d045c2d7906b09
 size 3809184360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9b3bc32af7a9c7224769cd6c49a9680aa7f8795c0d4e082d32018b4c599ff6
+oid sha256:21ad5221e1f7ef28d1eefb19cd0fee3fef5ece52f6f27106c14b5c6e4c86bc91
 size 2458291491

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8841fa7aad843ffcf2b76d868211d81553f8ce267313764fca81be4f5b42b4d
+oid sha256:8fdbd0a64c232d94ea2546e029d229e872e7990a092a5c5c86566d2492a53f3b
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c493c177a6a7b8f4b53d9f320f001568436248d37644f960edb69a4818ec2df
+oid sha256:64a6a4e6bbe43acf16ab43cab9cd60b8f70df5b08ce4b3f2a9b7397dc1ce58b0
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9333333333333333,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 3750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2458,6 +2458,181 @@
       "learning_rate": 3.436657681940701e-06,
       "loss": 0.1441,
       "step": 3500
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 9.182714462280273,
+      "learning_rate": 3.30188679245283e-06,
+      "loss": 0.2332,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 6.365874290466309,
+      "learning_rate": 3.1671159029649594e-06,
+      "loss": 0.1443,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9413333333333334,
+      "grad_norm": 6.266571521759033,
+      "learning_rate": 3.032345013477089e-06,
+      "loss": 0.1959,
+      "step": 3530
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 7.494802474975586,
+      "learning_rate": 2.8975741239892183e-06,
+      "loss": 0.149,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9466666666666667,
+      "grad_norm": 5.22160005569458,
+      "learning_rate": 2.762803234501348e-06,
+      "loss": 0.3431,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9493333333333334,
+      "grad_norm": 11.847735404968262,
+      "learning_rate": 2.628032345013477e-06,
+      "loss": 0.2068,
+      "step": 3560
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 41.45210647583008,
+      "learning_rate": 2.4932614555256068e-06,
+      "loss": 0.2057,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9546666666666667,
+      "grad_norm": 8.89501953125,
+      "learning_rate": 2.358490566037736e-06,
+      "loss": 0.5128,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9573333333333334,
+      "grad_norm": 6.3149261474609375,
+      "learning_rate": 2.223719676549865e-06,
+      "loss": 0.1869,
+      "step": 3590
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.511444091796875,
+      "learning_rate": 2.088948787061995e-06,
+      "loss": 0.2311,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9626666666666667,
+      "grad_norm": 6.782158851623535,
+      "learning_rate": 1.954177897574124e-06,
+      "loss": 0.1655,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9653333333333334,
+      "grad_norm": 6.828353404998779,
+      "learning_rate": 1.8194070080862537e-06,
+      "loss": 0.1694,
+      "step": 3620
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 2.4872541427612305,
+      "learning_rate": 1.6846361185983827e-06,
+      "loss": 0.1647,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9706666666666667,
+      "grad_norm": 8.890005111694336,
+      "learning_rate": 1.5498652291105121e-06,
+      "loss": 0.1979,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9733333333333334,
+      "grad_norm": 7.4598259925842285,
+      "learning_rate": 1.4150943396226415e-06,
+      "loss": 0.3526,
+      "step": 3650
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 4.237139701843262,
+      "learning_rate": 1.280323450134771e-06,
+      "loss": 0.2159,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9786666666666667,
+      "grad_norm": 5.643311500549316,
+      "learning_rate": 1.1455525606469004e-06,
+      "loss": 0.1425,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 7.4330267906188965,
+      "learning_rate": 1.0107816711590296e-06,
+      "loss": 0.1761,
+      "step": 3680
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 12.03699779510498,
+      "learning_rate": 8.76010781671159e-07,
+      "loss": 0.2607,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 6.911093235015869,
+      "learning_rate": 7.412398921832885e-07,
+      "loss": 0.1755,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9893333333333333,
+      "grad_norm": 6.668974876403809,
+      "learning_rate": 6.064690026954178e-07,
+      "loss": 0.2031,
+      "step": 3710
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 11.474651336669922,
+      "learning_rate": 4.7169811320754717e-07,
+      "loss": 0.2236,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9946666666666667,
+      "grad_norm": 9.00444507598877,
+      "learning_rate": 3.369272237196766e-07,
+      "loss": 0.1306,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9973333333333333,
+      "grad_norm": 52.68935012817383,
+      "learning_rate": 2.0215633423180594e-07,
+      "loss": 0.231,
+      "step": 3740
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.777242183685303,
+      "learning_rate": 6.738544474393531e-08,
+      "loss": 0.1794,
+      "step": 3750
     }
   ],
   "logging_steps": 10,
@@ -2472,12 +2647,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.32834922129408e+16,
+  "total_flos": 6.77976396217344e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null