Training in progress, step 3104, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9f7918ab38db050be3a9dd669b4a4aa997e4e57f932ab8ea8b8f0d9c3d5f659
+oid sha256:2f83752452616cbd0ec0753eaf20e9c72241f5bcfd9d632ca202ecbffb9d78f8
 size 1917255968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3383ec5ad9f38bc04e190a337c2d0d9f8daec216c3f119a16ac6961ee52725b0
+oid sha256:f528f96812e9f223991da9868fc9a6eaf4ccb0794d4b9e94e0307de1f1907c32
 size 2479961379

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc13ab001c2da378e2756ece39f39d3895b380670aca5135bdf0d816e81afb69
+oid sha256:407a83273f352dc54c9ab1893170115347d1bdf347a8b3fc4e47f44848da4d88
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9318200112694197,
+  "epoch": 1.9987925621830476,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3104,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2115,6 +2115,76 @@
       "learning_rate": 1.5623773621572523e-07,
       "loss": 0.0739,
       "step": 3000
+    },
+    {
+      "epoch": 1.9382596796264993,
+      "grad_norm": 6.40625,
+      "learning_rate": 1.2791948759594553e-07,
+      "loss": 0.0698,
+      "step": 3010
+    },
+    {
+      "epoch": 1.9446993479835788,
+      "grad_norm": 9.8125,
+      "learning_rate": 1.0242389662981078e-07,
+      "loss": 0.0931,
+      "step": 3020
+    },
+    {
+      "epoch": 1.9511390163406586,
+      "grad_norm": 5.6875,
+      "learning_rate": 7.975385673529844e-08,
+      "loss": 0.1264,
+      "step": 3030
+    },
+    {
+      "epoch": 1.957578684697738,
+      "grad_norm": 3.484375,
+      "learning_rate": 5.991194066709838e-08,
+      "loss": 0.0872,
+      "step": 3040
+    },
+    {
+      "epoch": 1.9640183530548176,
+      "grad_norm": 3.140625,
+      "learning_rate": 4.2900400224615835e-08,
+      "loss": 0.0666,
+      "step": 3050
+    },
+    {
+      "epoch": 1.9704580214118974,
+      "grad_norm": 5.03125,
+      "learning_rate": 2.872116599644259e-08,
+      "loss": 0.0956,
+      "step": 3060
+    },
+    {
+      "epoch": 1.976897689768977,
+      "grad_norm": 3.734375,
+      "learning_rate": 1.7375847141248846e-08,
+      "loss": 0.0917,
+      "step": 3070
+    },
+    {
+      "epoch": 1.9833373581260565,
+      "grad_norm": 9.375,
+      "learning_rate": 8.865731205168205e-09,
+      "loss": 0.1889,
+      "step": 3080
+    },
+    {
+      "epoch": 1.9897770264831363,
+      "grad_norm": 2.46875,
+      "learning_rate": 3.1917839756784307e-09,
+      "loss": 0.0837,
+      "step": 3090
+    },
+    {
+      "epoch": 1.9962166948402156,
+      "grad_norm": 4.28125,
+      "learning_rate": 3.546493719946975e-10,
+      "loss": 0.0915,
+      "step": 3100
     }
   ],
   "logging_steps": 10,
@@ -2129,12 +2199,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.342450154710569e+17,
+  "total_flos": 2.4232838290224538e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null