Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b36c9471045998dc6ad7ee4cc2aeaaefdf3d7a9d28a0cd9c73fd2c71767f171
+oid sha256:015c50ef3cde554cb45fca70e293899004f8c74f38fe544b92ee6cb8590f1c23
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eeb36ac22e168f2791b1d42d9a549e8a5fbb6edbd445e239c7b0078ddc1aa5a
+oid sha256:705f923f250e4cf34713454dca4260a74ca588c8ae26ba728c768e0fda6447b8
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1c4787f018a3c9e54b5e79ac2c75cee94a09ef16036a89d6aba6538b3bb7ab
+oid sha256:10d0c02e3e01cb40066e614c88f8501c0a7503da6a695a0a7c21dcc6749a0bb7
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5d7003fbeece0ada81f421f3f56f766cbc81de1969abfff4e2967e108e8909
+oid sha256:c330d623accbcedfeb643ae851caa657e0812de23ec84a3194c1294e13bd1b0f
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:980a9ecbf3277df9f2b030642ae90342406f96444773adebef3d7ebf41969890
+oid sha256:8f9525251bc4e9d90d7d701e292e353aed7200d16ad9e83c22a6eb9c7ee071f4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.000599999999999,
+  "epoch": 2.999133333333333,
   "eval_steps": 500,
-  "global_step": 29500,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4138,6 +4138,76 @@
       "learning_rate": 2.2379155141950547e-08,
       "loss": 0.7814482879638672,
       "step": 29500
+    },
+    {
+      "epoch": 1.0016666666666667,
+      "grad_norm": 1.808127522468567,
+      "learning_rate": 1.8230180538784115e-08,
+      "loss": 0.5795806884765625,
+      "step": 29550
+    },
+    {
+      "epoch": 1.0033333333333334,
+      "grad_norm": 1.9930639266967773,
+      "learning_rate": 1.4505979828129401e-08,
+      "loss": 0.6081678390502929,
+      "step": 29600
+    },
+    {
+      "epoch": 1.005,
+      "grad_norm": 2.1188387870788574,
+      "learning_rate": 1.1206658601197185e-08,
+      "loss": 0.595140495300293,
+      "step": 29650
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 2.0174291133880615,
+      "learning_rate": 8.332310402714427e-09,
+      "loss": 0.579749412536621,
+      "step": 29700
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 2.3788022994995117,
+      "learning_rate": 5.883016728259749e-09,
+      "loss": 0.6074051284790039,
+      "step": 29750
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 1.9448168277740479,
+      "learning_rate": 3.858847021970258e-09,
+      "loss": 0.5630842208862304,
+      "step": 29800
+    },
+    {
+      "epoch": 1.0116666666666667,
+      "grad_norm": 2.65925669670105,
+      "learning_rate": 2.25985867455647e-09,
+      "loss": 0.6157372665405273,
+      "step": 29850
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 2.4260473251342773,
+      "learning_rate": 1.086097021681942e-09,
+      "loss": 0.8739725494384766,
+      "step": 29900
+    },
+    {
+      "epoch": 1.015,
+      "grad_norm": 2.43849515914917,
+      "learning_rate": 3.375953426842937e-10,
+      "loss": 0.8965128326416015,
+      "step": 29950
+    },
+    {
+      "epoch": 2.0004,
+      "grad_norm": 1.4195460081100464,
+      "learning_rate": 1.437485961597318e-11,
+      "loss": 0.7812672424316406,
+      "step": 30000
     }
   ],
   "logging_steps": 50,
@@ -4152,12 +4222,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.657073497418203e+18,
+  "total_flos": 2.704080406538674e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null