Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76d432bdfd75388e2f2bf97e41cbffbd758bca422a8064692ccd7123cc35f5da
+oid sha256:b3b5bb327faeac62e7892e785eb64bce846806695269e440cb38927f5a0c61a3
 size 61226900

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0baaed0401940e242338532f7a22ba84c70eacc745fe31806e46807a8617d14a
+oid sha256:6d85e3216c9d23ea0904884a218dc46d117c269eb9122a8a493a3c4d28bba42f
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1b61f4c32eeed29fe12cabb7f194fe85997dd2fe781338dc8ff5784b7ccda29
+oid sha256:63fabb8ebd45581c1e1dd8e5806076cd4945d840d40d3cdd5ee1127201d878a5
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.44077134986225897,
+  "epoch": 0.5876951331496786,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 12.655,
       "eval_steps_per_second": 3.191,
       "step": 15
+    },
+    {
+      "epoch": 0.4701561065197429,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.4995408631772268,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.5289256198347108,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.5583103764921947,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.5876951331496786,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.5876951331496786,
+      "eval_loss": NaN,
+      "eval_runtime": 18.1756,
+      "eval_samples_per_second": 12.654,
+      "eval_steps_per_second": 3.191,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.770634359078912e+17,
+  "total_flos": 2.360845812105216e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null