Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f18ddb439c416b303a327c63066b104029aae26ef95783736f89114e0ae568d7
+oid sha256:fdbca7497b61ec2477e990962d74f6bd97e79994647e64a4751791dccad4a0b5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d52990953d1b8a81a00b7cecfd9c211b1ca6db6b881889b76e3a32894320cdb
+oid sha256:529c9e51cf346c9538de8a198d0e350de38ac30f5061dd3c6b0f0716ac464501
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14857142857142858,
+  "epoch": 0.19047619047619047,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.0,
       "step": 35
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "eval_loss": NaN,
+      "eval_runtime": 6.9787,
+      "eval_samples_per_second": 15.906,
+      "eval_steps_per_second": 8.024,
+      "step": 40
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "eval_loss": NaN,
+      "eval_runtime": 6.9648,
+      "eval_samples_per_second": 15.937,
+      "eval_steps_per_second": 8.04,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6408340481507328.0,
+  "total_flos": 8215821130137600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null