Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da16b0e874343aca4c11d370c45917e6f162c63be579655f2d98600ad813541
+oid sha256:c9912261213232ce8c099cba98014c05e886d1a41269621ba9bdff32fb9b6469
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbadab122c5c0f7ffa8352df0bb2cf6ae56a1e473fbaee09e1a2facb6aab91e4
+oid sha256:461b97d6a4bc9b2c6becc83e18fecfc9b406d46a152ca7f71752a98bbb7b0e2f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
+oid sha256:204b783eee4578e262211ed4342a25463d72b9f2b43a34a1fb0c83abcbfcca96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13086150490730644,
+  "epoch": 0.19629225736095965,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.0001963525491562421,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.13740458015267176,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012653483024396533,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.15703380588876772,
+      "grad_norm": NaN,
+      "learning_rate": 6.183221215612904e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.15703380588876772,
+      "eval_loss": NaN,
+      "eval_runtime": 21.3055,
+      "eval_samples_per_second": 13.612,
+      "eval_steps_per_second": 4.553,
+      "step": 24
+    },
+    {
+      "epoch": 0.1766630316248637,
+      "grad_norm": NaN,
+      "learning_rate": 1.634902137174483e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.19629225736095965,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.977348285838131e+16,
+  "total_flos": 4.459896197716378e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null