Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e0cd5296079ffc15a035b3eca454f686d69c252d72318c2fd10c1e9c5486d2
+oid sha256:4c364696c4e48cb0a64b22c97bcf1034859015edee13664cee55fa74a9fdee03
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8842814fcbb5bf82c20ef3e8fe248730f63f6eea210e672a9d5639a70f212f0
+oid sha256:ca4bbcd7e604761a5f8062bde9187e12afaf4e5dd8fef116bef3e8bcbb57aade
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014563460278162091,
+  "epoch": 0.019417947037549455,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 28.137,
       "eval_steps_per_second": 14.072,
       "step": 150
+    },
+    {
+      "epoch": 0.015534357630039564,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.9052,
+      "step": 160
+    },
+    {
+      "epoch": 0.016505254981917038,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.01747615233379451,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.01844704968567198,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 15.7935,
+      "step": 190
+    },
+    {
+      "epoch": 0.019417947037549455,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0935,
+      "step": 200
+    },
+    {
+      "epoch": 0.019417947037549455,
+      "eval_loss": NaN,
+      "eval_runtime": 154.0929,
+      "eval_samples_per_second": 28.145,
+      "eval_steps_per_second": 14.076,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.150425749664563e+16,
+  "total_flos": 4.166974809361613e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null