Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a8ddc19eb71baa5819594f50ff1d10e2ef8f9a558a1e809c1af285c22208ef
+oid sha256:4f8009fdc806005f5a11dfe3d501909749d95aec61cb68fbf25b5adf49c5f6f1
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a42e3237e0828dd78e8556d6bc1b0846c64c71da0237055654d6fad4b9b1041
+oid sha256:0e2eea5917a4ae9c226361c7f5f807e0ab64ce5ea6340ca776c63d8f38a07203
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025364616360177554,
+  "epoch": 0.033819488480236734,
   "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": 11.138,
       "eval_steps_per_second": 5.569,
       "step": 150
+    },
+    {
+      "epoch": 0.027055590784189388,
+      "grad_norm": NaN,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 67.0935,
+      "step": 160
+    },
+    {
+      "epoch": 0.028746565208201225,
+      "grad_norm": NaN,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 0.2994,
+      "step": 170
+    },
+    {
+      "epoch": 0.030437539632213063,
+      "grad_norm": NaN,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 79.1237,
+      "step": 180
+    },
+    {
+      "epoch": 0.0321285140562249,
+      "grad_norm": NaN,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.7457,
+      "step": 190
+    },
+    {
+      "epoch": 0.033819488480236734,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 72.2216,
+      "step": 200
+    },
+    {
+      "epoch": 0.033819488480236734,
+      "eval_loss": NaN,
+      "eval_runtime": 223.7147,
+      "eval_samples_per_second": 11.13,
+      "eval_steps_per_second": 5.565,
+      "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": 9.51193937903616e+16,
+  "total_flos": 1.268523024777216e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null