Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8888ebfcf72dd1c09323ce02035bf44a585c5ab9d04235e1f4b4c31817cd756f
+oid sha256:051e094100790644028ba2db283d3976b13b4d0ba87e0ea28eaa896870e1a710
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07581f904033a0ab370aa54c2129a6ac68fa8ec2896255f78437ac9a2520dc9f
+oid sha256:55743e330b33b6dab007b0a23ad920cc13acf142db90f3910f8e9a63b3040f5b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005743165632896853,
+  "epoch": 0.011486331265793705,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 18.576,
       "eval_steps_per_second": 9.293,
       "step": 50
+    },
+    {
+      "epoch": 0.006891798759476223,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 3.6482,
+      "step": 60
+    },
+    {
+      "epoch": 0.008040431886055594,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.436,
+      "step": 70
+    },
+    {
+      "epoch": 0.009189065012634964,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0954,
+      "step": 80
+    },
+    {
+      "epoch": 0.010337698139214336,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.011486331265793705,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.4721,
+      "step": 100
+    },
+    {
+      "epoch": 0.011486331265793705,
+      "eval_loss": NaN,
+      "eval_runtime": 98.6813,
+      "eval_samples_per_second": 18.575,
+      "eval_steps_per_second": 9.293,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8525445171511296.0,
+  "total_flos": 1.7226672717692928e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null