Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:436fb53485955b91754ed1aa8da84143064d32cf13f93500fa1bc5b479d5e530
+oid sha256:76d432bdfd75388e2f2bf97e41cbffbd758bca422a8064692ccd7123cc35f5da
 size 61226900

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1450fd405ce8a996f339e682fa4c71d4f050ed00d5cbf4d5e0f307f00c576bf7
+oid sha256:0baaed0401940e242338532f7a22ba84c70eacc745fe31806e46807a8617d14a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e43168a4d54e6ce53a8ab9259c7a5d142fb95551b7b745174f485aa526807e
+oid sha256:e1b61f4c32eeed29fe12cabb7f194fe85997dd2fe781338dc8ff5784b7ccda29
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2938475665748393,
+  "epoch": 0.44077134986225897,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 12.655,
       "eval_steps_per_second": 3.191,
       "step": 10
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.3526170798898072,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.3820018365472911,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.411386593204775,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.44077134986225897,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.44077134986225897,
+      "eval_loss": NaN,
+      "eval_runtime": 18.175,
+      "eval_samples_per_second": 12.655,
+      "eval_steps_per_second": 3.191,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.180422906052608e+17,
+  "total_flos": 1.770634359078912e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null