Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:955adf8c4b458c57bbd1aac1bc895d7398ae3aa1b7c250ae2e091d005c426e88
+oid sha256:ca3903f897141ffd2387c79b5b610764fc719f42b1251f0411d688d0ef363b07
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424f739be4501cfe7d354e89eb7c2636e769fe1c10cff142c347b71521f5cff2
+oid sha256:59dfd7e3c5f47e9c59dd82d5934b354dca1792ccd6d53d936783c3e96fc445c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0001976577555961852,
+  "epoch": 0.0003953155111923704,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 53.43,
       "eval_steps_per_second": 26.719,
       "step": 3
+    },
+    {
+      "epoch": 0.00026354367412824697,
+      "grad_norm": 0.0,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0003294295926603087,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0003953155111923704,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0003953155111923704,
+      "eval_loss": NaN,
+      "eval_runtime": 120.0788,
+      "eval_samples_per_second": 53.223,
+      "eval_steps_per_second": 26.616,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26711449141248.0,
+  "total_flos": 53422898282496.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null