Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fae6334833e7efe8070707b304b16d0998e10732791bd49f59560775a9f1c026
+oid sha256:e8794c561b31544f869366f25676607fbf0c30714cc0e300efdd0316f8abcc9d
 size 168149074

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2456464aa9b1df5819cd245fdae9e766ba71ea54353d58eeec5d8332638043f
+oid sha256:c7b41d0414f063913e8fa4ed2763406357e7ee2399d1133f6b24b1caee59c8df
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24771935e2cc6865e45cb9845fff8f5062a16e493718a5b8ceeb26de1bdafbf2
+oid sha256:394bc46780d76eee244df4255a9b39beee30de1da78f381b0fdf9eba1e0035bd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d34eaeb2ad1dc74afd65ebd73018346f4b2caf6f2283a8b4e637b1352adae7
+oid sha256:694311e029126c23d613c63196baa49e57f5b701aaaca36f6d24271f0de77526
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c2ae561cd1fc3959c94f2f041a08b6a9b8b3c9c542c85c5998ad25875523a7
+oid sha256:890b133b77d6e29dcc5d6e5427bf0b09b8270be6f6b5fa05b57fdc0126b0d2b2
 size 15024

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": 0.07142857142857142,
+  "epoch": 0.14285714285714285,
   "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": 30.3,
       "eval_steps_per_second": 7.575,
       "step": 3
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "eval_loss": NaN,
+      "eval_runtime": 1.1268,
+      "eval_samples_per_second": 31.948,
+      "eval_steps_per_second": 7.987,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4438954195550208.0,
+  "total_flos": 8877908391100416.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null