Training in progress, step 12, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8b908582542df2a292f3bb64a48d2a1c53d4c1e82708b7c3637e95baee25df6
+oid sha256:75c4551385431dfdc82f28d91a18f3e519edae20c75dc3e50a0705a36b3cb8a0
 size 18810036

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b3d87a829d09ba718b2a31b99c8b59b0bd0fc308b71a1cb52398ad5f4e39ac
+oid sha256:4967959e8851c5d28aa2bac805fef41d59582f9afffc3400db2f209b7aa2cdee
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de11e1523f429ed63a4f48e82acf6cabdd60ea1c016639e1cb3237df974fec1
+oid sha256:dfe8596e793c9868898cdf32c45d526c71b84747acc34fcd4850d4d300b785c9
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c4ce4d091756f12bab6bdc9cd40c04605bb3ee460b6a7d0066229771ebb2eb2
+oid sha256:65f96fac9738bd743d88f80ce88e146114dc2ab55ff1e159bd8b01a0222db339
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6481012658227848,
+  "epoch": 0.9721518987341772,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,42 @@
       "eval_samples_per_second": 42.237,
       "eval_steps_per_second": 10.559,
       "step": 8
+    },
+    {
+      "epoch": 0.7291139240506329,
+      "grad_norm": NaN,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": NaN,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.8911392405063291,
+      "grad_norm": NaN,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.9721518987341772,
+      "grad_norm": NaN,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.9721518987341772,
+      "eval_loss": NaN,
+      "eval_runtime": 1.9919,
+      "eval_samples_per_second": 42.171,
+      "eval_steps_per_second": 10.543,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -106,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9228215050567680.0,
+  "total_flos": 1.384232257585152e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null