Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bdc7cf740865fb1d8c048facba21652f00f116a73eeeb9585d5d52c82401667
+oid sha256:c3890dfc1fde83cfc27f250d0d23e480acffa260b99a1da89fe334349e9fd9eb
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f5b53745b74659ffcd33c52bbcc3cf7410024302c64b22bf689d37c6f52291
+oid sha256:bef29255c56d57747ac865abe12b2d4e86999d135f886601a4d530f98622aa86
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99a92fc5d469ae2e9aea728c1ef40552420e76ef90bd45072efd4ce87c57843e
+oid sha256:37c2591c788a196317d62c3707cd45db6be298de7eb35743b3ce78c85ba36598
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef58d5829883f07384e8c567510be5466d708878a0d13274af5f9ed6399d9a7e
+oid sha256:976a8370765eceef78baed512c4c1d93c0d7c89e92f9ad4ad75ff4e95a25bbff
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851937d40ae6d20d9cb2cc006d9792ad67529a12f11643c038037452a10911fc
+oid sha256:34374caeb9730942bf159925444951e14ea8b03d7e5cc146ddd7a6ab9733c2d9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa0f75a1f3e346be25756b578158b09a68943f0b9f1cfe29f97939687f864ef
+oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25622775800711745,
+  "epoch": 0.2846975088967972,
   "eval_steps": 4,
-  "global_step": 36,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -339,6 +339,42 @@
       "eval_samples_per_second": 32.939,
       "eval_steps_per_second": 4.169,
       "step": 36
+    },
+    {
+      "epoch": 0.26334519572953735,
+      "grad_norm": NaN,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.2704626334519573,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.2775800711743772,
+      "grad_norm": NaN,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.2846975088967972,
+      "grad_norm": NaN,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.2846975088967972,
+      "eval_loss": NaN,
+      "eval_runtime": 7.1924,
+      "eval_samples_per_second": 32.952,
+      "eval_steps_per_second": 4.171,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -358,7 +394,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0683176883270451e+17,
+  "total_flos": 1.1870196536967168e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null