Training in progress, step 63, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ebaaeb09b4a79510f6b1cf4fa25839833b63b5c128c08ebcca2bb31063ff910
+oid sha256:ebca97e9fd3ccc847bc041f65eaf2dd5ef3ef75a755dbc12a481d1e23e63943b
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebb71260a7dcaddefac8cc5b9550679bc1d61957461bab473d931b6f3791d6db
+oid sha256:63eb6e69f6f7d9904bc94aeeed5d2d905f7e153a3f6407edf275ba5537bef7d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
+oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07055653097056061,
+  "epoch": 0.08231595279898739,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 5.869,
       "eval_steps_per_second": 2.934,
       "step": 54
+    },
+    {
+      "epoch": 0.07447633824670287,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011175373974578378,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.07839614552284513,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.08231595279898739,
+      "grad_norm": NaN,
+      "learning_rate": 8.824626025421626e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.08231595279898739,
+      "eval_loss": NaN,
+      "eval_runtime": 639.1005,
+      "eval_samples_per_second": 4.034,
+      "eval_steps_per_second": 2.017,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.5233150845976576e+17,
+  "total_flos": 6.443867598697267e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null