Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:103a96ef37cb357fa5c1052bbbc4b2a7dd59f64e361fb5446389e16a531c1ecf
+oid sha256:e3cd50213d58781172ab45a966c225c15475c6da900dc1f0cf934b4537db3df0
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a19b9686ca77be999f83e9ddc33bdff77a178a1e2335119c75e0808cb3a74244
+oid sha256:40bfb7a2bb9e09979ca0850fe7db152528103f342b31a7d7161ea872baf3db7f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014234875444839857,
+  "epoch": 0.028469750889679714,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 12.342,
       "eval_steps_per_second": 1.543,
       "step": 5
+    },
+    {
+      "epoch": 0.01708185053380783,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.025622775800711744,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.028469750889679714,
+      "eval_loss": NaN,
+      "eval_runtime": 48.0728,
+      "eval_samples_per_second": 12.315,
+      "eval_steps_per_second": 1.539,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8886804283392000.0,
+  "total_flos": 1.7773608566784e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null