Training in progress, step 6, checkpoint

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a397d93afdbc96ba0c9ac212a5a50ede0190844c4a9268376265824f5a80b28d
+oid sha256:3f9b0aecdcbc1ef6a985202ad21c9afbb7a09e1136b808cb6d87b5484ee23420
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2dc5577a643196cfe630d8e2debe20ea0df8f5f98273f54c6d0704d40f551ab
+oid sha256:cbb84b305596fb3cc68795959f612d65e961ddfa0d366482534e89f8bd43f72d
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2eb052c49d073768e9b65ee3e9658972469bcfd89271b686e0b8b61ad99b28
+oid sha256:b1b1f4135482f8e6ab4c0bff25845dd231f3f6afd4b40b094907ed59535b63ae
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa10bd234a63a80835e649004ba79149ae74b79f9f7c9078b18fb61fc7761bf
+oid sha256:ace520f7f3a46e3992e2ff8814c09d5ebddf402f03204522349e0d7986ebeca1
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380b3e8ce512b1b99a4f205745d31f2e2692c0f0c0e60658b36efd9ea6c889a6
+oid sha256:8967b93bee541d58b2b16421a6b30a92c947d8c673b2f45392097ce8f3475830
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd90fa9cda39aaf4bbaa39c52bc3b96e93174995905cb613a0e6f2e7ee800dac
+oid sha256:cafd580388905e923d76cd19c2e149d4fa189b205109f9f6c9d69ad4bc0d4323
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72357f2d607e499b251630bcb12e2c2f0918a323b1a9596950eafb3601a20cb8
+oid sha256:97e943462f993b4c6778bc1a0b01c1aa85f59cb7b1b0924507ba3f0fde50d1f8
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa472eb1369c4aafcc0d0acca1378910fe5aebb270f08358f969f2933d9ffc67
+oid sha256:e4930ab50d16eef8d85da54c9a267fe9bccb1ada8d6a69507ea0e2cb66b9e22d
 size 15984

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00038652322360368483,
+  "epoch": 0.0007730464472073697,
   "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": 267.434,
       "eval_steps_per_second": 33.429,
       "step": 3
+    },
+    {
+      "epoch": 0.0005153642981382464,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 2.6969,
+      "step": 4
+    },
+    {
+      "epoch": 0.0006442053726728081,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 2.7296,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007730464472073697,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 3.0787,
+      "step": 6
+    },
+    {
+      "epoch": 0.0007730464472073697,
+      "eval_loss": 3.1917941570281982,
+      "eval_runtime": 48.3147,
+      "eval_samples_per_second": 270.559,
+      "eval_steps_per_second": 33.82,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 333210206601216.0,
+  "total_flos": 666420413202432.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null