Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2f25c5e8547502483de03a82d8261e785b99fb9c046b6e4be80d46f535fad1
+oid sha256:da9ca59cda04a48a7bc13f8f064118e5e390a24fbf9a17d3b21de5b8d0c169c5
 size 147781268

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64348d23d61878278ae4c95949a84a77e8b4d69045ab6dab8b3fed6a24d4fe6d
+oid sha256:e1807731d788099118091845b07fc2a28def49c3ade7b082b6ef3b856f918715
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01054713249835201,
+  "epoch": 0.015820698747528016,
   "eval_steps": 1,
-  "global_step": 4,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,36 @@
       "eval_samples_per_second": 7.654,
       "eval_steps_per_second": 3.827,
       "step": 4
+    },
+    {
+      "epoch": 0.013183915622940013,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.013183915622940013,
+      "eval_loss": NaN,
+      "eval_runtime": 20.9515,
+      "eval_samples_per_second": 7.637,
+      "eval_steps_per_second": 3.818,
+      "step": 5
+    },
+    {
+      "epoch": 0.015820698747528016,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.015820698747528016,
+      "eval_loss": NaN,
+      "eval_runtime": 21.0027,
+      "eval_samples_per_second": 7.618,
+      "eval_steps_per_second": 3.809,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -86,7 +116,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2598112623329280.0,
+  "total_flos": 3897168934993920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null