Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0235e7ff8efed9c9306b23473829de670f7b5976122c45e007b8285545114a43
+oid sha256:b5f5cc161a91512901a16d0451aed799071f29b93aba05163a0f58ec74d8efec
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e300bddb0d7e7d6e026d32cddc3203212379cd7e7d4945e7775d35a028e0ce1f
+oid sha256:77820273899338f3cb44d8b61f14d2376760c84be6dcbd25e712a3423d224d4a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab098d97568c94b26c087e3ff4fd649c3aaa775049e6dbf18e927dde2c5feee8
+oid sha256:4abdd3b29509160214335978cbd2a63c87f2b7769a5608c5e772a6c51d699b65
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009578544061302681,
+  "epoch": 0.019157088122605363,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 0.0,
       "step": 5
+    },
+    {
+      "epoch": 0.011494252873563218,
+      "grad_norm": NaN,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.011494252873563218,
+      "eval_loss": NaN,
+      "eval_runtime": 24.832,
+      "eval_samples_per_second": 8.86,
+      "eval_steps_per_second": 4.43,
+      "step": 6
+    },
+    {
+      "epoch": 0.013409961685823755,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.01532567049808429,
+      "grad_norm": NaN,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.017241379310344827,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.017241379310344827,
+      "eval_loss": NaN,
+      "eval_runtime": 24.885,
+      "eval_samples_per_second": 8.841,
+      "eval_steps_per_second": 4.42,
+      "step": 9
+    },
+    {
+      "epoch": 0.019157088122605363,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +128,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1643164226027520.0,
+  "total_flos": 3286328452055040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null