Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d91c832b67c02aa33888ab224c025cb43af148cb1da4b1553a7c01333d38b303
+oid sha256:9a84a251ecd9c8fb67c63a59a8d224783f20b00322aa91714b6858fd0de1eb9d
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8181bbb6dbbe773b6043f4d0c1ba0a1b3a6b72812530d5f0820e8cb22570383
+oid sha256:6b51af41e21b1e50a7239889a0695d87b128e603cc3df58acf5c3bb469524745
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0546534403234975e-05,
+  "epoch": 0.00015163960320970494,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,64 @@
       "eval_samples_per_second": 41.83,
       "eval_steps_per_second": 20.915,
       "step": 3
+    },
+    {
+      "epoch": 6.739537920431331e-05,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 8.424422400539163e-05,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00010109306880646995,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.00010109306880646995,
+      "eval_loss": NaN,
+      "eval_runtime": 600.6945,
+      "eval_samples_per_second": 41.602,
+      "eval_steps_per_second": 20.801,
+      "step": 6
+    },
+    {
+      "epoch": 0.00011794191360754829,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.00013479075840862662,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.00015163960320970494,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.00015163960320970494,
+      "eval_loss": NaN,
+      "eval_runtime": 598.4315,
+      "eval_samples_per_second": 41.759,
+      "eval_steps_per_second": 20.88,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -63,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 97289477554176.0,
+  "total_flos": 291868432662528.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null