Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6915cf39aa52369ab809622459bdf7175d673c5b329de0fca21af860c95bc2a7
+oid sha256:29ebe786966751a3e2c4268b3e706ec920024cc1a2eb0421160475771f3f5391
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46ed0df392b4fc0be5f0420fb317f012013f46218f2091eea915fb2c868e32e2
+oid sha256:f50aeb0a974d8d9c23bcc7726067ae57e79a6640cea27b805c7e421f49cf4aec
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8126f8f06e0a6d7e0707e196db5bb4addfa3cf453e563b330ebc28ce6cb3605
+oid sha256:db0b1940fafc234876afdb531814a14e95ce2f83f10415288be2b4dc6e65dc97
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b28ee0addfe1fdb5c9554035d0aace280dc61b8aded9640b8ddc91a063558e8
+oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.046296296296296294,
+  "epoch": 0.09259259259259259,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00027,
       "loss": 33.2546,
       "step": 9
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 1.129874348640442,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 33.2003,
+      "step": 12
+    },
+    {
+      "epoch": 0.06944444444444445,
+      "grad_norm": 1.220507264137268,
+      "learning_rate": 0.00025606601717798207,
+      "loss": 33.1562,
+      "step": 15
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "eval_loss": 11.024332046508789,
+      "eval_runtime": 0.22,
+      "eval_samples_per_second": 313.633,
+      "eval_steps_per_second": 159.089,
+      "step": 16
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 1.0811697244644165,
+      "learning_rate": 0.0001963525491562421,
+      "loss": 33.0782,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 155996651520.0,
+  "total_flos": 311993303040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null