Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a3a1d4e26de45ce1a1d6f3fcc2f9080c7593fc8f9a99549892b999259373558
+oid sha256:a99fb2be30f9e2c0bd050de0fb659c66a374ed8bbf852a1b69f1c52beb5b662b
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459d0bdb85627d36604c66aca8fd43277b3ab782c361fe7160745f318b190065
+oid sha256:1de72d05e86641fcda9e96937025dcf4545ff9de4176a22a7cbef5519292c8b7
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
+oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008477569763334511,
+  "epoch": 0.012716354645001766,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 454.935,
       "eval_steps_per_second": 227.467,
       "step": 6
+    },
+    {
+      "epoch": 0.009890498057223597,
+      "grad_norm": 1.1208932399749756,
+      "learning_rate": 0.00014,
+      "loss": 44.2396,
+      "step": 7
+    },
+    {
+      "epoch": 0.01130342635111268,
+      "grad_norm": 1.0517933368682861,
+      "learning_rate": 0.00016,
+      "loss": 44.2893,
+      "step": 8
+    },
+    {
+      "epoch": 0.012716354645001766,
+      "grad_norm": 1.1171672344207764,
+      "learning_rate": 0.00018,
+      "loss": 44.331,
+      "step": 9
+    },
+    {
+      "epoch": 0.012716354645001766,
+      "eval_loss": 11.075115203857422,
+      "eval_runtime": 0.6817,
+      "eval_samples_per_second": 437.111,
+      "eval_steps_per_second": 218.556,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4482662400.0,
+  "total_flos": 6723993600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null