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:e79bc44ab877622017dce04dd19ef4258722e75d1de98c96251c12b409b82104
+oid sha256:9362dfe5b12fccd1d7c4e883933f359b4a5a93323ff324212c0ae76b489cb706
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2def98ff3fd0dfc26af8d4025858ece5b9bf950a7c04cd72572f940729debf5
+oid sha256:166017f4d27e9e6e9f038985033b0393663d867a7be2888c873b757d43864155
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0487bfb89a9431459512945db445fb6a7eebafe77f5238e31ca39145f2b035a9
+oid sha256:1d19bc63f2e461b259ea29712943b7f82b3b557c494d13d97c480a3eab868a91
 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": 0.0037002775208140612,
+  "epoch": 0.005550416281221091,
   "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": 20.82,
       "eval_steps_per_second": 10.425,
       "step": 6
+    },
+    {
+      "epoch": 0.004316990440949738,
+      "grad_norm": 6.540224552154541,
+      "learning_rate": 0.00014,
+      "loss": 9.095,
+      "step": 7
+    },
+    {
+      "epoch": 0.004933703361085414,
+      "grad_norm": 5.252821445465088,
+      "learning_rate": 0.00016,
+      "loss": 5.8836,
+      "step": 8
+    },
+    {
+      "epoch": 0.005550416281221091,
+      "grad_norm": 13.80943489074707,
+      "learning_rate": 0.00018,
+      "loss": 5.7512,
+      "step": 9
+    },
+    {
+      "epoch": 0.005550416281221091,
+      "eval_loss": 1.355873942375183,
+      "eval_runtime": 32.811,
+      "eval_samples_per_second": 20.816,
+      "eval_steps_per_second": 10.423,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1332361122576384.0,
+  "total_flos": 1980536803829760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null