Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cb4c14e19057149a42043224fab6db52c49ae88a5c3c6e1afa5e2a8c0fd115
+oid sha256:ecb37b745c154e3b2563a1e0f9e6586a33244ec0c14de4916d4b241070d091d0
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a76311cb4017e091ca1493b14a0935d51b4c881cdc71b580db7c3e9ecf90952
+oid sha256:6e322f9b6f834c1ce38990f46347fee678aa3723da3b604d664c6685a7563e3b
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9908c81d4f08fa0707f543eeeb598037560bf300bf9c35b62655c74c41b96908
+oid sha256:6b51af41e21b1e50a7239889a0695d87b128e603cc3df58acf5c3bb469524745
 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": 0.0005951200158698671,
+  "epoch": 0.0008926800238048007,
   "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": 49.491,
       "eval_steps_per_second": 24.751,
       "step": 6
+    },
+    {
+      "epoch": 0.0006943066851815116,
+      "grad_norm": 2.329558849334717,
+      "learning_rate": 0.00014,
+      "loss": 3.6807,
+      "step": 7
+    },
+    {
+      "epoch": 0.0007934933544931561,
+      "grad_norm": 2.337567090988159,
+      "learning_rate": 0.00016,
+      "loss": 3.1091,
+      "step": 8
+    },
+    {
+      "epoch": 0.0008926800238048007,
+      "grad_norm": 3.2499704360961914,
+      "learning_rate": 0.00018,
+      "loss": 2.8589,
+      "step": 9
+    },
+    {
+      "epoch": 0.0008926800238048007,
+      "eval_loss": 3.16778302192688,
+      "eval_runtime": 84.2737,
+      "eval_samples_per_second": 50.372,
+      "eval_steps_per_second": 25.192,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 194578955108352.0,
+  "total_flos": 291868432662528.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null