Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321ec1fe961e5e3e9becad498e6f6297346b9690c8cb98f6f92a27bd24488dde
+oid sha256:d02277d45b5e739e97716ecccb7bffef29f004793ab213f53d88fd6667c40c9b
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c08720b84c8eef0050ad5e1cef857a9c7e430480350d885b1232630510302f1
+oid sha256:141a8ec4e5ec125405de7564bd7c9ce422dabdf58ed3d8198db51cfceb27faa5
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a427adcb42a5e21efe60aeff1fc331ce48c7ff904cf00d837fab2409ae1ed3f
+oid sha256:702327b551c4e20ef5af863061e25c1972735379504477c4bd2355e08bc4820d
 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": 0.005063291139240506,
+  "epoch": 0.007594936708860759,
   "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": 8.66,
       "eval_steps_per_second": 4.339,
       "step": 6
+    },
+    {
+      "epoch": 0.00590717299578059,
+      "grad_norm": 0.3555045425891876,
+      "learning_rate": 0.00014,
+      "loss": 2.464,
+      "step": 7
+    },
+    {
+      "epoch": 0.006751054852320675,
+      "grad_norm": 0.3778963088989258,
+      "learning_rate": 0.00016,
+      "loss": 2.2624,
+      "step": 8
+    },
+    {
+      "epoch": 0.007594936708860759,
+      "grad_norm": 0.4649808704853058,
+      "learning_rate": 0.00018,
+      "loss": 2.4903,
+      "step": 9
+    },
+    {
+      "epoch": 0.007594936708860759,
+      "eval_loss": 0.6111209988594055,
+      "eval_runtime": 57.5504,
+      "eval_samples_per_second": 8.671,
+      "eval_steps_per_second": 4.344,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4076840838758400.0,
+  "total_flos": 6115261258137600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null