Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:860af7f59f0bb7511236cd4cffa6d9502cb9cca82d5d25e947b67aec557d2e96
+oid sha256:172a2d2df9217845dc5eed7be99b3b1d88c8ad57bb5e4778673af07ba0223edb
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbff0a2488cd60a2dc59aa274e511151b01dfa31e027531070467d558a1d0d28
+oid sha256:b32514f59643a512c840363f4d21054ffbe51751e47eee08d8a865fddb8715b0
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a8fbdd40f7edc9d5266c41a92e911a33f810a381088729bf4c84d9fe8f8cfae
+oid sha256:15bb659d872e51cdcf51d1386f1d5644386953ebd4919b30d517a420347b48ff
 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": 0.028070175438596492,
+  "epoch": 0.042105263157894736,
   "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": 36.639,
       "eval_steps_per_second": 18.319,
       "step": 6
+    },
+    {
+      "epoch": 0.03274853801169591,
+      "grad_norm": 1.0808058977127075,
+      "learning_rate": 0.00014,
+      "loss": 1.0512,
+      "step": 7
+    },
+    {
+      "epoch": 0.03742690058479532,
+      "grad_norm": 0.93768709897995,
+      "learning_rate": 0.00016,
+      "loss": 0.7952,
+      "step": 8
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.7182030081748962,
+      "learning_rate": 0.00018,
+      "loss": 0.6028,
+      "step": 9
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "eval_loss": 0.8555219769477844,
+      "eval_runtime": 2.3883,
+      "eval_samples_per_second": 37.684,
+      "eval_steps_per_second": 18.842,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 312560831692800.0,
+  "total_flos": 475092464173056.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null