Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c313d121b8cf9c1606b20dc305aa2ae5c6cbd999df1c7c19a1340a0661d4c75
+oid sha256:e1db613e106b9983b89219cf83629f9516be0f96c9a8b5c0a3eed1c8bcd3e198
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d499ff7fe1790e71b11c0ef861748c7fcc85d6a24176688edb62d3f1fff9a30
+oid sha256:4e6b68197fddf17e0ce735e75b95e18d5880320df13ec8e7d2862a1aa98a99ff
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a07c66a8bbda035c71637231362589b93f6d10c6d5ad4f8f3c1facfda53ac13
+oid sha256:653a7d79cc851bf5423ac30748a3285a94a397664d2f1baf19c62f5e6cbf4c2d
 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": 0.0010283657554203446,
+  "epoch": 0.0015425486331305167,
   "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": 15.317,
       "eval_steps_per_second": 7.661,
       "step": 6
+    },
+    {
+      "epoch": 0.0011997600479904018,
+      "grad_norm": 0.6433274149894714,
+      "learning_rate": 0.00014,
+      "loss": 4.9182,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013711543405604593,
+      "grad_norm": 0.6342811584472656,
+      "learning_rate": 0.00016,
+      "loss": 4.8562,
+      "step": 8
+    },
+    {
+      "epoch": 0.0015425486331305167,
+      "grad_norm": 0.8066439032554626,
+      "learning_rate": 0.00018,
+      "loss": 4.2763,
+      "step": 9
+    },
+    {
+      "epoch": 0.0015425486331305167,
+      "eval_loss": 1.21627676486969,
+      "eval_runtime": 160.4101,
+      "eval_samples_per_second": 15.317,
+      "eval_steps_per_second": 7.662,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2632959708364800.0,
+  "total_flos": 3906972470476800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null