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:b120f2d1082aa749d7f55b25bb06e6f25effdbe3e562a09038d70066d72d89d8
+oid sha256:6d716729fcc92359abb6e9b40deaaa29f0e654c4bcf465144c21866046cc549e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947946d453ff958543c5437338e0ff3aecfa4fc26d93ecd182bb61610e883362
+oid sha256:b3549dffaef450f1d94abcea1fa09effcf291cb046f9c5ab5b49f61214a8a304
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2fe91e4b71ad96971401f0069a1c0bd726c6e3d3f180c7c5724b4adc2dcccdc
+oid sha256:7170a2d9b24ecc77552af509fa5ca848d0a66f21c29b073517cc02fd19368fe3
 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": 0.010291595197255575,
+  "epoch": 0.015437392795883362,
   "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": 15.294,
       "eval_steps_per_second": 7.647,
       "step": 6
+    },
+    {
+      "epoch": 0.012006861063464836,
+      "grad_norm": 18.84572982788086,
+      "learning_rate": 0.00014,
+      "loss": 7.9854,
+      "step": 7
+    },
+    {
+      "epoch": 0.0137221269296741,
+      "grad_norm": 16.23927116394043,
+      "learning_rate": 0.00016,
+      "loss": 5.275,
+      "step": 8
+    },
+    {
+      "epoch": 0.015437392795883362,
+      "grad_norm": 21.072099685668945,
+      "learning_rate": 0.00018,
+      "loss": 4.0998,
+      "step": 9
+    },
+    {
+      "epoch": 0.015437392795883362,
+      "eval_loss": 3.4490346908569336,
+      "eval_runtime": 16.0797,
+      "eval_samples_per_second": 15.299,
+      "eval_steps_per_second": 7.649,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 1664607823331328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null