Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be79793e97133d7f72190ed9a6a467fa4c271d9d64a4315b9cd6affa9b64b44
+oid sha256:f8699ffb7ddec90880f6858f8958c1b3b9dbdd986c33f01738cf0b3a623960eb
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab169778e4485cbaeac1b88ea77b7a4d77e00286773e7621048a49e1c071a217
+oid sha256:1d5b2963742215e113d7ee09023622abb4dbcc9bb796eb9925e1914a678b221d
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238d91f489adef697523368efde471946ec4962b97178a433b03cee9c743141e
+oid sha256:1094888e690d760f5dc6beb93863816b44facd96c60f74f3826e1336734dec25
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
+oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006291591046581972,
+  "epoch": 0.009437386569872959,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 51.711,
       "eval_steps_per_second": 25.855,
       "step": 26
+    },
+    {
+      "epoch": 0.007259528130671506,
+      "grad_norm": 2.896638870239258,
+      "learning_rate": 0.0002,
+      "loss": 5.5457,
+      "step": 30
+    },
+    {
+      "epoch": 0.009437386569872959,
+      "eval_loss": 1.4132994413375854,
+      "eval_runtime": 33.6179,
+      "eval_samples_per_second": 51.758,
+      "eval_steps_per_second": 25.879,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1007681745715200.0,
+  "total_flos": 1492861845504000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null