Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb5d64611e9393823802e84b732b234bfbced5fbf177db8a8894d13eda15ea9
+oid sha256:c2286226470da6d60425fcfe468092ef768c8b9085963373fbde4074da799a63
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b086b6d64d9ce798d2d28fefbfd0f84466871aaa0a37bd1b856d1912a4ab8645
+oid sha256:d11b4da0ba3a3f5ea5741ff5a23e38f5ac52788510f476693b7ee16153d7de87
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79791411d71c1113ecebaa01b1bfad87290258ad79fdc9d6745b07f0639a2399
+oid sha256:931c4cb6691233616bf5b1c6107fffe0dba00db02219ee36d8d78aa2418d5343
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04395121415229096,
+  "epoch": 0.06592682122843643,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 18.183,
       "eval_steps_per_second": 9.101,
       "step": 100
+    },
+    {
+      "epoch": 0.048346335567520056,
+      "grad_norm": 2.872164011001587,
+      "learning_rate": 0.0002,
+      "loss": 0.4823,
+      "step": 110
+    },
+    {
+      "epoch": 0.052741456982749145,
+      "grad_norm": 1.444300889968872,
+      "learning_rate": 0.0002,
+      "loss": 0.3751,
+      "step": 120
+    },
+    {
+      "epoch": 0.05713657839797824,
+      "grad_norm": 6.023801803588867,
+      "learning_rate": 0.0002,
+      "loss": 0.4278,
+      "step": 130
+    },
+    {
+      "epoch": 0.06153169981320734,
+      "grad_norm": 5.9031782150268555,
+      "learning_rate": 0.0002,
+      "loss": 0.2955,
+      "step": 140
+    },
+    {
+      "epoch": 0.06592682122843643,
+      "grad_norm": 4.795778274536133,
+      "learning_rate": 0.0002,
+      "loss": 0.282,
+      "step": 150
+    },
+    {
+      "epoch": 0.06592682122843643,
+      "eval_loss": 0.07622317224740982,
+      "eval_runtime": 52.8602,
+      "eval_samples_per_second": 18.142,
+      "eval_steps_per_second": 9.081,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.626358152790016e+16,
+  "total_flos": 3.888638815371264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null