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:b6461e1ab6b31231a16c7570773b49510657f317227243d78306e21c749cee96
+oid sha256:6eaa81a275e1ab565d302607e164c226e464b36aab55a3a3b1f2ad6e84d74243
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c7a9bded82e862989792f0e466cbd3581f6502b5884bb8ad1e8aca4fa2a94a
+oid sha256:10816abf3249cbe7ae5313e8c37ab079f4a1dd883870af919e0d9ef78b6d8ba9
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b91b616bd452b894e1aea50022754f9be4afc2c867b79623be361a63b980b2
+oid sha256:df2eff7fc04c424d03efebb207948c12df40c4005d61c167cc0982b8e6c469d5
 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": 0.2663115845539281,
+  "epoch": 0.3994673768308921,
   "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": 363.671,
       "eval_steps_per_second": 182.979,
       "step": 100
+    },
+    {
+      "epoch": 0.2929427430093209,
+      "grad_norm": 1.1754047870635986,
+      "learning_rate": 0.0002,
+      "loss": 43.9785,
+      "step": 110
+    },
+    {
+      "epoch": 0.3195739014647137,
+      "grad_norm": 0.8138487935066223,
+      "learning_rate": 0.0002,
+      "loss": 43.9158,
+      "step": 120
+    },
+    {
+      "epoch": 0.34620505992010653,
+      "grad_norm": 0.9201197028160095,
+      "learning_rate": 0.0002,
+      "loss": 43.9227,
+      "step": 130
+    },
+    {
+      "epoch": 0.37283621837549935,
+      "grad_norm": 0.8453980088233948,
+      "learning_rate": 0.0002,
+      "loss": 43.9068,
+      "step": 140
+    },
+    {
+      "epoch": 0.3994673768308921,
+      "grad_norm": 0.8276954293251038,
+      "learning_rate": 0.0002,
+      "loss": 43.7968,
+      "step": 150
+    },
+    {
+      "epoch": 0.3994673768308921,
+      "eval_loss": 10.950996398925781,
+      "eval_runtime": 0.4461,
+      "eval_samples_per_second": 356.405,
+      "eval_steps_per_second": 179.323,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 143445196800.0,
+  "total_flos": 215167795200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null