Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a1a412b4417b09db633fe1f785b0a65830420fa8e4be125a617d4dd85fe1e62
+oid sha256:3ee4d05b4c02ed66326e99fd1df18389dddac6bc1c570fba5dfbc3d09285b0cf
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c421ca5210fe7fbd13a4fd15c9d33224cb6011c7cd232cfdd1ce8cfd025f2ac
+oid sha256:a849fa1d9941b3754ba370b3e6ee14ddb9dd082ae6fa641fd5377aa3bf63a516
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58172de5502b3aa1c59bc9671fc2db0288d4d215bc0e3ddf041f8963fc20488a
+oid sha256:bafe321b9c5a1744332ee7bfba8928cea1245498308304b39f58a86543bb739e
 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": 0.014268727705112961,
+  "epoch": 0.02140309155766944,
   "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": 81.506,
       "eval_steps_per_second": 40.753,
       "step": 6
+    },
+    {
+      "epoch": 0.016646848989298454,
+      "grad_norm": 22.75138282775879,
+      "learning_rate": 0.00014,
+      "loss": 10.3443,
+      "step": 7
+    },
+    {
+      "epoch": 0.019024970273483946,
+      "grad_norm": 26.50885772705078,
+      "learning_rate": 0.00016,
+      "loss": 11.268,
+      "step": 8
+    },
+    {
+      "epoch": 0.02140309155766944,
+      "grad_norm": 19.236141204833984,
+      "learning_rate": 0.00018,
+      "loss": 10.6174,
+      "step": 9
+    },
+    {
+      "epoch": 0.02140309155766944,
+      "eval_loss": 2.715468406677246,
+      "eval_runtime": 2.1818,
+      "eval_samples_per_second": 81.585,
+      "eval_steps_per_second": 40.793,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 63603210190848.0,
+  "total_flos": 100887850647552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null