Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20920ab18906b5fa73f7d3693314c5c793cdc6f413b5a29ed65223545fc9f3d4
+oid sha256:a7601b3f7c8299d76d2a136a2ce058326c64ffeb29c0209bc9cf2957894be319
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a3cd302c87437cb41469bea150e2f77b2cc4e815063eb4e2162ecd368806335
+oid sha256:37db65d824a3946b9cc1aaf0fc91b7cf12f54e37178e10b9544ad15faee5dd1d
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c432173c3e03ab35f379f99e76ec96a95398876df77ad2334860facd5d9a0fd
+oid sha256:59870425f15b9c5b2c89fce32a5e0487ab127e9451b5309669abcf6644851b81
 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": 0.0006225519441778423,
+  "epoch": 0.0009338279162667636,
   "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": 50.207,
       "eval_steps_per_second": 25.104,
       "step": 6
+    },
+    {
+      "epoch": 0.000726310601540816,
+      "grad_norm": 1.1553844213485718,
+      "learning_rate": 0.00014,
+      "loss": 1.9767,
+      "step": 7
+    },
+    {
+      "epoch": 0.0008300692589037898,
+      "grad_norm": 1.0176719427108765,
+      "learning_rate": 0.00016,
+      "loss": 1.7407,
+      "step": 8
+    },
+    {
+      "epoch": 0.0009338279162667636,
+      "grad_norm": 1.0879982709884644,
+      "learning_rate": 0.00018,
+      "loss": 1.8643,
+      "step": 9
+    },
+    {
+      "epoch": 0.0009338279162667636,
+      "eval_loss": 1.9784159660339355,
+      "eval_runtime": 81.6761,
+      "eval_samples_per_second": 49.684,
+      "eval_steps_per_second": 24.842,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 71230531043328.0,
+  "total_flos": 109071750660096.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null