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:e5a662cf0d698b2160e7c2d951b2e7980570d88aba9ddedaccc6ea265e083495
+oid sha256:24616924943a6f3ccbeedb41c498b680225ea3f4456b6939e2435c501d186344
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc2c85e02953fbfd03308fa3f1857cffd7d9e6a00b49c6d551534aa884128bf
+oid sha256:84524474f3e23eb217898e6a07bfcffd330ba7927d061a39e9a098234b3924cf
 size 52046596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:636274c6e62fd2fc06507e9257836f6068e600de02c02f4ed1fdb7155a1b6608
+oid sha256:2bc758cdf54cfc640ea7dfa079c4a2d02488281639614f10e41e866a95706831
 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": 0.00045974369289121313,
+  "epoch": 0.0006896155393368198,
   "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": 3.661,
       "eval_steps_per_second": 1.831,
       "step": 6
+    },
+    {
+      "epoch": 0.0005363676417064154,
+      "grad_norm": 1.934218406677246,
+      "learning_rate": 0.00014,
+      "loss": 0.3667,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006129915905216175,
+      "grad_norm": 1.2223925590515137,
+      "learning_rate": 0.00016,
+      "loss": 0.2294,
+      "step": 8
+    },
+    {
+      "epoch": 0.0006896155393368198,
+      "grad_norm": 1.2483911514282227,
+      "learning_rate": 0.00018,
+      "loss": 0.136,
+      "step": 9
+    },
+    {
+      "epoch": 0.0006896155393368198,
+      "eval_loss": 0.08404787629842758,
+      "eval_runtime": 1502.7204,
+      "eval_samples_per_second": 3.657,
+      "eval_steps_per_second": 1.829,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3951230409768960.0,
+  "total_flos": 5926845614653440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null