Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f00d787c3e769b8619e465684b3d175946f3f15b5b2809d6880c84a517b8d97
+oid sha256:1b3e7a055bee93eff4916a0a1100094335a21c739ecdc89410f0869bc3219472
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61c58ff7ea01ee452fd3a57c6b4ddbbcb2b351c18ab6c61d2142c28e1638600
+oid sha256:5c629c4b92292d1c5381cf7c79d8c186308716552ad0869a14279daf570d7a56
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01fc1ce580e28a619d9332a6abc08d276d77522f73350afe3c772a2760eb6750
+oid sha256:a16d6a24acb0d8767414c9bffb55aafc1fecd7029ecd96860439687be7b08e18
 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": 0.006974716652136007,
+  "epoch": 0.010462074978204011,
   "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": 21.322,
       "eval_steps_per_second": 10.69,
       "step": 6
+    },
+    {
+      "epoch": 0.008137169427492008,
+      "grad_norm": 0.8567973375320435,
+      "learning_rate": 0.00014,
+      "loss": 0.701,
+      "step": 7
+    },
+    {
+      "epoch": 0.00929962220284801,
+      "grad_norm": 0.6242435574531555,
+      "learning_rate": 0.00016,
+      "loss": 0.5408,
+      "step": 8
+    },
+    {
+      "epoch": 0.010462074978204011,
+      "grad_norm": 0.5915112495422363,
+      "learning_rate": 0.00018,
+      "loss": 0.5469,
+      "step": 9
+    },
+    {
+      "epoch": 0.010462074978204011,
+      "eval_loss": 0.4810210168361664,
+      "eval_runtime": 17.0883,
+      "eval_samples_per_second": 21.243,
+      "eval_steps_per_second": 10.651,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1803325141942272.0,
+  "total_flos": 2635629053607936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null