Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f5f4d51433d8d023414faacd42d0cea7e0afc874bcb8ca55a69574bc63a702
+oid sha256:64f7d8b1e36d5fbfb24b429279a7961ec5e20b79a6558adcee2eac69a5327f6e
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3afedf4178f46bac29e8538f2a2bde9d1ef396f34de84e16a7e6d6954aaa192
+oid sha256:2cf39cf0a5f0ff8a6d57acc0d2444e07a8cd03dcbe7192d70642dc2f6bdaafcc
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27e83968c2d0fcbd9ce3decdbd850180096a3c3813ec3f1e2e7fbcdcb1b335e3
+oid sha256:487921a1acd258b82e58b9ec98a7bf8fbb6715ade97fa26c5f93634426742553
 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": 0.00039121717443395764,
+  "epoch": 0.0005868257616509365,
   "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": 35.711,
       "eval_steps_per_second": 17.856,
       "step": 6
+    },
+    {
+      "epoch": 0.00045642003683961726,
+      "grad_norm": 4.376823902130127,
+      "learning_rate": 0.00014,
+      "loss": 12.742,
+      "step": 7
+    },
+    {
+      "epoch": 0.0005216228992452769,
+      "grad_norm": 5.373292446136475,
+      "learning_rate": 0.00016,
+      "loss": 12.2543,
+      "step": 8
+    },
+    {
+      "epoch": 0.0005868257616509365,
+      "grad_norm": 6.618515968322754,
+      "learning_rate": 0.00018,
+      "loss": 11.7093,
+      "step": 9
+    },
+    {
+      "epoch": 0.0005868257616509365,
+      "eval_loss": 2.806042194366455,
+      "eval_runtime": 180.8621,
+      "eval_samples_per_second": 35.707,
+      "eval_steps_per_second": 17.853,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 979486818435072.0,
+  "total_flos": 1469230227652608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null