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:b43e582f9f23c2737fd9798b5f858afc782ffd7f7ac5f759e874caf0b8e714d6
+oid sha256:b0b8bb193e24030b8354775942d3b461797e03b118e05215685a25ab4f05a909
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7800a3e988f37263567222d747e4f8f07b1e0d0dd8f8b0c291a16a368da8d682
+oid sha256:5a9785116d32ec567a73de364c9b9ff82e17beb784ebe79d0120ea50b24added
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea8f278f29641100a56e280ef65934b0fccc8f8d9851be121c701ebed8ce795
+oid sha256:9df170cb6acde393f26f26d8b291e01ba34281d10b477edb2225f4b80d02e472
 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": 0.002711558016043385,
+  "epoch": 0.004067337024065077,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 18.965,
       "eval_steps_per_second": 9.482,
       "step": 6
+    },
+    {
+      "epoch": 0.003163484352050616,
+      "grad_norm": 0.04382634907960892,
+      "learning_rate": 0.00014,
+      "loss": 11.9479,
+      "step": 7
+    },
+    {
+      "epoch": 0.0036154106880578467,
+      "grad_norm": 0.0340876542031765,
+      "learning_rate": 0.00016,
+      "loss": 11.9464,
+      "step": 8
+    },
+    {
+      "epoch": 0.004067337024065077,
+      "grad_norm": 0.0457964763045311,
+      "learning_rate": 0.00018,
+      "loss": 11.9488,
+      "step": 9
+    },
+    {
+      "epoch": 0.004067337024065077,
+      "eval_loss": 11.947565078735352,
+      "eval_runtime": 49.0401,
+      "eval_samples_per_second": 19.005,
+      "eval_steps_per_second": 9.502,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1211154432.0,
+  "total_flos": 1861042176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null