Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff2715ae5ad266f6a321332f52654547d92979eb5b73cf08f9521c5a6e6c9ad
+oid sha256:d5622eb52859b0d4101e82f0f9a26c5abec4ad32fc60124e72a4dc02960df434
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c768d54cf6862125a542e6c27c1423bc85ed8624457d097da258a7cb229ec03
+oid sha256:9c6c518bb255fe60720133c817f8e71b3035c2b4c397f9319986b320b8c860aa
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e39b58f8dd1428862d10b2ca179766f5915d74ecb29dc037da3881ece550f5
+oid sha256:971b3c8cf853f22869b90ddddf63ef0566b6ceb377f3b57b66478e5d06e3e51b
 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": 0.00307416421160497,
+  "epoch": 0.004611246317407455,
   "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": 4.578,
       "eval_steps_per_second": 4.578,
       "step": 6
+    },
+    {
+      "epoch": 0.0035865249135391317,
+      "grad_norm": 0.5923784375190735,
+      "learning_rate": 0.00014,
+      "loss": 1.2382,
+      "step": 7
+    },
+    {
+      "epoch": 0.004098885615473293,
+      "grad_norm": 0.6953917145729065,
+      "learning_rate": 0.00016,
+      "loss": 1.271,
+      "step": 8
+    },
+    {
+      "epoch": 0.004611246317407455,
+      "grad_norm": 0.8029590249061584,
+      "learning_rate": 0.00018,
+      "loss": 0.6573,
+      "step": 9
+    },
+    {
+      "epoch": 0.004611246317407455,
+      "eval_loss": 1.064617395401001,
+      "eval_runtime": 89.7935,
+      "eval_samples_per_second": 4.577,
+      "eval_steps_per_second": 4.577,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4194232159961088.0,
+  "total_flos": 6291348239941632.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null