Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:084b254081faec9380ea542a323464dfa83cb5d431cbeb4cf1add968b3373b6b
+oid sha256:323cbc457030d7c1f1fd7b0eda0bda7e233ebfb9d66cae12568eeaaaab94a15c
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1ab14446b88427b0169aa606fb0ce2331a012b1205fada3b05d6c498141668
+oid sha256:dc6920bf845b9e4981763ed71f30132dd61eb861bb691055df3db35739b6e132
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b35c8e31723066aef0ea0dfb2c5b6fe2e13cec12317c048b86f03568518e1162
+oid sha256:f6354c71b2bd3e2107bccaf19347553510bee577d0bedfe1ce37cadf83534f1c
 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": 0.0017851829812555787,
+  "epoch": 0.002677774471883368,
   "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": 8.238,
       "eval_steps_per_second": 4.119,
       "step": 6
+    },
+    {
+      "epoch": 0.0020827134781315083,
+      "grad_norm": 1.1815612316131592,
+      "learning_rate": 0.00014,
+      "loss": 2.215,
+      "step": 7
+    },
+    {
+      "epoch": 0.0023802439750074383,
+      "grad_norm": 2.3964359760284424,
+      "learning_rate": 0.00016,
+      "loss": 3.0826,
+      "step": 8
+    },
+    {
+      "epoch": 0.002677774471883368,
+      "grad_norm": 4.077512264251709,
+      "learning_rate": 0.00018,
+      "loss": 3.6421,
+      "step": 9
+    },
+    {
+      "epoch": 0.002677774471883368,
+      "eval_loss": 3.4991986751556396,
+      "eval_runtime": 172.0593,
+      "eval_samples_per_second": 8.23,
+      "eval_steps_per_second": 4.115,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1904332228263936.0,
+  "total_flos": 2624890368688128.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null