Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42af0f81a69bd811619ede7815d260458d4555215be6c52cc3e55073496eb8e
+oid sha256:3909bf399c9a0567734c90631db8490c6fef8e4137802230e483adb34099146c
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aee0f387623a696f43d185ef4719ed0c1779dfe087403e5c7dd8ee315801aa52
+oid sha256:750abeb6a036f68f971f74a56e7601860c00995b29898ab3a1fc5e1bf1b1f181
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae2446b36b671be08c46bd3c933854b77a85f5b7ea9d33b9ab0cf510dce69e7
+oid sha256:ec2ddbaa8bba775edf415d96dfe5570dd34c0cd61b7fa5167b0e0c1db7bd35f1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09945300845350571,
+  "epoch": 0.14917951268025859,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 24.741,
       "eval_steps_per_second": 12.37,
       "step": 100
+    },
+    {
+      "epoch": 0.10939830929885629,
+      "grad_norm": 0.0002713771245907992,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.0003,
+      "step": 110
+    },
+    {
+      "epoch": 0.11934361014420686,
+      "grad_norm": 0.00031669007148593664,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.12928891098955744,
+      "grad_norm": 0.0003192306903656572,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.0012,
+      "step": 130
+    },
+    {
+      "epoch": 0.139234211834908,
+      "grad_norm": 0.23460803925991058,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.0001,
+      "step": 140
+    },
+    {
+      "epoch": 0.14917951268025859,
+      "grad_norm": 0.002061684150248766,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.14917951268025859,
+      "eval_loss": 0.0003408108896110207,
+      "eval_runtime": 17.1663,
+      "eval_samples_per_second": 24.7,
+      "eval_steps_per_second": 12.35,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.231444885307392e+16,
+  "total_flos": 4.86285395361792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null