Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b03d0c5b082e21e024088651e8e56692d9eeda1f67bfc6563aac6ae2de0793b
+oid sha256:03a618c804373e17358b08829f93ce35240669dee17a0c56a2828ee866037519
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f16345b871e27c201de1f475086ef9903b26df2d1351ee7db824506ef45586
+oid sha256:77a26372bc60c0c9eb820d10862cde5152e01445d8df975dd857349d555623e8
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c08bef82cd879a5d72fef5b1189f3c5257256cba756344e8656354d56485e14
+oid sha256:daef4d440c8b18b4e8ed70951f06793ba8c673633b41a899a0c8049a3b7dbb4a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005316085588977983,
+  "epoch": 0.0010632171177955966,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 72.622,
       "eval_steps_per_second": 36.326,
       "step": 3
+    },
+    {
+      "epoch": 0.000708811411863731,
+      "grad_norm": 59.070701599121094,
+      "learning_rate": 8e-05,
+      "loss": 17.0189,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008860142648296638,
+      "grad_norm": 53.60502624511719,
+      "learning_rate": 0.0001,
+      "loss": 18.4737,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010632171177955966,
+      "grad_norm": 62.920711517333984,
+      "learning_rate": 0.00012,
+      "loss": 18.7371,
+      "step": 6
+    },
+    {
+      "epoch": 0.0010632171177955966,
+      "eval_loss": 4.5854315757751465,
+      "eval_runtime": 32.4984,
+      "eval_samples_per_second": 73.142,
+      "eval_steps_per_second": 36.586,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 39477854601216.0,
+  "total_flos": 72376066768896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null