Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2113ee10d6700ad29ba8a3955cd44cf111dd99902abb9ce5fecc1e04e8311eae
+oid sha256:c1bb6581d17652f455662f249ac91e05b6d013823347fde3e6cd7b1044acd611
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5520358de47c920d15d7a7726b6c81ede71bc1f6590626b7353283e12c88c3b
+oid sha256:dbb872a21d8b5b11bc1475f938f44135fec7797927bf4c73df4821167d4985aa
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e1568a9e8418232f5cb6d15207f018fdd610216d44e9fd26dbeb423790da509
+oid sha256:830c0717e1a623f4428da5c6215b99cc10f0295b0807586eba37d260994f5fd2
 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": 0.00010412147505422994,
+  "epoch": 0.00020824295010845987,
   "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": 37.925,
       "eval_steps_per_second": 18.963,
       "step": 3
+    },
+    {
+      "epoch": 0.00013882863340563992,
+      "grad_norm": 2.1943202018737793,
+      "learning_rate": 8e-05,
+      "loss": 5.1899,
+      "step": 4
+    },
+    {
+      "epoch": 0.0001735357917570499,
+      "grad_norm": 5.0044145584106445,
+      "learning_rate": 0.0001,
+      "loss": 7.0007,
+      "step": 5
+    },
+    {
+      "epoch": 0.00020824295010845987,
+      "grad_norm": 2.0717947483062744,
+      "learning_rate": 0.00012,
+      "loss": 4.5291,
+      "step": 6
+    },
+    {
+      "epoch": 0.00020824295010845987,
+      "eval_loss": 1.281042456626892,
+      "eval_runtime": 321.7797,
+      "eval_samples_per_second": 37.703,
+      "eval_steps_per_second": 18.851,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 342798394982400.0,
+  "total_flos": 669273056870400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null