Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c85fd0c43959577fe5c62e4579e43ec7ac1c69c1cd48e7ae0acb495d2d43487
+oid sha256:4ed3ffbc346190ce3c98c8fead063538fbb8b39a927967522055cce14970beef
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c852a09e2930f136c1eae151e406a6dda35f85e36095716bdf27a09941e81bcd
+oid sha256:603e1a77b078786e3a0766730c5d4307e63a5dc657b5d84f05b3a3e0794ec585
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b432cedc7e4872aad041f24f2f1516e45d279e4f00110bf2e7d8fcd3dd5a6680
+oid sha256:fdacbad4cb5c5b201b8278a06f6d380ea7579ea2ad463c9cc04eb0e18aa64385
 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": 0.005794302269435055,
+  "epoch": 0.01158860453887011,
   "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": 2.626,
       "eval_steps_per_second": 1.313,
       "step": 3
+    },
+    {
+      "epoch": 0.00772573635924674,
+      "grad_norm": 0.4064790904521942,
+      "learning_rate": 8e-05,
+      "loss": 1.2321,
+      "step": 4
+    },
+    {
+      "epoch": 0.009657170449058426,
+      "grad_norm": 0.2956888675689697,
+      "learning_rate": 0.0001,
+      "loss": 1.2542,
+      "step": 5
+    },
+    {
+      "epoch": 0.01158860453887011,
+      "grad_norm": 0.2672729194164276,
+      "learning_rate": 0.00012,
+      "loss": 1.3084,
+      "step": 6
+    },
+    {
+      "epoch": 0.01158860453887011,
+      "eval_loss": 1.3224433660507202,
+      "eval_runtime": 83.1083,
+      "eval_samples_per_second": 2.623,
+      "eval_steps_per_second": 1.312,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3920749211418624.0,
+  "total_flos": 7841498422837248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null