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:a099b4266d93e53a33252d5934ad7f874990195985e3874e167c552668e189d5
+oid sha256:d1b2afdda1288d1b9fa3975417dd78522d9535ce08f1a721df83e34c0e2ca0fe
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b38d16207d8c32a552450f92dbe3ce515d24880f82bae3b36700389549e9fff
+oid sha256:835a2b452770f033d1633206e6f2aad81852a5bacfe9d4be2b616baa695b30fd
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82fcf039beb4b291ee9d2cc5a0b88f5c16fce727986185e7a1db46146cb4d558
+oid sha256:d535d91cb488f359eba4014dbef366efc23fdf15f3e817cbecb2688aaf399c87
 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": 0.0005516987724702312,
+  "epoch": 0.0011033975449404624,
   "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": 20.745,
       "eval_steps_per_second": 10.373,
       "step": 3
+    },
+    {
+      "epoch": 0.0007355983632936417,
+      "grad_norm": 0.35487285256385803,
+      "learning_rate": 8e-05,
+      "loss": 1.2765,
+      "step": 4
+    },
+    {
+      "epoch": 0.0009194979541170521,
+      "grad_norm": 0.3256043493747711,
+      "learning_rate": 0.0001,
+      "loss": 1.2646,
+      "step": 5
+    },
+    {
+      "epoch": 0.0011033975449404624,
+      "grad_norm": 0.29252171516418457,
+      "learning_rate": 0.00012,
+      "loss": 1.1082,
+      "step": 6
+    },
+    {
+      "epoch": 0.0011033975449404624,
+      "eval_loss": 1.173251986503601,
+      "eval_runtime": 110.4161,
+      "eval_samples_per_second": 20.74,
+      "eval_steps_per_second": 10.37,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 369021899243520.0,
+  "total_flos": 820048664985600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null