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:f35613c25f9df71810dea5aa7e22906f65992574ff3ffd28e8ec140c0c8268f3
+oid sha256:8f69244e2f138e82f81f98097aaa7db663e379d9b24ab1d713b773811451b129
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd3f82175e6ce32acb4515108e1b966b403b31edacff060ac640baede09b403b
+oid sha256:8fd886a4cf3b88fddc33a0185a5f34576035f1e814dbd465db1364fd3aa181dc
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 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": 6.39897616381379e-05,
+  "epoch": 0.0001279795232762758,
   "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": 162.73,
       "eval_steps_per_second": 81.365,
       "step": 3
+    },
+    {
+      "epoch": 8.531968218418386e-05,
+      "grad_norm": 0.01359029021114111,
+      "learning_rate": 8e-05,
+      "loss": 11.9345,
+      "step": 4
+    },
+    {
+      "epoch": 0.00010664960273022984,
+      "grad_norm": 0.01420881599187851,
+      "learning_rate": 0.0001,
+      "loss": 11.9364,
+      "step": 5
+    },
+    {
+      "epoch": 0.0001279795232762758,
+      "grad_norm": 0.011488054879009724,
+      "learning_rate": 0.00012,
+      "loss": 11.9313,
+      "step": 6
+    },
+    {
+      "epoch": 0.0001279795232762758,
+      "eval_loss": 11.931743621826172,
+      "eval_runtime": 121.6631,
+      "eval_samples_per_second": 162.251,
+      "eval_steps_per_second": 81.126,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 708968448.0,
+  "total_flos": 1417936896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null