Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fdb0ea6538631c519052fe4bd6a0ea4829fc053b08a5f185684a79291384cb
+oid sha256:bb1a21df5aaaf46d18ad732a489f8c3845221c341d465ebf9be6eeaaac6666de
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3448641cfa72d61ac0124a54a6de8ce1b0b8871fa8f9ee81c52d4f8ba1cc057
+oid sha256:fd0e0076ad6d43c74a3a58dbae61e4dec432c50c350d45632fae2aececfc37b2
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794553ffc19824ca7d869ee31576eee6569bc9a34ac9dff8109822f1332bd921
+oid sha256:2b184aea029f3721657bcfebf3500fc97ea749134c5f6570a032a92790adab8f
 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": 0.0008757206451142086,
+  "epoch": 0.001751441290228417,
   "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": 4.602,
       "eval_steps_per_second": 4.602,
       "step": 3
+    },
+    {
+      "epoch": 0.0011676275268189447,
+      "grad_norm": 1.551091194152832,
+      "learning_rate": 8e-05,
+      "loss": 2.6092,
+      "step": 4
+    },
+    {
+      "epoch": 0.001459534408523681,
+      "grad_norm": 0.9703443646430969,
+      "learning_rate": 0.0001,
+      "loss": 2.2054,
+      "step": 5
+    },
+    {
+      "epoch": 0.001751441290228417,
+      "grad_norm": 0.7744807600975037,
+      "learning_rate": 0.00012,
+      "loss": 2.2196,
+      "step": 6
+    },
+    {
+      "epoch": 0.001751441290228417,
+      "eval_loss": 2.5537147521972656,
+      "eval_runtime": 156.9202,
+      "eval_samples_per_second": 4.601,
+      "eval_steps_per_second": 4.601,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2097116079980544.0,
+  "total_flos": 4194232159961088.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null