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:f80860b3c79f9c62dc12e7c9e70b22a85be485a36fe855a3e12972cfdf62c1dc
+oid sha256:85ec2da4273051c575b27bc0e03421574e5b95872f1cf6e5f8cfdd65db2b9a77
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d24647eef4231db1c4916aade0e217cdcf95b1286fdf9f2a7d9e9654533a8d2
+oid sha256:fe77937d17f666bcedb63ca2b56b2df75371283b4dc13ae27851d131b803cb92
 size 132798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d59da8b4c57e23808f6e7dcb0354444fad839b17a806f0ce3f6a4809c61621
+oid sha256:059e301c18065b1c9a75f81e66def92b497540651351d8bc02434f165c0917ad
 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": 0.007259528130671506,
+  "epoch": 0.014519056261343012,
   "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": 69.656,
       "eval_steps_per_second": 34.828,
       "step": 3
+    },
+    {
+      "epoch": 0.009679370840895343,
+      "grad_norm": 3.9328174591064453,
+      "learning_rate": 8e-05,
+      "loss": 44.2043,
+      "step": 4
+    },
+    {
+      "epoch": 0.012099213551119177,
+      "grad_norm": 3.8412272930145264,
+      "learning_rate": 0.0001,
+      "loss": 44.2909,
+      "step": 5
+    },
+    {
+      "epoch": 0.014519056261343012,
+      "grad_norm": 3.7023684978485107,
+      "learning_rate": 0.00012,
+      "loss": 44.2077,
+      "step": 6
+    },
+    {
+      "epoch": 0.014519056261343012,
+      "eval_loss": 11.053502082824707,
+      "eval_runtime": 2.5656,
+      "eval_samples_per_second": 67.821,
+      "eval_steps_per_second": 33.91,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22460497920.0,
+  "total_flos": 44920995840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null