Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:785b448d2c1c1bc067b67d39fe4323378ab774daa6c5dccecd64f904772ab056
+oid sha256:3057c5936d48c6a453f17a59b751b3558947822a670b22f02f4be5064bb5e055
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1636b1722f88e4ed3da0ab6aaff25856cef01efc30a66e0314f9489b3e9cee3
+oid sha256:332f95c81c2da5f1386621742e09088e27aeaee3f8f25c2f4229a146f66780df
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c808ea84fed9a855744aa146cfcc689bc13d3f79af6237c8b90439c3bf9a3ab
+oid sha256:b80206c13058d7daa054916148a5accb4d4b8074ce483ed6f0982d5ee7d68114
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008171881916306309,
+  "epoch": 0.0012257822874459463,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 2.521,
       "eval_steps_per_second": 2.521,
       "step": 6
+    },
+    {
+      "epoch": 0.0009533862235690695,
+      "grad_norm": 23.612119674682617,
+      "learning_rate": 0.00014,
+      "loss": 8.1276,
+      "step": 7
+    },
+    {
+      "epoch": 0.001089584255507508,
+      "grad_norm": 29.537059783935547,
+      "learning_rate": 0.00016,
+      "loss": 6.5983,
+      "step": 8
+    },
+    {
+      "epoch": 0.0012257822874459463,
+      "grad_norm": 21.244483947753906,
+      "learning_rate": 0.00018,
+      "loss": 4.3311,
+      "step": 9
+    },
+    {
+      "epoch": 0.0012257822874459463,
+      "eval_loss": 2.8899948596954346,
+      "eval_runtime": 608.9823,
+      "eval_samples_per_second": 2.539,
+      "eval_steps_per_second": 2.539,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3920749211418624.0,
+  "total_flos": 5881123817127936.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null