Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365aa4a8be46fa54fa865bcafa6a4dfe007d56652a0d5c06ca7d0636a0f5a209
+oid sha256:99d1f1b94a3a9b94941cf858fb3821dcb4031dca53de45a34a9bc5d94e9b94cb
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:086362e2ba798149ff26a460ab6c64f40090f56448b19e4edf10b49ae53c3f34
+oid sha256:7af4808ac012592bf59bbeb49e07ccc22677aeb0e20b31fceb18a0fc8a94f611
 size 37965300

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74eff1aaeb23f7c5da967314ef09fcadcf8dd98129b2e23c18e30cad1f3d98d1
+oid sha256:1881ec4d999362af1e52c36de1e218d3800542004d7f7c7edd42a089b7296ccc
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9851603423fb43d1355a5f5983f8e9d76c57606e6f614a7bfe4a891b37432eea
+oid sha256:00d02bbc0fa1d27820c289ea283e0155cafcbd62fa1759df4850d0a715649da0
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f46fb008ba3c7da3e9e101bf4ecbc4bad6629c45b9309b3e086e9f7d532acc7
+oid sha256:c73827ec09ff37ba195a38bf7f08f0537cea0c0a55db5d2fc0d29f759ccdcccb
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe7a6ab6b0ef57f3a70c2600dd377e8e8143fc9aff53ed8b18bdb97f0a7530a4
+oid sha256:4822c4ae863c6a81149f37fecf8fc589c5a0e68b5f03747420a5cc6ab7af0d14
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8d67cb450b52f0e8c119bc12056288e233502618cc60a00093b7235d32690f
+oid sha256:1e9b440498b750929a8558219fefc2e4ad160122931aa3d6799fc4f65cdd7304
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3557a500edd97558f50d759c9608b3728faa270af5958bea28917da46b71cc49
+oid sha256:4f0c18fbbe129f61ea282f7dbcc97540666d69c89e3f1cc4842d356efb45d0d6
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89293bd36a457766675f173525438c12fe41efee6816a576f7c754bf87d895da
+oid sha256:a99554429161338da1a7001f3a511ce540238038412b9c31276e6f7379ad186a
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39ad3dac0593de5b65cfc5b98fe9ccb8faf46a1295e7f40744e13cdcda701a9
+oid sha256:e39d4edd2882a248daa72fe9c907359ed8ef2a193dbcaec84663291acb998ec0
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001756311745334797,
+  "epoch": 0.0026344676180021956,
   "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": 79.974,
       "eval_steps_per_second": 10.007,
       "step": 6
+    },
+    {
+      "epoch": 0.002049030369557263,
+      "grad_norm": 3.9022231101989746,
+      "learning_rate": 0.00012,
+      "loss": 8.7262,
+      "step": 7
+    },
+    {
+      "epoch": 0.0023417489937797293,
+      "grad_norm": 3.7130041122436523,
+      "learning_rate": 0.00014,
+      "loss": 7.817,
+      "step": 8
+    },
+    {
+      "epoch": 0.0026344676180021956,
+      "grad_norm": 3.589695930480957,
+      "learning_rate": 0.00016,
+      "loss": 7.2472,
+      "step": 9
+    },
+    {
+      "epoch": 0.0026344676180021956,
+      "eval_loss": 6.745285987854004,
+      "eval_runtime": 71.9266,
+      "eval_samples_per_second": 79.998,
+      "eval_steps_per_second": 10.01,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6270090416750592.0,
+  "total_flos": 9405135625125888.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null