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:bd2da53f61eb6db505431f16a777ac5d11094fa5cabb01f1aed4953f7138e9f5
+oid sha256:43325a2a3bad9df41468a206abdbe9a48a62185ff112f098c0f43b8b6c812fbb
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017a5dea33f4189e44bb025f49754350735d40031a84b1350e69f951f54e0d96
+oid sha256:52b29e7b2dae1a212c61a65589691c4805682caf362d1f25a3e9ea8d7ae43483
 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 sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014018691588785047,
+  "epoch": 0.02102803738317757,
   "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": 78.683,
       "eval_steps_per_second": 9.931,
       "step": 6
+    },
+    {
+      "epoch": 0.016355140186915886,
+      "grad_norm": 0.8447181582450867,
+      "learning_rate": 0.00014,
+      "loss": 2.1857,
+      "step": 7
+    },
+    {
+      "epoch": 0.018691588785046728,
+      "grad_norm": 1.064998745918274,
+      "learning_rate": 0.00016,
+      "loss": 2.2227,
+      "step": 8
+    },
+    {
+      "epoch": 0.02102803738317757,
+      "grad_norm": 1.8660669326782227,
+      "learning_rate": 0.00018,
+      "loss": 2.5705,
+      "step": 9
+    },
+    {
+      "epoch": 0.02102803738317757,
+      "eval_loss": 2.6046745777130127,
+      "eval_runtime": 9.1641,
+      "eval_samples_per_second": 78.677,
+      "eval_steps_per_second": 9.93,
+      "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