Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9247e85c0b428e6c4df00e3c96003077b3d595c3d197fff0ad1a5a12813982
+oid sha256:fd6e399e65e0697a4cd7b5bc2fa52961a1e4ca94b124ddda8a86545105061f02
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7e3a902687b65af9c3499ecc30c3e854fddf9d044bc544eaa05556dfa37a36
+oid sha256:15aa36d2d52ee9992db721f3bf2162c71a270a3dfc019189907fb933307162b6
 size 82460660

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08552d6171039c58b0f5e156ff0104092ecc181cbac95225bae0bc4d05b3b73c
+oid sha256:7fb2a68993bdbdfda2b78b8d08683583ad9a3da360caf1b9921eae0847d7c252
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc6d64248ff3d7f5bcbdc06e2809265fcb6dbe5ab9a0d3ccda821f6cb31797c
+oid sha256:f629ef6cf58883c1435755f27f710c16e053656612fe2d30855f87cb1c474a91
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56830e92f43aa07dde9343126392c6cb294f12ee3add0b3ccc1fe353fdd5af4a
+oid sha256:4a0360f63d0bfb1206e8307430bd30711ae1fb32c8b92787d373c208986063dc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5cedfbbd36b3b93e531c49018cfbac7f06a9ba025abba39000b9e354c1669c3
+oid sha256:ce39cb2d5d9d413d1a68eac1b8f1313c68155dd35c6f415a24b9b488aa665e93
 size 15024

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": 0.03096774193548387,
+  "epoch": 0.04645161290322581,
   "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": 17.785,
       "eval_steps_per_second": 4.446,
       "step": 6
+    },
+    {
+      "epoch": 0.03612903225806452,
+      "grad_norm": 3.047846794128418,
+      "learning_rate": 0.00014,
+      "loss": 2.3486,
+      "step": 7
+    },
+    {
+      "epoch": 0.04129032258064516,
+      "grad_norm": 3.2430038452148438,
+      "learning_rate": 0.00016,
+      "loss": 2.1589,
+      "step": 8
+    },
+    {
+      "epoch": 0.04645161290322581,
+      "grad_norm": 2.8587591648101807,
+      "learning_rate": 0.00018,
+      "loss": 2.1334,
+      "step": 9
+    },
+    {
+      "epoch": 0.04645161290322581,
+      "eval_loss": 1.8293477296829224,
+      "eval_runtime": 9.2285,
+      "eval_samples_per_second": 17.771,
+      "eval_steps_per_second": 4.443,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6776928237191168e+16,
+  "total_flos": 2.516539235578675e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null