Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d144b6251b434c255a137c6d5f9abc131b6632ed79229037b8d0aadbb38150b
+oid sha256:f8956f03efb99bbf51254d89c73a39e5a8a22710cc4523a20b08c74048664a70
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ead54d3eeabe6c83da8447c6d53797385c379ad0e01e896243dde0c8e6a1522
+oid sha256:4d267a6b0c57c28362468e52c81cc67a834f278d486ca427393f9c6028ac2920
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4de299cbec32b5d620d205f1f2a93ee7464a54e8fcaacd4b8b3e6b0405decdd
+oid sha256:fef7042edb9f55c78095920a6111885d241ba48c28d42e22fc2ac4506fd8af5b
 size 15920

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1552a17619eb4c01542ef3d38cde7ebf823269f799a9837865507c490630e25d
+oid sha256:e89ecd0f22a73026d4179e0d3ce3ccb4c34ff1d451d0e7c309bcf88cfd02bfdf
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616c0982798d495aeb87e7449cefa5387ac0a9a461d4d8a7f49b3ed4762a9d01
+oid sha256:2ca28515e43522bea0132c12428f6b650ddf97ee8f33c61b53eaa4087871190a
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f754b0d6d5a589b9d9129496adf70cc30b5837b7ed9f5bea4d8389e260494cb
+oid sha256:b556ea9aeffedd3a795e135287a0840659fc8c0ec4d610fe58f516f0ea1f653c
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbbd478418c0631809362bd8343db09e56fff205337c89e0bd5a13e1fcbbf270
+oid sha256:d9dd00cc299e41bda49be9e2ea1c984c405c5543b90d95b6fc49963be6a22074
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de430d208cb610f56f58c34b34c3cff7cbf48817d861d16488f05a19150a661b
+oid sha256:452c1974cc8fff33c653fe87290deb9c50f9a38a309be948de1ec6660ad006ea
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e511796e67e9e843f481209f3019cc0fff69bda5b5dacc01795de460c4fcb76a
+oid sha256:7bcf5cde5f5689ece072356d6b3488190f66fe1533434ae72b49cf7a74e4d57b
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe4da818a22ca7eaa9e0e4852985d51baf9aa336036efbe2a239c9fb71bc35a
+oid sha256:a2f98794b0cdbed7cc5fd63b0c9dfdbc09245bb22cdf7800feb27298bbac8a9e
 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": 0.031088082901554404,
+  "epoch": 0.046632124352331605,
   "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": 53.262,
       "eval_steps_per_second": 6.719,
       "step": 6
+    },
+    {
+      "epoch": 0.03626943005181347,
+      "grad_norm": 1.6933070421218872,
+      "learning_rate": 0.00014,
+      "loss": 2.1506,
+      "step": 7
+    },
+    {
+      "epoch": 0.04145077720207254,
+      "grad_norm": 2.2071964740753174,
+      "learning_rate": 0.00016,
+      "loss": 2.1208,
+      "step": 8
+    },
+    {
+      "epoch": 0.046632124352331605,
+      "grad_norm": 2.2025673389434814,
+      "learning_rate": 0.00018,
+      "loss": 2.1536,
+      "step": 9
+    },
+    {
+      "epoch": 0.046632124352331605,
+      "eval_loss": 2.0101969242095947,
+      "eval_runtime": 6.1068,
+      "eval_samples_per_second": 53.22,
+      "eval_steps_per_second": 6.714,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9650863991685120.0,
+  "total_flos": 1.447629598752768e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null