Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4482d7256d18df484f99d9344cd6c73f2c6be890e580f3dacff2935ac4574db5
+oid sha256:6d5c66b6ffda021237c9a3115ef48c563bdc76349c79fb2c7c5241e4c0491b2f
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397cbf3fd95b8441e13a80d3458d1d5118939022ab9c9f740a39f40dcfc6302f
+oid sha256:5109a92eb438ee2a74a28631740ab42f422667d66326971776fad9bb5fd6c70c
 size 82460660

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d7bd5bd26fb498fac45d7a49833d11a7c8053ebb24166db6968f1081bb4cc7
+oid sha256:0524491b2cbb00c2c8bf92935b27c0c8415926c182a2ae29784bff8683c2ca22
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f665697f616128f42731916c7044720dea1d302d4144b429951163834ef9e5d
+oid sha256:01fcfc9c89ee2c5890f040dad1ce0c6fe540609b6cee7e0d21d7f980a79b13cb
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984ed304ee2572c476b1d7a45e6238796d5af9a4e90fc90ca75172730556a741
+oid sha256:38d4ba61cffcb299e48489e74353d2e61936c89e4c8eac1c79c7544323e29350
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21af059a95787b7103d10be3dd2a11ad053234532829088ec510f2255efcaac2
+oid sha256:c32abb5bec1e6ac1fe8165766ea3654be86d90351042bf3409dd4368f62c2c4e
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d9244d7c44bd09796fa40aa056d4d8f84a0e62a0760ef9fb058e3b6f83f559b
+oid sha256:4dfa554528bc82d959dabfbd96640f6e380a6603f98f4e438b3be297113362bc
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e3d03497958e23e4f9a788b468b828dda534d6fb5b783596c62c2fcee0cda2
+oid sha256:a8b9f9c45856e3431088b9f1af4ddf561dc01f39dd2787aea79ed362bb2ba073
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377df699a816e08c783752ebd9f711a4239e23640fb988b4f539150862736011
+oid sha256:ea4ad072a9dd5444ff20683781218febde95b0b2273aea074f8d461d2d22f2cc
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e479b5fc35fe4d057156da47d86e23a8eec615fb7c45d4d529249205f42d59
+oid sha256:2dc8abdb4abb1ced175224941679bc40048e3666374c008c2d593b10a0268603
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36923076923076925,
+  "epoch": 0.5538461538461539,
   "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": 21.423,
       "eval_steps_per_second": 3.174,
       "step": 6
+    },
+    {
+      "epoch": 0.4307692307692308,
+      "grad_norm": 2.464343547821045,
+      "learning_rate": 0.0001,
+      "loss": 4.1546,
+      "step": 7
+    },
+    {
+      "epoch": 0.49230769230769234,
+      "grad_norm": 2.381273031234741,
+      "learning_rate": 0.00012,
+      "loss": 3.6829,
+      "step": 8
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 3.1305465698242188,
+      "learning_rate": 0.00014,
+      "loss": 3.8566,
+      "step": 9
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "eval_loss": 3.2923731803894043,
+      "eval_runtime": 1.2727,
+      "eval_samples_per_second": 21.214,
+      "eval_steps_per_second": 3.143,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3553856474382336e+16,
+  "total_flos": 5.03307847115735e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null