Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b4672df5bb2f5c4ff6fee46427e0d5872131bc59a699f89cdb5b0d45df49b8
+oid sha256:731cafc11fa7c4a142858108d7af866d61337c4f08d449eb256479264c521749
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb87890333146848effb7093da7c562e23020283928496b03dbac3cf881cb9c4
+oid sha256:c65cb70b9a7ba4742a5c5faba92ea6b358ee8115dda2194123d00696788d68e2
 size 11710970

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4af877ef2fb8003634e1cf816281910569d028406209457734444c6ca5961b11
+oid sha256:da5a4ae588d824591f53580b3b11e4b509b69086b1ac0e682f97341ca2f209a1
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b94aeb9644edcda3c8c594475b03f79a276357c0927d7c222df2172c45dd928c
+oid sha256:051edb58c1177b5e5e14c9e71436ef45ed45b57cbff0f64aeb1ef492f01d86a4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac58b5cfdcd32024a5d61a12b17e2b7b97934fc0c508913d60e28668dba1a54
+oid sha256:a44c98272bd3b4f2ac204de34d3d9a19353fe7c4a9c52ed73896742ec484d67b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:095950735dcc001e20e282cc8dace03e98cb60772af238467f10a7fd75462c05
+oid sha256:019f1715cee0a033ca1ce2fb562bb8a40ce585cfd132821a3c89beeca1eff7a0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.032350882650283845,
+  "epoch": 0.04852632397542577,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 520.045,
       "eval_steps_per_second": 16.257,
       "step": 20
+    },
+    {
+      "epoch": 0.03732794151955829,
+      "grad_norm": 0.6048240661621094,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.1735,
+      "step": 30
+    },
+    {
+      "epoch": 0.03732794151955829,
+      "eval_loss": 2.1391475200653076,
+      "eval_runtime": 41.6534,
+      "eval_samples_per_second": 519.934,
+      "eval_steps_per_second": 16.253,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.002677376889651e+16,
+  "total_flos": 6.004016065334477e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null