Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de6a1de0d6419f97a132b387798ebb2154fe6a5d5ebec5f49f0f087a9412e62e
+oid sha256:9ca628055cf73f0552619bd75c85f6a330ae01c141ab7d5ea7a5d588ef3a6372
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db769c1d57803d4b074aa776a31373c94f47c24a5bcdb625016574f2db422a7a
+oid sha256:39d9a64265cff6a5beef829ab1cb0a8dba23392b6fb9cf0742885e23d766f86e
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b0f69563309dc958f9c21e989482a40608995709ae1979e8f697efcafe269a6
+oid sha256:3604863e83d39486aefcc031059e824dd3fd492043ba02202f208a2c805306ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009457921008844907,
+  "epoch": 0.012610561345126543,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 27.859,
       "eval_steps_per_second": 3.482,
       "step": 27
+    },
+    {
+      "epoch": 0.010508801120938787,
+      "grad_norm": 0.21918490529060364,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.1566,
+      "step": 30
+    },
+    {
+      "epoch": 0.011559681233032665,
+      "grad_norm": 0.21285656094551086,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.1424,
+      "step": 33
+    },
+    {
+      "epoch": 0.012610561345126543,
+      "grad_norm": 0.2332816869020462,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.1502,
+      "step": 36
+    },
+    {
+      "epoch": 0.012610561345126543,
+      "eval_loss": 1.129488468170166,
+      "eval_runtime": 172.61,
+      "eval_samples_per_second": 27.855,
+      "eval_steps_per_second": 3.482,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1117182737973248e+16,
+  "total_flos": 1.4822910317297664e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null