Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec04c77e10f6919d671b05060fe2b81417b12ddb5174a7ba7c9f444044b9834
+oid sha256:6bf1bab86c3ccd339099e24b0cfe867a3d14547cc32ba41f0e716f38d1530b45
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2c9bcb198c1ab1b254c53a8fb0293eccf1b76535a69d36ada2370f8484f5ae1
+oid sha256:0dbb92c9c08bdfe40985f0f1507ad416a2c8c5c4089118fc921bf466aba26298
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c2114e917b04734ecf6d6c29e2dec4f37e3e775e81af5b53e52453122fa4372
+oid sha256:5f4f0e8dad369bc7bb59d5e7f497c51f10df0b55006fce373720fb706b727122
 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": 0.11501597444089456,
+  "epoch": 0.15335463258785942,
   "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": 36.187,
       "eval_steps_per_second": 4.581,
       "step": 27
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 0.7949721217155457,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.6592,
+      "step": 30
+    },
+    {
+      "epoch": 0.14057507987220447,
+      "grad_norm": 0.5070735812187195,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.6234,
+      "step": 33
+    },
+    {
+      "epoch": 0.15335463258785942,
+      "grad_norm": 0.6172641515731812,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.6746,
+      "step": 36
+    },
+    {
+      "epoch": 0.15335463258785942,
+      "eval_loss": 0.6016714572906494,
+      "eval_runtime": 10.9227,
+      "eval_samples_per_second": 36.163,
+      "eval_steps_per_second": 4.578,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7053851718844416.0,
+  "total_flos": 9405135625125888.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null