Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d8ed9060677932e30e5eec5262149c6e57d8bb3019137addfd3bee204633ae
+oid sha256:0e49043602b6687528192396e68cce5bde976fd5316e48b0bf112643366c6827
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d89dab04e435ae615bf053b6a9111ee79774d94fdd36893b0bfe0699b1fc33
+oid sha256:3a5c33b36f96d01a520b65221383a3f4b0560ce19bfa321d66087d1b32af879f
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e699daa34b94905d677ee7d2001f460693531758e3745e205c3ed4e29615cc1
+oid sha256:62b7e659592cddd3f51c87b74c90fba547c931f31933d3a49da9466abbe8bfce
 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": 0.10131332082551595,
+  "epoch": 0.1350844277673546,
   "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": 13.685,
       "eval_steps_per_second": 3.467,
       "step": 27
+    },
+    {
+      "epoch": 0.1125703564727955,
+      "grad_norm": 0.3799557685852051,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.045,
+      "step": 30
+    },
+    {
+      "epoch": 0.12382739212007504,
+      "grad_norm": 0.9986750483512878,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0625,
+      "step": 33
+    },
+    {
+      "epoch": 0.1350844277673546,
+      "grad_norm": 0.397352010011673,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0679,
+      "step": 36
+    },
+    {
+      "epoch": 0.1350844277673546,
+      "eval_loss": 0.05288050323724747,
+      "eval_runtime": 16.4545,
+      "eval_samples_per_second": 13.674,
+      "eval_steps_per_second": 3.464,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.919549725212672e+16,
+  "total_flos": 2.559399633616896e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null