Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1998222069d39e2f1a3f61817ad7bd9c3165c96a8ad66bb7cc054b768e56c0a
+oid sha256:116891ae0ef4cfa6f919d2744ec5a1f25dac6cb37192283e4d375cdece627943
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b3a6e43cf2e54821b5e00f89f0604c5819f0b05153acce0d8261af85539df2
+oid sha256:333e95c1fc799ccfd6b4ea02c8a0d11c2c127db01d49687161fec5e08472f5fb
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38409eba6413bce3b94b991e47f4c82368cb4192db5df85e36439951931f100f
+oid sha256:c5d410b3554f51a9e330e4afd32a4b9dfb61483b755d339ad915a14e3add09dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017094017094017096,
+  "epoch": 0.021367521367521368,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 6.54,
       "eval_steps_per_second": 0.82,
       "step": 20
+    },
+    {
+      "epoch": 0.017948717948717947,
+      "grad_norm": 2.400944709777832,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 2.7548,
+      "step": 21
+    },
+    {
+      "epoch": 0.020512820512820513,
+      "grad_norm": 2.2111105918884277,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 2.8021,
+      "step": 24
+    },
+    {
+      "epoch": 0.021367521367521368,
+      "eval_loss": 0.6264845132827759,
+      "eval_runtime": 301.4841,
+      "eval_samples_per_second": 6.538,
+      "eval_steps_per_second": 0.819,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.15209445769216e+16,
+  "total_flos": 6.4401180721152e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null