Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8502d8fd9ec5209c2b1fe2b2a5c752ecb4b4c612edad1030f4565ced0b590ccc
+oid sha256:55f98dd4d3ec19cbbbbbbd0f6be86c34f529a26bb31524b110261cb58dcb79bb
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:929a44962ec08e0029307c672946e49232e97f8a3eb9fde91c2aedecf2df4439
+oid sha256:16ef75e4d5ec5193ac7eb3a6de956ef2310c06737acf73158e72d541609f8167
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d2c6bb21a3bf16e24591514b759917b69cadf404c12e76fa21aada81445209
+oid sha256:ae5c619a4da90fa409bbf7a5cbb5a9f5b01fe3852d698c17628b4c1fb740305c
 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": 0.23880597014925373,
+  "epoch": 0.29850746268656714,
   "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": 4.169,
       "eval_steps_per_second": 0.532,
       "step": 20
+    },
+    {
+      "epoch": 0.2507462686567164,
+      "grad_norm": 3.0785763263702393,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 5.4397,
+      "step": 21
+    },
+    {
+      "epoch": 0.2865671641791045,
+      "grad_norm": 3.0347342491149902,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 5.3316,
+      "step": 24
+    },
+    {
+      "epoch": 0.29850746268656714,
+      "eval_loss": 1.3502321243286133,
+      "eval_runtime": 33.8052,
+      "eval_samples_per_second": 4.171,
+      "eval_steps_per_second": 0.532,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.723992035950592e+16,
+  "total_flos": 7.15499004493824e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null