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:e0489cd2102d8ad28f7b3c1a78f8fa074eef771313308d2746a78ce8dbc98ee7
+oid sha256:8a939469575153adfbfc2f3df26d10e9ee8f30b3b3fe9a6b8d08f986f514c849
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f0b83671ea89b4dd938cc01e06f3bd36b649d0771387c0f14c47d4fb12790f
+oid sha256:b412ed276d0ee13ba4b6aaeb08f7f3cd1ad7ce4fc6039e3c9c5bf4af59fe3d2a
 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": 0.038113387327298714,
+  "epoch": 0.04764173415912339,
   "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": 6.288,
       "eval_steps_per_second": 0.79,
       "step": 20
+    },
+    {
+      "epoch": 0.04001905669366365,
+      "grad_norm": 1.3049689531326294,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 2.2512,
+      "step": 21
+    },
+    {
+      "epoch": 0.045736064792758456,
+      "grad_norm": 1.2573634386062622,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 2.2554,
+      "step": 24
+    },
+    {
+      "epoch": 0.04764173415912339,
+      "eval_loss": 2.2932698726654053,
+      "eval_runtime": 140.5269,
+      "eval_samples_per_second": 6.291,
+      "eval_steps_per_second": 0.79,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.034054314983424e+16,
+  "total_flos": 7.54256789372928e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null