Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8729d60d03c5d30a44b8c2cd2ea03dffa040e64a49a948253bbd4427a60ca4
+oid sha256:088a68e66e552a6976c32f9b20f2ace92ad9ba2a29eb6bc282047ad6fa6b6f63
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a184ce6655e626145e594fed1dfc2b3445b33f1852c48feab665da5f10e284e
+oid sha256:7646b166ec03eeac2bbd06339911963ad75c4a191bbe8de095d6f8aeea4b6e35
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
 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": 0.291970802919708,
+  "epoch": 0.36496350364963503,
   "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": 189.414,
       "eval_steps_per_second": 24.706,
       "step": 20
+    },
+    {
+      "epoch": 0.30656934306569344,
+      "grad_norm": 0.4219861328601837,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 11.9163,
+      "step": 21
+    },
+    {
+      "epoch": 0.35036496350364965,
+      "grad_norm": 0.4657047390937805,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 11.9069,
+      "step": 24
+    },
+    {
+      "epoch": 0.36496350364963503,
+      "eval_loss": 11.893145561218262,
+      "eval_runtime": 0.6283,
+      "eval_samples_per_second": 183.04,
+      "eval_steps_per_second": 23.875,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 96416563200.0,
+  "total_flos": 120520704000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null