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:f3c549460f2352b0840c34e8087ed1a56d55058822c4640a721a9b46d68b93c4
+oid sha256:91940cb84df0e223d9d0770d73cc70bdf089bf28935a5d62be5ddf1e1c6da1a8
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446166174bae7855c669f468907c1ca21f637d9edeacae5364adbae3a691634a
+oid sha256:a97ca1023e822d94ab1b8c73eb1b769fa43ff3f17a37861038e1a1b7f7e75afc
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0202e01efe8f13fd7b2c8ee3c96f603708af0ebe0527513b8b210324c785c8c3
+oid sha256:847e6adafbce1ce406fa778b8b6d2b9c0edf688a485355f7d2d7c87ce66c4fa0
 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": 0.1724137931034483,
+  "epoch": 0.21551724137931033,
   "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": 10.862,
       "eval_steps_per_second": 1.393,
       "step": 20
+    },
+    {
+      "epoch": 0.1810344827586207,
+      "grad_norm": 12.186010360717773,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 2.8286,
+      "step": 21
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 14.021751403808594,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 2.9939,
+      "step": 24
+    },
+    {
+      "epoch": 0.21551724137931033,
+      "eval_loss": 0.6674009561538696,
+      "eval_runtime": 17.963,
+      "eval_samples_per_second": 10.856,
+      "eval_steps_per_second": 1.392,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.861996017975296e+16,
+  "total_flos": 3.57749502246912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null