Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f98dd4d3ec19cbbbbbbd0f6be86c34f529a26bb31524b110261cb58dcb79bb
+oid sha256:e21664bb6c1d1ae2c109122f4b3938bed613da6ad3c1ac0fc53a51bb2edd6857
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ef75e4d5ec5193ac7eb3a6de956ef2310c06737acf73158e72d541609f8167
+oid sha256:dea6e9aaa3c56756ed19a39c205a6002e9f082dc3c344c6d133fc719df87039f
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae5c619a4da90fa409bbf7a5cbb5a9f5b01fe3852d698c17628b4c1fb740305c
+oid sha256:5926316ccbdc15291fd4d44c743eae350fd67684d89bb86c8ec5f6337921754f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.29850746268656714,
+  "epoch": 0.3582089552238806,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,28 @@
       "eval_samples_per_second": 4.171,
       "eval_steps_per_second": 0.532,
       "step": 25
+    },
+    {
+      "epoch": 0.32238805970149254,
+      "grad_norm": 2.8705027103424072,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 5.4831,
+      "step": 27
+    },
+    {
+      "epoch": 0.3582089552238806,
+      "grad_norm": 2.9315133094787598,
+      "learning_rate": 5e-05,
+      "loss": 5.4605,
+      "step": 30
+    },
+    {
+      "epoch": 0.3582089552238806,
+      "eval_loss": 1.342836856842041,
+      "eval_runtime": 33.8234,
+      "eval_samples_per_second": 4.169,
+      "eval_steps_per_second": 0.532,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -130,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.15499004493824e+16,
+  "total_flos": 8.585988053925888e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null