Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23911c811d15e3313c7a7da9d536e108231c454ca04fdd49f379f6ab30e6e96f
+oid sha256:60ef1cdd5f1be94c2e3f8eb4e579675d7bfbd7ffd643c4438b803f2dd046ddae
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819b7f19547ebd3dbd829e6c9c4e16621a21ffc477802a034bff3db1e7dd467a
+oid sha256:7dd428a7fd0d68e315750e3ff8f87daeeaf310f9b46db7b1a5f61122a024b078
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb35249a84d7bcb3cccf7fe5b59ee8dc0f174103950c84a23cc071b3089b5686
+oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.010841338611588e-05,
+  "epoch": 0.00016021682677223176,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 4.608,
       "eval_steps_per_second": 4.608,
       "step": 3
+    },
+    {
+      "epoch": 0.0001068112178481545,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 5.4632,
+      "step": 4
+    },
+    {
+      "epoch": 0.00013351402231019313,
+      "grad_norm": 8.344459533691406,
+      "learning_rate": 6e-05,
+      "loss": 5.1562,
+      "step": 5
+    },
+    {
+      "epoch": 0.00016021682677223176,
+      "grad_norm": 7.8158040046691895,
+      "learning_rate": 8e-05,
+      "loss": 4.5659,
+      "step": 6
+    },
+    {
+      "epoch": 0.00016021682677223176,
+      "eval_loss": 4.253037929534912,
+      "eval_runtime": 1868.5451,
+      "eval_samples_per_second": 4.22,
+      "eval_steps_per_second": 4.22,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2225661850681344.0,
+  "total_flos": 4451323701362688.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null