Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e7e06879663d28174a82dc6b704095facb883f73afbf8f08665b9573c0a0017
+oid sha256:bdbfd8fce05c37dcc121a167e2dde13fe1f2c6699b0c49a54060b42078c21f0e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae31359390ebd44baeca72772348828cbb370f33737791b739de72f9d91a9c2
-size 2280
+oid sha256:de68237178b7cd8cb0aab344a72c6f20e2cfbe5e71c0a190446f1a432a9b7b98
+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 sha256:219c62af0a99d0a3db4c57e4189ef3b142499e30571ad5cc800b8b67c9ce1583
+oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.6434470174382516e-05,
+  "epoch": 0.00011286894034876503,
   "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": 5.082,
       "eval_steps_per_second": 5.082,
       "step": 3
+    },
+    {
+      "epoch": 7.524596023251002e-05,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 20.3679,
+      "step": 4
+    },
+    {
+      "epoch": 9.405745029063752e-05,
+      "grad_norm": 88.73544311523438,
+      "learning_rate": 2e-05,
+      "loss": 29.1746,
+      "step": 5
+    },
+    {
+      "epoch": 0.00011286894034876503,
+      "grad_norm": 71.97441864013672,
+      "learning_rate": 4e-05,
+      "loss": 21.5281,
+      "step": 6
+    },
+    {
+      "epoch": 0.00011286894034876503,
+      "eval_loss": 5.739979267120361,
+      "eval_runtime": 2197.5616,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 5.093,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2109388496044032.0,
+  "total_flos": 4218776992088064.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null