Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1f20b98d56a2c29e42040e491ba22a44842e42f246908aec8246deb357dc6e
+oid sha256:a49d83e389ad887b1763b72c12b0a12fe41aedaaeb82546e9d6f19f7904a34a4
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb40f6586f9e41fa6c2026c35bb1a801613c3c8290ae8e7a1b73b18b78a4e5d0
+oid sha256:85b03db9aeb0407d75951040b44bdc4c6bf88d7d878842433160a87cde91024e
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cedea84ae5bcdf326fe3249157e4b672c6609d9b8e239194674fe6ef3a65a40
+oid sha256:940d78ce95bb8f7eb48adc329f7531c0db71f4ebde5ffbc17217d635e541d518
 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": 0.0003097573567372225,
+  "epoch": 0.00046463603510583376,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 3.528,
       "eval_steps_per_second": 3.528,
       "step": 6
+    },
+    {
+      "epoch": 0.00036138358286009293,
+      "grad_norm": 51.97016525268555,
+      "learning_rate": 6e-05,
+      "loss": 20.0777,
+      "step": 7
+    },
+    {
+      "epoch": 0.00041300980898296334,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 17.7553,
+      "step": 8
+    },
+    {
+      "epoch": 0.00046463603510583376,
+      "grad_norm": 45.40068817138672,
+      "learning_rate": 8e-05,
+      "loss": 18.4153,
+      "step": 9
+    },
+    {
+      "epoch": 0.00046463603510583376,
+      "eval_loss": 3.409105062484741,
+      "eval_runtime": 1155.3327,
+      "eval_samples_per_second": 3.53,
+      "eval_steps_per_second": 3.53,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6861841414225920.0,
+  "total_flos": 1.029276212133888e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null