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:badfb3d2419e1643537b39d8b2781c934aa6616be2c4e768482645c6b95cb3a7
+oid sha256:4d1f20b98d56a2c29e42040e491ba22a44842e42f246908aec8246deb357dc6e
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a46db53ad48fd15e7866c1efeaada6342480904172d6171f942860265add9b61
-size 2600
+oid sha256:fb40f6586f9e41fa6c2026c35bb1a801613c3c8290ae8e7a1b73b18b78a4e5d0
+size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7b88aa04473c265091eba5201c4e3fc95bc89bb999625696e8460f3ad3c9ad
+oid sha256:4cedea84ae5bcdf326fe3249157e4b672c6609d9b8e239194674fe6ef3a65a40
 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": 0.00015487867836861126,
+  "epoch": 0.0003097573567372225,
   "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": 3.511,
       "eval_steps_per_second": 3.511,
       "step": 3
+    },
+    {
+      "epoch": 0.00020650490449148167,
+      "grad_norm": 33.112857818603516,
+      "learning_rate": 2e-05,
+      "loss": 15.6053,
+      "step": 4
+    },
+    {
+      "epoch": 0.0002581311306143521,
+      "grad_norm": NaN,
+      "learning_rate": 2e-05,
+      "loss": 16.6773,
+      "step": 5
+    },
+    {
+      "epoch": 0.0003097573567372225,
+      "grad_norm": 36.85125732421875,
+      "learning_rate": 4e-05,
+      "loss": 17.8976,
+      "step": 6
+    },
+    {
+      "epoch": 0.0003097573567372225,
+      "eval_loss": 4.365196228027344,
+      "eval_runtime": 1155.9375,
+      "eval_samples_per_second": 3.528,
+      "eval_steps_per_second": 3.528,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3430920707112960.0,
+  "total_flos": 6861841414225920.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null