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:fb3bff090ac21a9f79bdec3f19adea904a1c9048bf0b740fcd27a3dee2a3fb99
+oid sha256:a1ec088f4fa09729549619be3383c35daf7301e2f67ed6c482674b8984894288
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e267c8551e92bec1c0d95190b0e7d8b2184a65730d3c55852532864c0cb462
+oid sha256:81c041afed3ff3ddbeb18461be75189fe89e384134b34aa15d4ba4d7d5bb3375
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d785e1f858f9b24c91f6a197613a9f3b03b25de4e2921242c11b806523a9c2b
+oid sha256:daf57e31af47133854b198d2ed1bf061cf80e24e56fc7a49ef63f0f861ee6fba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000975371860521824,
+  "epoch": 0.001463057790782736,
   "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": 20.265,
       "eval_steps_per_second": 10.136,
       "step": 6
+    },
+    {
+      "epoch": 0.0011379338372754612,
+      "grad_norm": 0.23090657591819763,
+      "learning_rate": 0.00014,
+      "loss": 0.8491,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013004958140290985,
+      "grad_norm": 0.28002697229385376,
+      "learning_rate": 0.00016,
+      "loss": 0.8703,
+      "step": 8
+    },
+    {
+      "epoch": 0.001463057790782736,
+      "grad_norm": 0.2905180752277374,
+      "learning_rate": 0.00018,
+      "loss": 0.7873,
+      "step": 9
+    },
+    {
+      "epoch": 0.001463057790782736,
+      "eval_loss": 0.7985858917236328,
+      "eval_runtime": 127.3819,
+      "eval_samples_per_second": 20.34,
+      "eval_steps_per_second": 10.174,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1978877607936000.0,
+  "total_flos": 3007893964062720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null