Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e14174a017723caf4cc48fc46af7307fc22a0347d79eaa9c09d6d398b97568
+oid sha256:10e807563c8392e2a8fe02a3ee15fe6453cdb26b8f97a5eb12eac6f20a235352
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc196954d869ece37636b0a87eca3ae563790fee023637465f9761db17d9c66f
+oid sha256:dea226daefa3aa2330b560d3a96fc8c1819e1f25c4b9214ce91dd4b76f2e17f2
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4cdaf766e3d5fc16b2b4b2604721049e3e08689f51246ace33b226a9a536a78
+oid sha256:622ceae4b401457d5f97faddd86200595cdd37a28f8777a4752d43d821eed8e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4967fab956f007beafd6b8bc5c5dee4d86950ea055e4ab46c9a7cdc66a69112d
+oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018293070229298554,
+  "epoch": 0.020325633588109505,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 131.035,
       "eval_steps_per_second": 65.522,
       "step": 81
+    },
+    {
+      "epoch": 0.018970591348902204,
+      "grad_norm": 0.02584969997406006,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 10.3516,
+      "step": 84
+    },
+    {
+      "epoch": 0.019648112468505854,
+      "grad_norm": 0.029781047254800797,
+      "learning_rate": 1.2750399292720283e-05,
+      "loss": 10.3506,
+      "step": 87
+    },
+    {
+      "epoch": 0.020325633588109505,
+      "grad_norm": 0.022765731438994408,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 10.3504,
+      "step": 90
+    },
+    {
+      "epoch": 0.020325633588109505,
+      "eval_loss": 10.350595474243164,
+      "eval_runtime": 113.4837,
+      "eval_samples_per_second": 131.429,
+      "eval_steps_per_second": 65.719,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 34642128273408.0,
+  "total_flos": 38491253637120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null