Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d2b6a2ce268c2572230b81f4baf3ff023ebe9bda1a0096b8861aaf4ec8b5445
+oid sha256:815d6bb5bf102182e22a1174867f1fb39e240d76c6eb3906632181e6235e80eb
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01ff9dfe24def6624784ff51ff2cfba6e007499f02c405e96dcd64d7b9d17f32
+oid sha256:25995127a8eff83576b0aa8269e0157f0685925857b5fdd51022cb4dda263146
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76176b194774cb7a663950593f31d2e41cbb03e09a4aaaaf2425c3c4a43bad6c
+oid sha256:a12a89be9332cd67b8b31b4c46ef54558059ca89ed9c61c00ead2e0293a8fd09
 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": 0.0077934495335055184,
+  "epoch": 0.008659388370561688,
   "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": 2.894,
       "eval_steps_per_second": 1.447,
       "step": 81
+    },
+    {
+      "epoch": 0.008082095812524242,
+      "grad_norm": 17.062747955322266,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.306,
+      "step": 84
+    },
+    {
+      "epoch": 0.008370742091542965,
+      "grad_norm": 15.015271186828613,
+      "learning_rate": 1.2750399292720283e-05,
+      "loss": 4.3013,
+      "step": 87
+    },
+    {
+      "epoch": 0.008659388370561688,
+      "grad_norm": 12.879692077636719,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 4.3707,
+      "step": 90
+    },
+    {
+      "epoch": 0.008659388370561688,
+      "eval_loss": 0.1438611000776291,
+      "eval_runtime": 12295.3446,
+      "eval_samples_per_second": 2.847,
+      "eval_steps_per_second": 1.424,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.259916615505674e+17,
+  "total_flos": 4.7332406838951936e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null