Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dbb01367f671944e9c6e9655a84db01999723494d0937bc1a89892aef6b45db
+oid sha256:f936485fe4a1cc4cba365745259ba34d48f547914c25782f114345bc8aff4917
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303d35bbb23dc6ed0336e81606e4782ec6e19b795af329b88d4e82830aa21b90
+oid sha256:765a1428de72f862cfc12a76798ebec3a3dc6508fe1471f9673917bed6d95a97
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b75c47b564804b350765d160229fd697697b4a313f72348c86e82f4cef49df
+oid sha256:de640fa99e5941b21233304e139535faa7a366f48810e513a4ede28893ca34c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6119402985074627,
+  "epoch": 1.7910447761194028,
   "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": 15.068,
       "eval_steps_per_second": 1.95,
       "step": 81
+    },
+    {
+      "epoch": 1.671641791044776,
+      "grad_norm": 0.6275697350502014,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.9247,
+      "step": 84
+    },
+    {
+      "epoch": 1.7313432835820897,
+      "grad_norm": 0.5964632630348206,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.9138,
+      "step": 87
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 0.5972414016723633,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.8821,
+      "step": 90
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "eval_loss": 0.9789036512374878,
+      "eval_runtime": 5.6422,
+      "eval_samples_per_second": 15.065,
+      "eval_steps_per_second": 1.95,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.058193875706839e+17,
+  "total_flos": 1.1758163520493978e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null