Uploaded checkpoint-32500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e556f93d429e40e699d986989b577cb8c22804f241827fcd7d0cce4c58fb33
+oid sha256:59ec9fad15410ceb587e40b784f8ea3dc54e938ac10a95294d3699c990784967
 size 119975656

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd9579d4caf7f2a052e069804a5114ee1cfb406fc8c83bf59d9dd95fdab911ed
+oid sha256:c12910df6856fa33f58fb4ff472bdd6dc11e30b0182e3ccd2be9e925b347150f
 size 60477396

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b0827c468c23f41a6083f7fc3e6f3ebf585bd2815b57f652696125baed11e8
-size 14180
+oid sha256:dec85530e6760daecc8dcc8115ae33468e447116708e85bebcec9d39f1d56b5a
+size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a8f997004f1eea51654cbeb6b0eb881175b2d1ad913ffc6dcbce16821f7297
+oid sha256:d5e0762973dbc38f3dbaecc0938289f2d4040e8f1f2eb1a8e5d560966a6ea45a
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.75,
+  "epoch": 0.8125,
   "eval_steps": 2500,
-  "global_step": 30000,
+  "global_step": 32500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -313,6 +313,28 @@
       "eval_samples_per_second": 4.959,
       "eval_steps_per_second": 4.959,
       "step": 30000
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.4199697971343994,
+      "learning_rate": 2.3257971014492754e-06,
+      "loss": 1.2925,
+      "step": 31000
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 10.922388076782227,
+      "learning_rate": 1.7460869565217393e-06,
+      "loss": 1.2885,
+      "step": 32000
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 1.3001521825790405,
+      "eval_runtime": 201.9216,
+      "eval_samples_per_second": 4.952,
+      "eval_steps_per_second": 4.952,
+      "step": 32500
     }
   ],
   "logging_steps": 1000,
@@ -320,7 +342,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2500,
-  "total_flos": 4.8306377981952e+17,
+  "total_flos": 5.2331909480448e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null