Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5558f857e05142eb3450a949ed4043e46ae2ffec75640452b6ecfd147c6e9eb9
+oid sha256:6e26ab07144e1dc16be43a4d0366e055503e53e47b249459de9f1e9faf8919d8
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc4750cea08d0182320ed1ad14b96e4a9261bf8c163da6d4abb0d1ad8720f2b7
+oid sha256:28d408fa6cd13306f8391751c750bb6cd641f13f956e836815197c00bdbfa3ac
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f5ca53c3302957dcf54171727b834f30b4ce4941c252de022059ae072dcb1c
+oid sha256:9d255463ac767724210dab727ce3e6422f5bea83e31d653ead42c7476e8e460a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594dcf1d063251cca4c3b70569456a468140193c0f517d256489d095068b4748
+oid sha256:4bcb6468c96e42ca9e19eeef69577865d7a693066e16690bd13303c9f6654183
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018094731240021287,
+  "epoch": 0.03512506652474721,
   "eval_steps": 5,
-  "global_step": 17,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,72 @@
       "eval_samples_per_second": 13.974,
       "eval_steps_per_second": 6.987,
       "step": 15
+    },
+    {
+      "epoch": 0.019159127195316657,
+      "grad_norm": 0.21007171273231506,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 0.3951,
+      "step": 18
+    },
+    {
+      "epoch": 0.021287919105907396,
+      "eval_loss": 0.37646475434303284,
+      "eval_runtime": 28.3194,
+      "eval_samples_per_second": 13.983,
+      "eval_steps_per_second": 6.992,
+      "step": 20
+    },
+    {
+      "epoch": 0.022352315061202766,
+      "grad_norm": 0.2738609313964844,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.379,
+      "step": 21
+    },
+    {
+      "epoch": 0.025545502927088876,
+      "grad_norm": 0.1851503849029541,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 0.3225,
+      "step": 24
+    },
+    {
+      "epoch": 0.026609898882384245,
+      "eval_loss": 0.3364916741847992,
+      "eval_runtime": 28.3568,
+      "eval_samples_per_second": 13.965,
+      "eval_steps_per_second": 6.982,
+      "step": 25
+    },
+    {
+      "epoch": 0.028738690792974985,
+      "grad_norm": 0.1698993593454361,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.3176,
+      "step": 27
+    },
+    {
+      "epoch": 0.031931878658861094,
+      "grad_norm": 0.14914517104625702,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.2347,
+      "step": 30
+    },
+    {
+      "epoch": 0.031931878658861094,
+      "eval_loss": 0.32247039675712585,
+      "eval_runtime": 28.3731,
+      "eval_samples_per_second": 13.957,
+      "eval_steps_per_second": 6.978,
+      "step": 30
+    },
+    {
+      "epoch": 0.03512506652474721,
+      "grad_norm": 0.25325828790664673,
+      "learning_rate": 0.0,
+      "loss": 0.3379,
+      "step": 33
     }
   ],
   "logging_steps": 3,
@@ -88,12 +154,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1645128368259072.0,
+  "total_flos": 3193484479561728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null