Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:400620106b3cff5b4b4142e9edb9768eca7dd9bdd4789cc77df819575c281147
+oid sha256:31d35e29e57fa5bad420fb6ad53cd99fe7e1934578b2cf4c5f02c11b6dc51ad6
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0be69b04aa6a670c840461092f23685be402d2fd625ecec061d5088d921536eb
+oid sha256:c28cae85a0e7a28d9440f12cd0a5ddf8ff133db2f69de4ca2570c8818ad979ba
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfcfd5e133f2f2340612d67096d68f4b96d6e485041671364e214a08c01caf7c
+oid sha256:037efb1585de1959202c69f662c6218305d4387c1880c29474dfba03ffd3be46
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19910657306955967,
+  "epoch": 0.2552648372686662,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 38.393,
       "eval_steps_per_second": 4.799,
       "step": 30
+    },
+    {
+      "epoch": 0.204211869814933,
+      "grad_norm": 0.0595882311463356,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5444,
+      "step": 40
+    },
+    {
+      "epoch": 0.204211869814933,
+      "eval_loss": 0.540993332862854,
+      "eval_runtime": 34.4989,
+      "eval_samples_per_second": 38.262,
+      "eval_steps_per_second": 4.783,
+      "step": 40
+    },
+    {
+      "epoch": 0.2552648372686662,
+      "grad_norm": 0.05125812813639641,
+      "learning_rate": 0.0,
+      "loss": 0.5309,
+      "step": 50
+    },
+    {
+      "epoch": 0.2552648372686662,
+      "eval_loss": 0.5400261282920837,
+      "eval_runtime": 34.4315,
+      "eval_samples_per_second": 38.337,
+      "eval_steps_per_second": 4.792,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.192283888562995e+16,
+  "total_flos": 4.09267165200384e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null