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:d20252fdeadc431b80bf3dba7cdc1f1b56dbb894dd64ca65b90d12b65a0b1a5f
+oid sha256:cde628f343758a99b602a6ac54604b226ee7c848be109fd33bf797984c28d4b8
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7692821f21da1e6cb1d4981bf1c9828301470ee6af7250faa1bdfb06669a8af0
+oid sha256:bb0c2167cf8adf20b96cdcc8f3f7ae0a49a8ed6518e9fb6f56575b2e092c0670
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd19e18c4ac18e3c1719cc1acfa191482fdb0394cd8eba0fe84d1e0799ffc4cb
+oid sha256:f403cb5e05ae1077a947e2a55947ef4aa0ffcee6d22e5bec100d80304d34344d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016586921850079744,
+  "epoch": 0.02126528442317916,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 3.4176,
       "step": 35
+    },
+    {
+      "epoch": 0.01701222753854333,
+      "grad_norm": 1.3800708055496216,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.1392,
+      "step": 40
+    },
+    {
+      "epoch": 0.01701222753854333,
+      "eval_loss": 0.788581371307373,
+      "eval_runtime": 54.9664,
+      "eval_samples_per_second": 18.011,
+      "eval_steps_per_second": 9.006,
+      "step": 40
+    },
+    {
+      "epoch": 0.019138755980861243,
+      "grad_norm": 1.3181637525558472,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.0037,
+      "step": 45
+    },
+    {
+      "epoch": 0.02126528442317916,
+      "grad_norm": 1.3086178302764893,
+      "learning_rate": 0.0,
+      "loss": 3.0455,
+      "step": 50
+    },
+    {
+      "epoch": 0.02126528442317916,
+      "eval_loss": 0.7847435474395752,
+      "eval_runtime": 54.9263,
+      "eval_samples_per_second": 18.024,
+      "eval_steps_per_second": 9.012,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3580018173149184.0,
+  "total_flos": 4589766888652800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null