Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a06accd4fec5f25fcfc8f65d1ed01e8afbe9298eab63cb118d70362f30c79a
+oid sha256:c359ba24b20a819f878de0b6e84eb80c23d579785cc63fd5055d41a8a19c31b4
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:217542b1ce824b43c08117619f22cb9ed2f90f20b3621edb72974d424ee3be84
+oid sha256:f546bafe8703664d6c692d0189a0350e7a68c3f2b84afb26519e80ef15cf175d
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a63f420b9e7de84bbc3c5a80fdd9facfc42c1cda1e04aef6966e66fbe6f161f1
+oid sha256:8cdf07a28c1a078875b0a906ff6d3e3202e38624eb24ec7d2f3280a07f5c40e3
 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": 0.07624633431085044,
+  "epoch": 0.09775171065493646,
   "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": 0.6253,
       "step": 35
+    },
+    {
+      "epoch": 0.07820136852394917,
+      "grad_norm": 1.320988416671753,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5696,
+      "step": 40
+    },
+    {
+      "epoch": 0.07820136852394917,
+      "eval_loss": 0.574241578578949,
+      "eval_runtime": 13.724,
+      "eval_samples_per_second": 15.739,
+      "eval_steps_per_second": 7.869,
+      "step": 40
+    },
+    {
+      "epoch": 0.08797653958944282,
+      "grad_norm": 0.8891041874885559,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5825,
+      "step": 45
+    },
+    {
+      "epoch": 0.09775171065493646,
+      "grad_norm": 1.9904056787490845,
+      "learning_rate": 0.0,
+      "loss": 0.5554,
+      "step": 50
+    },
+    {
+      "epoch": 0.09775171065493646,
+      "eval_loss": 0.5622581839561462,
+      "eval_runtime": 13.654,
+      "eval_samples_per_second": 15.82,
+      "eval_steps_per_second": 7.91,
+      "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": 6796280579751936.0,
+  "total_flos": 8713180230451200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null