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:a6642daef3b69a0fff5cfc38c7ef35a8428615c39e2728488da2fa8721dc2900
+oid sha256:76b36973eebfd97c8ff752545e9a87ee24ceaa1bcf339c3b7bb599551c8ccea3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41fc74d7290320475151a142672865f8d3068fbb3acd892a910ba83f5c866fa
+oid sha256:6622fc362d29884bbdcdea75700e367d6ea47056d59bf682b7290f0d9a49baa9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f4d6bb4cc4e74c35f6a1360afa90540250a2e67956fb6d4004e4c1936bf578
+oid sha256:2ec2ea3c36f9a72a61d8e4063544561978c22d2e4671366561c977e22abfaad9
 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": 0.0006819612506120165,
+  "epoch": 0.0008743092956564314,
   "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": 2.5892,
       "step": 35
+    },
+    {
+      "epoch": 0.0006994474365251451,
+      "grad_norm": 4.788456916809082,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2618,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006994474365251451,
+      "eval_loss": 2.4747378826141357,
+      "eval_runtime": 3211.0842,
+      "eval_samples_per_second": 7.499,
+      "eval_steps_per_second": 3.75,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007868783660907883,
+      "grad_norm": 3.602632761001587,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9381,
+      "step": 45
+    },
+    {
+      "epoch": 0.0008743092956564314,
+      "grad_norm": 6.709247589111328,
+      "learning_rate": 0.0,
+      "loss": 2.6681,
+      "step": 50
+    },
+    {
+      "epoch": 0.0008743092956564314,
+      "eval_loss": 2.46523380279541,
+      "eval_runtime": 3208.1371,
+      "eval_samples_per_second": 7.506,
+      "eval_steps_per_second": 3.753,
+      "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": 1.0265081577209856e+16,
+  "total_flos": 1.3270623480446976e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null