Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:551591655f25df338dd89730ee636d3d15f171f74f5b9535bf9cfce6086d69a7
+oid sha256:84533e212ed2e8882467232d32340242e1296d1a17cb252053c1bee645d3041c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4956b08cdb6c4866c5be6320d57a4f110a2b40781fc46fc79639efd07e31488
+oid sha256:cfaa3d75a67d09f433a8e1f261b58e8e11895078f3b3014540328238f5143275
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a056a23a2b694850733aa8969819c8c578fa33328554e51a9e924a49fd0982
+oid sha256:63606c73c93c05d27e7758139a39e39228c390bd2d751703d97059d8f583fa7f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015556635877491491,
+  "epoch": 0.002333495381623724,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 2.5934,
       "step": 18
+    },
+    {
+      "epoch": 0.0016334467671366066,
+      "grad_norm": 2.3414273262023926,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.3222,
+      "step": 21
+    },
+    {
+      "epoch": 0.001866796305298979,
+      "grad_norm": 3.0098507404327393,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.3274,
+      "step": 24
+    },
+    {
+      "epoch": 0.001866796305298979,
+      "eval_loss": 2.291135549545288,
+      "eval_runtime": 312.7717,
+      "eval_samples_per_second": 17.31,
+      "eval_steps_per_second": 8.655,
+      "step": 24
+    },
+    {
+      "epoch": 0.0021001458434613514,
+      "grad_norm": 2.405668020248413,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.455,
+      "step": 27
+    },
+    {
+      "epoch": 0.002333495381623724,
+      "grad_norm": 2.5914838314056396,
+      "learning_rate": 0.0,
+      "loss": 2.5107,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null