Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288a97230b84be31f54bd24306a27101c685b8d76c9b92fde4eec893dc79ff60
+oid sha256:8ae205ed0244d8b8d68ae976b3e253229f67d9113129e01e7eb80070f91a9893
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074f067f1051dd5754e6b3ffc3a5ab216414e4701fe9127f27ca7216c99c4c51
+oid sha256:6fc0248eebe0e2dfdbd7ce559242bece6c3b29ae293569a0788024b940fccf69
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89125b381bd706e47d0969ca57bde232385b184bb6fee985c4b095b282bae7af
+oid sha256:3f04944917c15f265951392f0ad036c49b2e1d3572ae924179abc0eb1dc0ce1c
 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": 0.0021240673165949567,
+  "epoch": 0.0027231632264037905,
   "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": 0.525,
       "step": 35
+    },
+    {
+      "epoch": 0.0021785305811230326,
+      "grad_norm": 4.558568954467773,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4886,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021785305811230326,
+      "eval_loss": 0.47880464792251587,
+      "eval_runtime": 622.0545,
+      "eval_samples_per_second": 12.428,
+      "eval_steps_per_second": 6.215,
+      "step": 40
+    },
+    {
+      "epoch": 0.0024508469037634118,
+      "grad_norm": 5.0720930099487305,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5172,
+      "step": 45
+    },
+    {
+      "epoch": 0.0027231632264037905,
+      "grad_norm": 4.553873538970947,
+      "learning_rate": 0.0,
+      "loss": 0.3429,
+      "step": 50
+    },
+    {
+      "epoch": 0.0027231632264037905,
+      "eval_loss": 0.4715513586997986,
+      "eval_runtime": 621.6087,
+      "eval_samples_per_second": 12.437,
+      "eval_steps_per_second": 6.219,
+      "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": 7453256523448320.0,
+  "total_flos": 9555457081344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null