Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d284b1d560898fc0603b1fee32bf7ea68b6a8247a8d28c2a66052934934c5b8
+oid sha256:f964111bd33261810d0621a00549eefd90bd647cb51da4fc8eb860df02aa270a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d7450430e030c207b9eab0291e968ee060c30719a3018521be3244312ebe9e
+oid sha256:fc02845aa45e80a81096ba86b17e73e18fc8947814c9f2a132537c89c880e92c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe13ad15b195f5f55a4a15d23b1790e9c53eeb31b3b109b65810d8f057c7a87c
+oid sha256:fc3ae8669dae6ed476b02f06f40e4ea995710e71293810d35f1edb9f11c0e981
 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": 0.008944441259102116,
+  "epoch": 0.01146723238346425,
   "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": 2.2858,
       "step": 35
+    },
+    {
+      "epoch": 0.009173785906771401,
+      "grad_norm": 0.36664125323295593,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2416,
+      "step": 40
+    },
+    {
+      "epoch": 0.009173785906771401,
+      "eval_loss": 2.3079323768615723,
+      "eval_runtime": 168.202,
+      "eval_samples_per_second": 10.915,
+      "eval_steps_per_second": 5.458,
+      "step": 40
+    },
+    {
+      "epoch": 0.010320509145117826,
+      "grad_norm": 0.45867276191711426,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1968,
+      "step": 45
+    },
+    {
+      "epoch": 0.01146723238346425,
+      "grad_norm": 0.4931580722332001,
+      "learning_rate": 0.0,
+      "loss": 2.301,
+      "step": 50
+    },
+    {
+      "epoch": 0.01146723238346425,
+      "eval_loss": 2.3058359622955322,
+      "eval_runtime": 168.0314,
+      "eval_samples_per_second": 10.927,
+      "eval_steps_per_second": 5.463,
+      "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": 1.11975403094016e+16,
+  "total_flos": 1.4292133267636224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null