Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8611365ec5a858ac1fbd3d9eb61c0830f14eb6ec2aed3c7cff5e7ec8e5b001
+oid sha256:d4d38591876936611077682081f5a3014e29e95e4f061115b2dca1eda61ea307
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f0370173beae87b0831032e509a26f9b90b0976b74a081b4cdc061d7310d35
+oid sha256:15fe52832b3b11201d459cc7a3732518e4a5f6ab60c1872f59a55bc7dba2cfab
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c87fba58cd83a1346638b75af3b09e5621fa0899bcf250c1f1b8c6657363d66
+oid sha256:72651c7540cbbcf5427db4027989c008824318b8a8caa0187a4c96f78312cd92
 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": 0.0011740976006261853,
+  "epoch": 0.001505253334136135,
   "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": 1.9769,
       "step": 35
+    },
+    {
+      "epoch": 0.0012042026673089081,
+      "grad_norm": 0.2649514973163605,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0423,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012042026673089081,
+      "eval_loss": 2.0345399379730225,
+      "eval_runtime": 520.2716,
+      "eval_samples_per_second": 26.884,
+      "eval_steps_per_second": 13.443,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013547280007225216,
+      "grad_norm": 0.2631724774837494,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0381,
+      "step": 45
+    },
+    {
+      "epoch": 0.001505253334136135,
+      "grad_norm": 0.2650676965713501,
+      "learning_rate": 0.0,
+      "loss": 2.0805,
+      "step": 50
+    },
+    {
+      "epoch": 0.001505253334136135,
+      "eval_loss": 2.0340166091918945,
+      "eval_runtime": 519.8158,
+      "eval_samples_per_second": 26.908,
+      "eval_steps_per_second": 13.455,
+      "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": 2444091551907840.0,
+  "total_flos": 3124324152115200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null