Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c04b05e0c8350c80ac3527b674738930b892c247b965bd2659e10bd6ee44ff9
+oid sha256:5321e56934b34324cb00f4dcef13d379579af187a6bd32e75c83ac87c8024928
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a901e74c5adcb1c5881b64eeeeefee735ef00a2e2a4d166a0385003bf83c556
+oid sha256:637b4d99ef39ac909def2182245be5ca665ee45c010825e629eba4680aba8eb6
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f71c9d3267baf9c2b8096c6d7b74a49bbde096860c2ee8125089e1ffc5081e8f
+oid sha256:a4300d8b6f4c70f72e8e8cff18d74764ca7940a4984b5afd5af382974ab4bdd4
 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": 0.016586921850079744,
+  "epoch": 0.02126528442317916,
   "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": 2.7027,
       "step": 35
+    },
+    {
+      "epoch": 0.01701222753854333,
+      "grad_norm": 4.345822811126709,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.571,
+      "step": 40
+    },
+    {
+      "epoch": 0.01701222753854333,
+      "eval_loss": 2.0501210689544678,
+      "eval_runtime": 41.8304,
+      "eval_samples_per_second": 23.667,
+      "eval_steps_per_second": 11.833,
+      "step": 40
+    },
+    {
+      "epoch": 0.019138755980861243,
+      "grad_norm": 1.684922456741333,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.47,
+      "step": 45
+    },
+    {
+      "epoch": 0.02126528442317916,
+      "grad_norm": 1.7763071060180664,
+      "learning_rate": 0.0,
+      "loss": 1.1022,
+      "step": 50
+    },
+    {
+      "epoch": 0.02126528442317916,
+      "eval_loss": 2.0081968307495117,
+      "eval_runtime": 41.6129,
+      "eval_samples_per_second": 23.791,
+      "eval_steps_per_second": 11.895,
+      "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": 1905252268769280.0,
+  "total_flos": 2399807113003008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null