Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2842aa330f078d4ee66044bd6756720cb67567a2814c26b479b54e22dbc650b4
+oid sha256:d852191c874e90cb2858a67e4d8dbb1caba2b111a608a63b74e91f7f19074110
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5545bee7101c6d311e8404393c4c37157ac7324d0ccea45cb343703c8b5a0b24
+oid sha256:2f24bccee89ac9645ad1076790c22de699fea1e268f16627337699e92f8f82de
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a4d40f9c4bf65078886d54e1cfc54df5ccabb01b6dd112966b8979e806e106
+oid sha256:65941554dfccfdcf0ed28341039200adb2012eef3c09ec7b1fbc4a815a622955
 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": 0.0030321289043518823,
+  "epoch": 0.00388734474916908,
   "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": 0.6389,
       "step": 35
+    },
+    {
+      "epoch": 0.003109875799335264,
+      "grad_norm": 5.322411060333252,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.346,
+      "step": 40
+    },
+    {
+      "epoch": 0.003109875799335264,
+      "eval_loss": 0.5726699829101562,
+      "eval_runtime": 368.4717,
+      "eval_samples_per_second": 14.699,
+      "eval_steps_per_second": 7.349,
+      "step": 40
+    },
+    {
+      "epoch": 0.003498610274252172,
+      "grad_norm": 9.603562355041504,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7611,
+      "step": 45
+    },
+    {
+      "epoch": 0.00388734474916908,
+      "grad_norm": 4.514232635498047,
+      "learning_rate": 0.0,
+      "loss": 0.4263,
+      "step": 50
+    },
+    {
+      "epoch": 0.00388734474916908,
+      "eval_loss": 0.5639113783836365,
+      "eval_runtime": 373.153,
+      "eval_samples_per_second": 14.514,
+      "eval_steps_per_second": 7.257,
+      "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": 7305778780176384.0,
+  "total_flos": 9386538559340544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null