Training in progress, step 188, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44422a94a97be5919c4f8acf50c2d6cc910db29c178068c091ab4d9dfb7add7f
+oid sha256:c5fee9b3be3ceee10186d35e87ac0167e8f551634db0ee10b7fd71dcdb471a64
 size 368988278

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27486bbb86c05ad439b79d09b4e894cab395d3edf735d4ca92b233100a99ffac
+oid sha256:3edc9997421f59a2bab339723bfa57da56d3a3caeb07533babc705299d70ed21
 size 1107079290

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d9b86dea31fa233a9cd83c58b8309c25b99ab9d7e9c98c615fdb07adc8f1bd6
+oid sha256:906448df3b925c4237703b09a08232c313d6b304e3d61120e14d73631f8cabd0
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5304600082884376,
+  "epoch": 0.9972648155822628,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 188,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,62 @@
       "eval_samples_per_second": 821.122,
       "eval_steps_per_second": 25.712,
       "step": 100
+    },
+    {
+      "epoch": 0.5835060091172813,
+      "grad_norm": 13.484375,
+      "learning_rate": 9.988603516333233e-07,
+      "loss": 24.8423,
+      "step": 110
+    },
+    {
+      "epoch": 0.6365520099461252,
+      "grad_norm": 12.78125,
+      "learning_rate": 9.987567472363527e-07,
+      "loss": 24.5701,
+      "step": 120
+    },
+    {
+      "epoch": 0.689598010774969,
+      "grad_norm": 13.5625,
+      "learning_rate": 9.98653142839382e-07,
+      "loss": 24.5008,
+      "step": 130
+    },
+    {
+      "epoch": 0.7426440116038127,
+      "grad_norm": 10.8046875,
+      "learning_rate": 9.985495384424114e-07,
+      "loss": 24.1657,
+      "step": 140
+    },
+    {
+      "epoch": 0.7956900124326565,
+      "grad_norm": 15.5078125,
+      "learning_rate": 9.984459340454408e-07,
+      "loss": 24.2864,
+      "step": 150
+    },
+    {
+      "epoch": 0.8487360132615002,
+      "grad_norm": 11.609375,
+      "learning_rate": 9.983423296484702e-07,
+      "loss": 24.0425,
+      "step": 160
+    },
+    {
+      "epoch": 0.901782014090344,
+      "grad_norm": 11.1171875,
+      "learning_rate": 9.982387252514998e-07,
+      "loss": 24.1412,
+      "step": 170
+    },
+    {
+      "epoch": 0.9548280149191878,
+      "grad_norm": 15.390625,
+      "learning_rate": 9.98135120854529e-07,
+      "loss": 23.766,
+      "step": 180
     }
   ],
   "logging_steps": 10,
@@ -99,12 +155,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.7611165777461248e+17,
+  "total_flos": 5.1908991489828454e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null