Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37712096092d8d16805f1851c0cb5487c1de2a7e290293d6cb6687f076ec6366
+oid sha256:87daf2899d04d4febe58137194d308fe861c5231fea46a7e0ec272a670f8cd16
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ca88a3291a3f98680748610a53429c8f18e90fc183970e1796d919e06c73aa
+oid sha256:8bf1ffd51c3c288369dda643d8d02e835aece8f42b13f5ad2200dbfea8581807
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c56893ec02e2f131eda7c55d301561be28b6d224e001718380f1874157a5126
+oid sha256:13676d798414c5410cf7017c7ac5e30ea37d51120efaf6a4e6bf8aca5800315c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.059332509270704575,
+  "epoch": 0.07911001236093942,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 2.77,
       "eval_steps_per_second": 1.385,
       "step": 15
+    },
+    {
+      "epoch": 0.06328800988875155,
+      "grad_norm": 53.142982482910156,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 74.962,
+      "step": 16
+    },
+    {
+      "epoch": 0.06724351050679851,
+      "grad_norm": 52.852928161621094,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 68.2094,
+      "step": 17
+    },
+    {
+      "epoch": 0.07119901112484549,
+      "grad_norm": 48.375308990478516,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 67.8407,
+      "step": 18
+    },
+    {
+      "epoch": 0.07515451174289246,
+      "grad_norm": 47.157535552978516,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 66.793,
+      "step": 19
+    },
+    {
+      "epoch": 0.07911001236093942,
+      "grad_norm": 44.836360931396484,
+      "learning_rate": 0.0,
+      "loss": 63.8398,
+      "step": 20
+    },
+    {
+      "epoch": 0.07911001236093942,
+      "eval_loss": 2.0867512226104736,
+      "eval_runtime": 307.8872,
+      "eval_samples_per_second": 2.767,
+      "eval_steps_per_second": 1.384,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.5682996845674496e+17,
+  "total_flos": 2.0910662460899328e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null