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:d84907382e6743fa94ccae605274c46ca9a37968f360d7b61a36dc7c2504fc92
+oid sha256:d57e44c23e83c3389412d5afd96ecadfc38f7efcf1735ffb3aa04db49a8f133b
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d5706dbdc22e24884f1e7a50e570241e3498ac6179a4f1bcd0c5e7bafc5b93b
+oid sha256:41e4b698d400e01e1133ac948045750dcb3d10889b6001237278df46c1a105ef
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
+oid sha256:f0cab76d95a75c34838cec8f4adace53a2d256142482eba847df4bb06de7690f
 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": 0.08491066690252963,
+  "epoch": 0.11321422253670617,
   "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": 75.6,
       "eval_steps_per_second": 37.863,
       "step": 15
+    },
+    {
+      "epoch": 0.09057137802936494,
+      "grad_norm": 0.24435019493103027,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.4197,
+      "step": 16
+    },
+    {
+      "epoch": 0.09623208915620025,
+      "grad_norm": 0.24444067478179932,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.4299,
+      "step": 17
+    },
+    {
+      "epoch": 0.10189280028303556,
+      "grad_norm": 0.26259520649909973,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.4198,
+      "step": 18
+    },
+    {
+      "epoch": 0.10755351140987086,
+      "grad_norm": 0.2749709188938141,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.4089,
+      "step": 19
+    },
+    {
+      "epoch": 0.11321422253670617,
+      "grad_norm": 0.2748180031776428,
+      "learning_rate": 0.0,
+      "loss": 10.421,
+      "step": 20
+    },
+    {
+      "epoch": 0.11321422253670617,
+      "eval_loss": 10.425971984863281,
+      "eval_runtime": 7.8732,
+      "eval_samples_per_second": 75.573,
+      "eval_steps_per_second": 37.85,
+      "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": 12552587182080.0,
+  "total_flos": 16736782909440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null