Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:778eedd64602845047062e2a1581fe9bb85674d01c7e0b67207a07f3766bebfe
+oid sha256:c78c3bc80294621f4002d52124079ffb07ac373cf9f3b4eab2aea8b5ebaa7552
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f24289a734750455bda70547b39d0bfc7b0a3ce87d9ddef16b6c2b13837148a
+oid sha256:299547582c38b18d60c067ceee09cd8e6c034e39289399fcf65c581a8b2aa462
 size 20632762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 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": 0.002695871946082561,
+  "epoch": 0.0035944959281100815,
   "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": 58.84,
       "eval_steps_per_second": 29.42,
       "step": 15
+    },
+    {
+      "epoch": 0.002875596742488065,
+      "grad_norm": 3.454861879348755,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.3034,
+      "step": 16
+    },
+    {
+      "epoch": 0.0030553215388935693,
+      "grad_norm": 3.430015802383423,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.2587,
+      "step": 17
+    },
+    {
+      "epoch": 0.0032350463352990733,
+      "grad_norm": 3.1308865547180176,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.3871,
+      "step": 18
+    },
+    {
+      "epoch": 0.0034147711317045774,
+      "grad_norm": 3.044804811477661,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 3.0914,
+      "step": 19
+    },
+    {
+      "epoch": 0.0035944959281100815,
+      "grad_norm": 3.2286853790283203,
+      "learning_rate": 0.0,
+      "loss": 3.2646,
+      "step": 20
+    },
+    {
+      "epoch": 0.0035944959281100815,
+      "eval_loss": 3.3288919925689697,
+      "eval_runtime": 159.0883,
+      "eval_samples_per_second": 58.911,
+      "eval_steps_per_second": 29.455,
+      "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": 5592283789393920.0,
+  "total_flos": 7415588569743360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null