Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff6f7c7d919c4aa3aa022ca5e0c197de5faf259ecb32201d97797235ac1c753
+oid sha256:c68c54cfebc6fb9825303787afa3c2775739f767c8afb9190e60b1cd27a4e714
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f04fc892e014b6bc265869739aa884e033b443850ea42ed2c7a274b3d943b4
+oid sha256:6015b4b3463e9ed4334609e7dc7d61568a5816a69d49940bd525269c2c2830e3
 size 41119636

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": 0.013099006658661719,
+  "epoch": 0.017465342211548957,
   "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": 22.921,
       "eval_steps_per_second": 11.466,
       "step": 15
+    },
+    {
+      "epoch": 0.013972273769239166,
+      "grad_norm": 1.483850359916687,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 12.8118,
+      "step": 16
+    },
+    {
+      "epoch": 0.014845540879816614,
+      "grad_norm": 1.431255578994751,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 12.838,
+      "step": 17
+    },
+    {
+      "epoch": 0.015718807990394063,
+      "grad_norm": 1.660539984703064,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 13.8481,
+      "step": 18
+    },
+    {
+      "epoch": 0.01659207510097151,
+      "grad_norm": 1.5521190166473389,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 12.7012,
+      "step": 19
+    },
+    {
+      "epoch": 0.017465342211548957,
+      "grad_norm": 1.3667329549789429,
+      "learning_rate": 0.0,
+      "loss": 15.7016,
+      "step": 20
+    },
+    {
+      "epoch": 0.017465342211548957,
+      "eval_loss": NaN,
+      "eval_runtime": 84.0417,
+      "eval_samples_per_second": 22.953,
+      "eval_steps_per_second": 11.482,
+      "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": 1.9463553442381824e+16,
+  "total_flos": 2.5978550410543104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null