Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80200b7412a4d398d83f5e1c5b2790c427ac843ac6f8dcc4ca7165f149bbe890
+oid sha256:1a9689b639bef095f9d9be7c853dccf8edf48cf90aa66c07dac321499f5c1b3a
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f82149b96dd41c99aa2266e2fb6f3c7a68484a26112c5c82203a7dc357fdf591
+oid sha256:47bf0179e2a4f1eeeb42ae6e4662fe4587b5985584c76b0c01db6e9128db7ec5
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54695bae591aceb2574c0570650d7a15033601e879a5235bc5ef9cc452369efd
+oid sha256:8ea8f3c63b5a91434b55a7db9e9e888ce98c5d36cce664bfecf470c814be0613
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f589044fe72a89eeac5f01dfea2599de04455cb66e0a4998ee4eb766326c4c
+oid sha256:916fdec13e6efc15b18e2a6b6d384a81cd69075368b316d9722fd8205c98017b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0449333021296513,
+  "epoch": 0.04992589125516811,
   "eval_steps": 8,
-  "global_step": 72,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -255,6 +255,28 @@
       "eval_samples_per_second": 9.398,
       "eval_steps_per_second": 4.699,
       "step": 72
+    },
+    {
+      "epoch": 0.0468055230517201,
+      "grad_norm": 0.39400896430015564,
+      "learning_rate": 2.181685175319702e-05,
+      "loss": 0.8015,
+      "step": 75
+    },
+    {
+      "epoch": 0.048677743973788906,
+      "grad_norm": 0.382411390542984,
+      "learning_rate": 1.415512063981339e-05,
+      "loss": 0.8092,
+      "step": 78
+    },
+    {
+      "epoch": 0.04992589125516811,
+      "eval_loss": 0.752012312412262,
+      "eval_runtime": 574.415,
+      "eval_samples_per_second": 9.397,
+      "eval_steps_per_second": 4.699,
+      "step": 80
     }
   ],
   "logging_steps": 3,
@@ -274,7 +296,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.830538308891443e+17,
+  "total_flos": 4.256153676546048e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null