Training in progress, step 88, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a9689b639bef095f9d9be7c853dccf8edf48cf90aa66c07dac321499f5c1b3a
+oid sha256:15a814bc0de78d4a61f530665270046aeb2ae360e904ccece46f218ac88f40fc
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47bf0179e2a4f1eeeb42ae6e4662fe4587b5985584c76b0c01db6e9128db7ec5
+oid sha256:fc2e1157b29ecd0e179c5d66dae8354162847dad5dc2734e63939c7556de2b63
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea8f3c63b5a91434b55a7db9e9e888ce98c5d36cce664bfecf470c814be0613
+oid sha256:bf306a9b1914534d727644260ec730fedc7b57bd2d8fd998953572a924983513
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916fdec13e6efc15b18e2a6b6d384a81cd69075368b316d9722fd8205c98017b
+oid sha256:01a4e7013bdf0cfef44b18348c4082377d680816016af2638e8995bf0bb3c8d9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04992589125516811,
+  "epoch": 0.05491848038068492,
   "eval_steps": 8,
-  "global_step": 80,
+  "global_step": 88,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -277,6 +277,35 @@
       "eval_samples_per_second": 9.397,
       "eval_steps_per_second": 4.699,
       "step": 80
+    },
+    {
+      "epoch": 0.05054996489585771,
+      "grad_norm": 0.31652024388313293,
+      "learning_rate": 8.047222744854943e-06,
+      "loss": 0.7595,
+      "step": 81
+    },
+    {
+      "epoch": 0.052422185817926514,
+      "grad_norm": 0.3957296907901764,
+      "learning_rate": 3.6037139304146762e-06,
+      "loss": 0.802,
+      "step": 84
+    },
+    {
+      "epoch": 0.05429440673999532,
+      "grad_norm": 0.32933101058006287,
+      "learning_rate": 9.0502382320653e-07,
+      "loss": 0.802,
+      "step": 87
+    },
+    {
+      "epoch": 0.05491848038068492,
+      "eval_loss": 0.7515419125556946,
+      "eval_runtime": 574.5854,
+      "eval_samples_per_second": 9.395,
+      "eval_steps_per_second": 4.697,
+      "step": 88
     }
   ],
   "logging_steps": 3,
@@ -296,7 +325,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.256153676546048e+17,
+  "total_flos": 4.681769044200653e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null