Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156f276758316a99af9908f873723249666a6343317cd60f4ce0c3f30c372763
+oid sha256:c4ec6b96f3989633799ef9c6c85213a1bc5d81ea97b7fc483ae326b1c54534d9
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a24df2cfafa8f843a944ed1b0f6c1542c007e823cc58b9e950690b3f095ffdf
+oid sha256:ded7606b8e0f100ac0178a84c08f8b75e7725fbb51a7cdac8cba579a465fcdcf
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3402faab675d6ce12c7f65f4a41ea9563097b3e01456d349846f69b226bf1713
+oid sha256:012b3b2b1bae7e97243636afca60a311a7f1bb7f71a5d26125718cc46a272c98
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6363636363636362,
+  "epoch": 1.8181818181818183,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 36.095,
       "eval_steps_per_second": 4.727,
       "step": 81
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 0.9477640986442566,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 2.0882,
+      "step": 84
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 0.9164983630180359,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 2.046,
+      "step": 87
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 1.078360915184021,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 2.0393,
+      "step": 90
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "eval_loss": 2.0764904022216797,
+      "eval_runtime": 2.319,
+      "eval_samples_per_second": 36.223,
+      "eval_steps_per_second": 4.743,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1153390976303104e+16,
+  "total_flos": 2.3504674882584576e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null