Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66fa69c55f4cc539bfd7eeff21e2a8835faab284683500af2e49c58a7febcefc
+oid sha256:0a4bda59c28deb9c8ce2b5ea32115712d08dda9b80b999ebd634855767986719
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc5474a7eb1ef6bcd05c2e54d7fb2b90bb75ef2c3ee218f2708da7c7a1b1a73
+oid sha256:7e9543c7deeaec4382645b7b1aed0ed4688edd9136eb9e041fe58d8b54accd3a
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57ff65dae4d93bc6f3ce28e1c0ebd64b3f07e2650a62a688a062d79b9112b67
+oid sha256:4b68c240df99005b4953409aa7c52161db6b8b35e9abfde46531de4bfe3403b8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380805505206fcae9055c4a9e78aed7a5dda390c746cad96ecf2259c970f0ba0
+oid sha256:28c50acebbdd320cdbda27b93feb5d91578ce2eb03d7fc0517b7bfffd55baef8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0020224637942865397,
+  "epoch": 0.002311387193470331,
   "eval_steps": 2,
-  "global_step": 14,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,28 @@
       "eval_samples_per_second": 7.074,
       "eval_steps_per_second": 3.538,
       "step": 14
+    },
+    {
+      "epoch": 0.0021669254938784356,
+      "grad_norm": 12.992769241333008,
+      "learning_rate": 5e-05,
+      "loss": 8.358,
+      "step": 15
+    },
+    {
+      "epoch": 0.002311387193470331,
+      "grad_norm": 10.932060241699219,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 9.3938,
+      "step": 16
+    },
+    {
+      "epoch": 0.002311387193470331,
+      "eval_loss": 2.366903066635132,
+      "eval_runtime": 412.0962,
+      "eval_samples_per_second": 7.074,
+      "eval_steps_per_second": 3.538,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -188,7 +210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4574252510478336.0,
+  "total_flos": 5227717154832384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null