Training in progress, step 1440, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aad36523f653c0b77cbc992ea91311b49e96a68b9bac8b5fc5e7ff63686ac900
+oid sha256:64d6c5c98da7d7fc2308ce4cce8c077dacdaefc9c3e45997ff2a0b612a1ad5fb
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eae06a37ddc2a57f0d2662fd5d5d2cdd831ea69bc665ae17cf29a05b11e5d13
+oid sha256:bdf5fd6b5c41b0e5fd63b47580a5cc765e806b828011f641bf5fad58475b4f01
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:611ff9c30a238fa31d0058e6fc82212ffbe063da1a3832f3d98bad700efec653
+oid sha256:5db1fc58a2a72dbad3c41b2357780fb02b9c10ea5bf856d5df562a584278bb4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ee649f42236fc3525c15f4fc06e3387d0e6ad85bc6902d30e2ef469b193aea2
+oid sha256:c0fed88b87dca8914fe3b96a952dda114e542b0650af3a03c544afb4eea3bd4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5080500894454383,
+  "epoch": 0.5152057245080501,
   "eval_steps": 500,
-  "global_step": 1420,
+  "global_step": 1440,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1143,14 +1143,30 @@
       "loss": 0.3953,
       "num_input_tokens_seen": 955261,
       "step": 1420
+    },
+    {
+      "epoch": 0.5116279069767442,
+      "grad_norm": 0.3044353723526001,
+      "learning_rate": 9.767441860465116e-05,
+      "loss": 0.4226,
+      "num_input_tokens_seen": 961797,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5152057245080501,
+      "grad_norm": 0.4201965928077698,
+      "learning_rate": 9.695885509838999e-05,
+      "loss": 0.4031,
+      "num_input_tokens_seen": 967800,
+      "step": 1440
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 955261,
+  "num_input_tokens_seen": 967800,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.148044648894669e+16,
+  "total_flos": 2.17624043188224e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null