Training in progress, step 1460, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d6c5c98da7d7fc2308ce4cce8c077dacdaefc9c3e45997ff2a0b612a1ad5fb
+oid sha256:0a9dd76d05a2e42f0a235870826cac6a1a862e9177e3fdfc3df6375bf8c962f7
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf5fd6b5c41b0e5fd63b47580a5cc765e806b828011f641bf5fad58475b4f01
+oid sha256:73180325001e7199a9fa8e307df983b768067a47ac2bb87f53ed33257cc518b1
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db1fc58a2a72dbad3c41b2357780fb02b9c10ea5bf856d5df562a584278bb4f
+oid sha256:f2c1026c80e7a89c43cc4cbd7020f54f744ae2ab2afdd4d9cfc2858c89eab249
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0fed88b87dca8914fe3b96a952dda114e542b0650af3a03c544afb4eea3bd4e
+oid sha256:2c51b6cd9a7a4b073d03f781b9c72ee76a68ab37d000246487885bc3137149e4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5152057245080501,
+  "epoch": 0.5223613595706619,
   "eval_steps": 500,
-  "global_step": 1440,
+  "global_step": 1460,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1159,14 +1159,30 @@
       "loss": 0.4031,
       "num_input_tokens_seen": 967800,
       "step": 1440
+    },
+    {
+      "epoch": 0.518783542039356,
+      "grad_norm": 0.4523704946041107,
+      "learning_rate": 9.62432915921288e-05,
+      "loss": 0.3753,
+      "num_input_tokens_seen": 973223,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5223613595706619,
+      "grad_norm": 0.3966517448425293,
+      "learning_rate": 9.552772808586763e-05,
+      "loss": 0.4212,
+      "num_input_tokens_seen": 981582,
+      "step": 1460
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 967800,
+  "num_input_tokens_seen": 981582,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.17624043188224e+16,
+  "total_flos": 2.2072312829177856e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null