Training in progress, step 1480, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9dd76d05a2e42f0a235870826cac6a1a862e9177e3fdfc3df6375bf8c962f7
+oid sha256:c391de231f7ed92186d1a10241a7ab5e952075a13c23d6b84b45492cee3429f0
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73180325001e7199a9fa8e307df983b768067a47ac2bb87f53ed33257cc518b1
+oid sha256:faad0a21dc9b580a03e494fae6387e0a3b73c49e378acf3d445af2e73b59951b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c1026c80e7a89c43cc4cbd7020f54f744ae2ab2afdd4d9cfc2858c89eab249
+oid sha256:7ca61b35c59ebd89a4825d5fbf02c06acba38873c8cf9ce9e1e69e27d21b4b17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c51b6cd9a7a4b073d03f781b9c72ee76a68ab37d000246487885bc3137149e4
+oid sha256:ed33a752681152f4a94d0c64e56b596a28750fb35fe8a480a0094b3610dd201e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5223613595706619,
+  "epoch": 0.5295169946332737,
   "eval_steps": 500,
-  "global_step": 1460,
+  "global_step": 1480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1175,14 +1175,30 @@
       "loss": 0.4212,
       "num_input_tokens_seen": 981582,
       "step": 1460
+    },
+    {
+      "epoch": 0.5259391771019678,
+      "grad_norm": 0.3248649835586548,
+      "learning_rate": 9.481216457960644e-05,
+      "loss": 0.4052,
+      "num_input_tokens_seen": 988838,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5295169946332737,
+      "grad_norm": 0.23017796874046326,
+      "learning_rate": 9.409660107334526e-05,
+      "loss": 0.4019,
+      "num_input_tokens_seen": 995054,
+      "step": 1480
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 981582,
+  "num_input_tokens_seen": 995054,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.2072312829177856e+16,
+  "total_flos": 2.237525053426483e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null