Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e278fe75c0875651454a628fb5081e25c9b4eddb980049aa53d473f22d3859
+oid sha256:1df5141e8ddeb3a52fde5e36fc601b5e98a35a760b21dad4d770c16f1eab93ed
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ed5db3d6a74db1fc85886f2b7a625f5118fae9676ddbbe7eb972f86ea748ae
+oid sha256:93ead4589f80294e6843eb8b95d2991b1dc0bd7f68680239a89942448b55a764
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d455a0341a2c5c31eede937d31408b4b0a31f087c401955643a52ffd75f76a
+oid sha256:c4e6c6b149a116cec483f2a17b2bb809f7cc6274383aca9dd5c6e24801ded5e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf5b23a851e345e8e4081674591dcebfd10a22b109ff1badb1c585816cbde3fd
+oid sha256:d71dd396b34c87932ecfea63e93418697d0d152f826f8e27acd4064174d59bd1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3148479427549195,
+  "epoch": 0.3220035778175313,
   "eval_steps": 500,
-  "global_step": 880,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -711,14 +711,30 @@
       "loss": 0.4139,
       "num_input_tokens_seen": 587384,
       "step": 880
+    },
+    {
+      "epoch": 0.3184257602862254,
+      "grad_norm": 0.30183765292167664,
+      "learning_rate": 0.00013631484794275492,
+      "loss": 0.4412,
+      "num_input_tokens_seen": 594626,
+      "step": 890
+    },
+    {
+      "epoch": 0.3220035778175313,
+      "grad_norm": 0.24405309557914734,
+      "learning_rate": 0.00013559928443649375,
+      "loss": 0.4217,
+      "num_input_tokens_seen": 601425,
+      "step": 900
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 587384,
+  "num_input_tokens_seen": 601425,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.3208191876841472e+16,
+  "total_flos": 1.35239243825664e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null