Training in progress, step 2360, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8abb44f6aca403f71064a572c838010e4fcf7984d9faf66f884911976f427e2c
+oid sha256:bd0aba29ef3bfaae1191218954a63d90da222aed22aa2200b611cf74f049d222
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5421b6835db3269773718c76f42b20f1029476f55863aace65468871b75acead
+oid sha256:9d8cd6e4f50429cda27a28378dce5408f87f0a91096366b51efe3dd54bb9f0e0
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2906515e1bcbf65ec65f30890fb86fc07abf4f380736f4d75d70f44ddd1a161
+oid sha256:3eea0d25f64360cae73a775ba2c6c88f883be49aa9244b8f3d005a3b98fa5466
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0edca768de2b612c93b0f82e9eb2540d009ac62af5eb1b92baccfef4a526aeb
+oid sha256:328a8cc6caa8e9e02ff012a126152b40a2427772a86d6a8867f005290455d35c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8372093023255814,
+  "epoch": 0.8443649373881932,
   "eval_steps": 500,
-  "global_step": 2340,
+  "global_step": 2360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1879,14 +1879,30 @@
       "loss": 0.362,
       "num_input_tokens_seen": 1586863,
       "step": 2340
+    },
+    {
+      "epoch": 0.8407871198568873,
+      "grad_norm": 0.3128429353237152,
+      "learning_rate": 3.184257602862254e-05,
+      "loss": 0.373,
+      "num_input_tokens_seen": 1593227,
+      "step": 2350
+    },
+    {
+      "epoch": 0.8443649373881932,
+      "grad_norm": 0.3150210678577423,
+      "learning_rate": 3.112701252236136e-05,
+      "loss": 0.3722,
+      "num_input_tokens_seen": 1601444,
+      "step": 2360
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1586863,
+  "num_input_tokens_seen": 1601444,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.5682945034696704e+16,
+  "total_flos": 3.601082023346995e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null