Training in progress, step 6380, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:469c9ce6820a85a006cd1be1ac3e4bc00d3ff72e99862c889a25470f7a425355
+oid sha256:6d0dc7626ddde701087507da47f6483bfaa8f5f8e188458a83f2674165d89960
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f28a62275cf693c348113c53b24032412deef50018fc781c228dc840c1a2bf8
+oid sha256:96d7a1d37a2127f086863b0d86e41d38ac45c83459eba5f392016c96b8b91645
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4c351cd5bf9010bba98ddebc6172fea02d4349c1d4d85d7125985b1f4486fff
+oid sha256:f44a842856192a95499780f57278298938a0b08d05196d1a0077617782d19298
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a09e65d4f379cdacac12c0eb8ac2f7aee229cba4545b6e0dd83cf4c5c09dabe
+oid sha256:d00d77c9b01f729ad41511fced2214cb644688b952a92d0006d23c69218c0530
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5088,
+  "epoch": 0.5104,
   "eval_steps": 500,
-  "global_step": 6360,
+  "global_step": 6380,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2233,6 +2233,13 @@
       "learning_rate": 2.3934270118813024e-05,
       "loss": 3.4738,
       "step": 6360
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 24.581098556518555,
+      "learning_rate": 2.3895199510167793e-05,
+      "loss": 3.4775,
+      "step": 6380
     }
   ],
   "logging_steps": 20,
@@ -2240,7 +2247,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.5018678000943104e+16,
+  "total_flos": 1.5064671890374656e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null