Training in progress, step 6700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c13f2cc73f2b50eb3054c4f9f34e24e00ccbb2ee12f40760019fdb6ba4a7264
+oid sha256:baab6ce921f1613f657e84693cedae976231955db151735d337f863663c7e95d
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dc0a407b3cd6fb8c2009a5a2e28b1a647ee883170696f020ccd1bf2d47f70d5
+oid sha256:1b5cfe34653a49f261818a83aeb56f415a305909d4642a477a11be9eec2dd304
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dc43f4f08c4cb18483c623c72390b89d9e5c0e070695c8546fdb6db415c2659
+oid sha256:496c0941a8254c7f1b866b7962463a46dae8fc62e73271e65fb12a07ffd6629e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e6df07c2fbddd7c7262a897eedc5919a19077162b1c7b5831b4ba1cffd7cac
+oid sha256:fab7e6b1d1ff4eafb72e67dcebe45ceb949977389095195924aab3d52c70cb9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5344,
+  "epoch": 0.536,
   "eval_steps": 500,
-  "global_step": 6680,
+  "global_step": 6700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2345,6 +2345,13 @@
       "learning_rate": 2.329817541708346e-05,
       "loss": 3.4163,
       "step": 6680
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 21.337862014770508,
+      "learning_rate": 2.3257661740587055e-05,
+      "loss": 3.3443,
+      "step": 6700
     }
   ],
   "logging_steps": 20,
@@ -2352,7 +2359,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.5763273798680576e+16,
+  "total_flos": 1.5820716951601152e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null