Training in progress, step 6740, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baab6ce921f1613f657e84693cedae976231955db151735d337f863663c7e95d
+oid sha256:7bb5fc18755b1bc902fa960b0f60645e025420e2f705caa8dd38fa32ba2a515f
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5cfe34653a49f261818a83aeb56f415a305909d4642a477a11be9eec2dd304
+oid sha256:ba29c27cd92ae55f3cbe6a02b6f053222af12f4509080505a7f771088cee1368
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:496c0941a8254c7f1b866b7962463a46dae8fc62e73271e65fb12a07ffd6629e
+oid sha256:efc7a7c74bad975dd9444229576dbd2c0f4d486da085dd3b0799e3c2cfd1606c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab7e6b1d1ff4eafb72e67dcebe45ceb949977389095195924aab3d52c70cb9d
+oid sha256:ab72aa2c0b933f851e99251a29f0e0981ef1d4f3067a1de99a80ef1648d5af32
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.536,
+  "epoch": 0.5392,
   "eval_steps": 500,
-  "global_step": 6700,
+  "global_step": 6740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2352,6 +2352,20 @@
       "learning_rate": 2.3257661740587055e-05,
       "loss": 3.3443,
       "step": 6700
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 38.06822204589844,
+      "learning_rate": 2.3217061445126444e-05,
+      "loss": 3.4762,
+      "step": 6720
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 27.79935646057129,
+      "learning_rate": 2.3176374956579525e-05,
+      "loss": 3.4748,
+      "step": 6740
     }
   ],
   "logging_steps": 20,
@@ -2359,7 +2373,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.5820716951601152e+16,
+  "total_flos": 1.5917855258738688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null