Training in progress, step 7200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dbf43604912a67d12a82c3ddf5f1b939d015de908422b4c0f8e4699d02fcc4a
+oid sha256:44d89401fbca2f40400fdb6834e3a677208e11f52a19bc9be25c0057ea983475
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59c7c6053c0bd928ed9df145ce525bc50185508e88d636fcc91edf4745bcac0f
+oid sha256:beb9c6d2d11b4f177cc3790b2f12ad1c1f9399706b529d0ac545ef06d5c76f4d
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b74ab7e4f70a25c27af953fcf81e51d62ef1f062e1f6941b002637b31fbb04d6
+oid sha256:4e5ea69d1327aa2a2f41dcf01d7f65a4507c296565311e90ac8dee9f26a318d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e3e4f4d223c89d87dca50ebf348e1e323fc70dc0e5de01dc749be545d0332b2
+oid sha256:90eed9268b685a4adc40e6fe34acc82bd73b63bdc872d5161958be86a1c224ff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00520564142798181,
+  "epoch": 0.005354374040209862,
   "eval_steps": 2000,
-  "global_step": 7000,
+  "global_step": 7200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -252,6 +252,13 @@
       "learning_rate": 1.9999946677254565e-05,
       "loss": 1.5163,
       "step": 7000
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.813724994659424,
+      "learning_rate": 1.999994358178185e-05,
+      "loss": 1.5569,
+      "step": 7200
     }
   ],
   "logging_steps": 200,
@@ -259,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 9.194353461650227e+16,
+  "total_flos": 9.451356004088218e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null