Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a3d6d64873d72ccb4d6aab32514e385fdb79f364bbe3bfa15f4989fc678f1ca
+oid sha256:6782d9c18e4e4e4fea29ba54749f63f0db722c70f467d0023eda72bf9219a558
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d4fc3c09ac1c108335af5f57d98e42094e5637d27c6dcc87f3556c43089ec8
+oid sha256:4cdec188575dbf0eb2185e60afba725a3f99ba20ca9de25a0270611c216398c3
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8281579f6927ce1701283c7919e23a1b3d72217b3b8001cf7039ebd58df230a
+oid sha256:d84ff24272829488712f1989a7155b45cfe23d2e4fa9c1135e2fa3ea3593371d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0a9ae08a837d696210720a364c40061c9c8b036f36570a99f11fe3b8d70f51
+oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00032510972453202955,
+  "epoch": 0.0006502194490640591,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 37.673,
       "eval_steps_per_second": 18.839,
       "step": 13
+    },
+    {
+      "epoch": 0.0005001688069723531,
+      "grad_norm": 6.103735446929932,
+      "learning_rate": 0.0002,
+      "loss": 2.3802,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006502194490640591,
+      "eval_loss": 2.205092191696167,
+      "eval_runtime": 223.9454,
+      "eval_samples_per_second": 37.594,
+      "eval_steps_per_second": 18.799,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 339288173051904.0,
+  "total_flos": 678576346103808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null