Training in progress, step 65, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfb19cdffd8f2a70518ab31199f4b1827a2fbc7e048b596427974934df16daa
+oid sha256:b004125126c5ffcd7f5a52278582e0bbca469d3c94482cf7c834c9174f9bb268
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215dde8de4d4b55ff881d6061b02018ce74f36f87bf60b5e2a9be7f84ff0140d
+oid sha256:58626b946af51b020c1453719a4944beb19c24f35d12db6a55983a848644b8a4
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2c3514f0eafec6c2b250a2a0a609ed59534ef31c7ba11da3fe225c079d1575
+oid sha256:4d52029764bce6b207ece38b8ac6ef3a9c9a1677d93ff032b9d0c8abcf44917a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792ad29798cba378feffa861e2939c0c9205d97b89b46c0161cdef16a3d333a2
+oid sha256:fb438ab9499d5178d553290d304fad6bd105cd4f59f8f03d9657a249b7bd5f14
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014400443090556632,
+  "epoch": 0.01800055386319579,
   "eval_steps": 13,
-  "global_step": 52,
+  "global_step": 65,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -166,6 +166,42 @@
       "eval_samples_per_second": 13.191,
       "eval_steps_per_second": 1.65,
       "step": 52
+    },
+    {
+      "epoch": 0.014954306286347273,
+      "grad_norm": 3.195793628692627,
+      "learning_rate": 7.754484907260513e-05,
+      "loss": 1.4893,
+      "step": 54
+    },
+    {
+      "epoch": 0.015785101080033233,
+      "grad_norm": 2.969637393951416,
+      "learning_rate": 7.467541090321735e-05,
+      "loss": 1.5184,
+      "step": 57
+    },
+    {
+      "epoch": 0.016615895873719193,
+      "grad_norm": 2.318040609359741,
+      "learning_rate": 7.169418695587791e-05,
+      "loss": 1.5243,
+      "step": 60
+    },
+    {
+      "epoch": 0.01744669066740515,
+      "grad_norm": 3.390565872192383,
+      "learning_rate": 6.861468292009727e-05,
+      "loss": 1.4535,
+      "step": 63
+    },
+    {
+      "epoch": 0.01800055386319579,
+      "eval_loss": 0.36983951926231384,
+      "eval_runtime": 461.0103,
+      "eval_samples_per_second": 13.193,
+      "eval_steps_per_second": 1.651,
+      "step": 65
     }
   ],
   "logging_steps": 3,
@@ -185,7 +221,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.249073800419738e+16,
+  "total_flos": 1.0477654222307328e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null