Training in progress, step 56, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a249c8004081b9004e69983f978e119b5bf2063bc16bae03b87b6c29ca74a0
+oid sha256:fbaf1ed57b17e15838d7ba427275c71e5239abd01fce75f2b8831fac26d5aba5
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d155b28f5e7ed79a50ef3a32a655a17e7d9d4a06d622aba236d8bd6b5b6c0883
+oid sha256:33281a030601722e6e5833c52b1e422fe1559d066595f17c423831e4db7eafe0
 size 328468404

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be25ff62256a472fa1f448e3d453c1943f4c5ebc354b49207e62f20236deb6a
+oid sha256:18d1e322d844019667efd77005c343afd5a843933d60a6d377f0cac5bb77cb19
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f415cc44747810bca05c75d13f5253fa09a627c8a57f4da3e109dd0e1d508c
+oid sha256:6db846ff2ee419b9368c374e099a2c577a7103459c8f15233032b76636eccd21
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4dff8eb55605cbb8ac33421a282c2a3344fd33ccc979ba253b9e98ac353951c
+oid sha256:346c719b46ba2add08db3614f24dfa501356aff6bef89984c3850b171d54a423
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16dedcb8131c0bf718453558c27ee6713605b2e55751923de748d81e923d0f55
+oid sha256:ac6abe539c42e12e554dbb33ca0979eacce661411ac7da2a82a07086d592ab60
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab4a9e4ef073c8d05cbd3393b8f5e2be7efebf8d31894ffbc118b030a35e18a
+oid sha256:882cbcdafabe936edc086ed06911378377212c19ac6648379eaecef2ba03d21c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9405940594059405,
+  "epoch": 2.217821782178218,
   "eval_steps": 7,
-  "global_step": 49,
+  "global_step": 56,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -183,6 +183,28 @@
       "eval_samples_per_second": 66.119,
       "eval_steps_per_second": 4.667,
       "step": 49
+    },
+    {
+      "epoch": 2.01980198019802,
+      "grad_norm": 1.8872629404067993,
+      "learning_rate": 3.141687721698363e-05,
+      "loss": 1.4865,
+      "step": 51
+    },
+    {
+      "epoch": 2.1386138613861387,
+      "grad_norm": 0.8172866106033325,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9957,
+      "step": 54
+    },
+    {
+      "epoch": 2.217821782178218,
+      "eval_loss": 1.3781214952468872,
+      "eval_runtime": 1.286,
+      "eval_samples_per_second": 66.094,
+      "eval_steps_per_second": 4.665,
+      "step": 56
     }
   ],
   "logging_steps": 3,
@@ -202,7 +224,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3934508787525222e+17,
+  "total_flos": 1.5925152900028826e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null