Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156851059b77c4d7020160b80d5becc95df67c510d798077699cdb4c8917146c
+oid sha256:c9ea622c8a3ae4b59a8a654fb9b816a6441441a0ec016517cea76ba07c389661
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b33af5b48ccb00c224f465ac6d92ed128c008ed363a96d4beae550320a50cdc9
+oid sha256:3d49636346021d81f2d7cc722ec13261c206beec25caa17e53c798c19ba71615
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3295d9b8e6727a0572a17fcd9e9c0c197ca020ea3fd15f4c9bf4d70bd654e602
+oid sha256:92b963127b22ddeab5c967c77cf61654178062a733d4a71d3b34be157aad97ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
+oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0316288877174486,
+  "epoch": 0.037954665260938325,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 7.113,
       "eval_steps_per_second": 0.89,
       "step": 45
+    },
+    {
+      "epoch": 0.03373748023194518,
+      "grad_norm": 0.19310009479522705,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 0.7162,
+      "step": 48
+    },
+    {
+      "epoch": 0.03584607274644175,
+      "grad_norm": 0.18422365188598633,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 0.7279,
+      "step": 51
+    },
+    {
+      "epoch": 0.037954665260938325,
+      "grad_norm": 0.2260413020849228,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 0.7397,
+      "step": 54
+    },
+    {
+      "epoch": 0.037954665260938325,
+      "eval_loss": 0.7391679286956787,
+      "eval_runtime": 337.1783,
+      "eval_samples_per_second": 7.109,
+      "eval_steps_per_second": 0.89,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.189969410392064e+17,
+  "total_flos": 1.4279632924704768e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null