Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75410168de9c9bc220b54027abcffb1122fbd9afb0f31cdb49c905ab20aadb19
+oid sha256:d15cf64ecec0a56de9c6510b1d7afea5016131d9594db248bb116cb482893b41
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7012dc9d46f0f15c8164eb131494a13eaae25387fcd97b772839bbacb59cdbf8
+oid sha256:9911c34e1d05b715a51919ef9bdb30451b021909e53efaa150490585ecee6f8a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a15f8b7e107d1944aa714244b7981525070751630348b2f99259785cab9c85cb
+oid sha256:87951bd1d28cfc789427636c05788fc21db0e7e40be21589b4278413c44c66bd
 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": 0.033482142857142856,
+  "epoch": 0.04017857142857143,
   "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": 13.985,
       "eval_steps_per_second": 1.748,
       "step": 45
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 6.039599418640137,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 4.1585,
+      "step": 48
+    },
+    {
+      "epoch": 0.03794642857142857,
+      "grad_norm": 5.91121244430542,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 4.1427,
+      "step": 51
+    },
+    {
+      "epoch": 0.04017857142857143,
+      "grad_norm": 5.7630181312561035,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 3.8608,
+      "step": 54
+    },
+    {
+      "epoch": 0.04017857142857143,
+      "eval_loss": 4.20692253112793,
+      "eval_runtime": 162.0191,
+      "eval_samples_per_second": 13.974,
+      "eval_steps_per_second": 1.747,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.676985552044032e+16,
+  "total_flos": 8.012382662452838e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null