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:ab7f542898d6f7e1164d46f6a96ab03ce263b9319f0aeb341d0480e3302d9a85
+oid sha256:e06516458bb5cc1cefb675e7284a758b5c2a16011f9e85916dfcfe2b5fa2f7f8
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd61025408e557acce6485e26fa7379f2ee69f9889123cf50208f062a926a4d5
+oid sha256:4c3feb0defcc442d81eb4ffab5303fefb5db4f514fcba727fdfd34d87b3cf50e
 size 61392180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed0751afc86b51a475068fd3d064802215f73338970ca437e2aa986730e3cda
+oid sha256:187ff4a0a247f233680554d821ca2a92a82b8895ad2235a345f226002ac53b72
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10233086981239341,
+  "epoch": 0.12279704377487209,
   "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": 20.632,
       "eval_steps_per_second": 2.589,
       "step": 45
+    },
+    {
+      "epoch": 0.10915292779988629,
+      "grad_norm": 0.4994668662548065,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.5962,
+      "step": 48
+    },
+    {
+      "epoch": 0.11597498578737919,
+      "grad_norm": 0.4232550859451294,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.7046,
+      "step": 51
+    },
+    {
+      "epoch": 0.12279704377487209,
+      "grad_norm": 0.5421936511993408,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.7675,
+      "step": 54
+    },
+    {
+      "epoch": 0.12279704377487209,
+      "eval_loss": 1.6868067979812622,
+      "eval_runtime": 35.9161,
+      "eval_samples_per_second": 20.631,
+      "eval_steps_per_second": 2.589,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7019967018827776e+16,
+  "total_flos": 3.212067507850445e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null