Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6025d2368312752b86b7edf0c0bc416c221cc07f2a3f3246f0089144bc31ee01
+oid sha256:49f30c4c505b6bc2fa9b9c9032c3de34fe90603c1c788bce24bdba7d93c78ada
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6f655d8ffc9cd307536c7c01014c1a6d177aaff88710c2cdb1a2de1ab3673a0
+oid sha256:7dc0d66eb2dbcef0d88c488dea0aa5d0ab96543623260fb168804101deab5325
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69363b571608ea891a243316f5833df4d3c3af272068a043b9b978810851ad3a
+oid sha256:d78fb67a36a8ef685bd85c725b53ceb6959fc211f83739a3ee60241ff56c81f4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23639774859287055,
+  "epoch": 0.2701688555347092,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 13.662,
       "eval_steps_per_second": 3.461,
       "step": 63
+    },
+    {
+      "epoch": 0.24765478424015008,
+      "grad_norm": 0.1131921261548996,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0062,
+      "step": 66
+    },
+    {
+      "epoch": 0.2589118198874296,
+      "grad_norm": 0.6602727770805359,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.007,
+      "step": 69
+    },
+    {
+      "epoch": 0.2701688555347092,
+      "grad_norm": 0.03234098479151726,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0012,
+      "step": 72
+    },
+    {
+      "epoch": 0.2701688555347092,
+      "eval_loss": 0.004046585410833359,
+      "eval_runtime": 16.4739,
+      "eval_samples_per_second": 13.658,
+      "eval_steps_per_second": 3.46,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.478949358829568e+16,
+  "total_flos": 5.118799267233792e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null