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:dedc4283d74b96d3365730aade2d5ce973d88a3f30dbcfff941cbb89a7655559
+oid sha256:1988a1db74d5c9129b157c19b51ea7207ba60c2aebaed3965a9450c632ddd421
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3dd7fe23ff03c3e30af5c1cad2f92251d3a0191178e1d707204085e9c08e67
+oid sha256:b252f5b095fd0053ada5a06757aef7478edd59ef0bd5dfa621de7ede148772e7
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c0b0bf7901f8440d57c140f37d42ec44e25b28f62a126cb668b5c02dd5da3a
+oid sha256:4ad92fd4b5f7e6a6a5f26004088019a02ea35ba88f09d7fe4ea750d8038814f9
 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": 0.32142857142857145,
+  "epoch": 0.3673469387755102,
   "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": 596.042,
       "eval_steps_per_second": 151.72,
       "step": 63
+    },
+    {
+      "epoch": 0.336734693877551,
+      "grad_norm": 0.21916939318180084,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 6.829,
+      "step": 66
+    },
+    {
+      "epoch": 0.3520408163265306,
+      "grad_norm": 0.23701028525829315,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 6.8313,
+      "step": 69
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 0.18295414745807648,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 6.8278,
+      "step": 72
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "eval_loss": 6.82876443862915,
+      "eval_runtime": 0.2784,
+      "eval_samples_per_second": 592.608,
+      "eval_steps_per_second": 150.846,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 605510664192.0,
+  "total_flos": 692012187648.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null