Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac636223cdcd3ab27a9c4560861e021fdaf6b7c116171efc10d9c8e93df67ae
+oid sha256:c91e72a3e318d4dd79ad1a3f60541d41c8fc9c519c11d05121e4b9d511b7b9a5
 size 891333320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddd3f3d13565885d23c59ff5b5f5873f5c5586042ae31336783737f09c801ed2
+oid sha256:133d7b7a67f93577f1b2433ec8874d898e8b054406f84e33299d60a60da77663
 size 452984596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be55bbd185d3b184a97f2de34a3f525f05f10c2c723bb4e6abdc315e689b1502
+oid sha256:b0ea16f6cbc3482bc244d205dbea74f7ab7b04b6705a0543758bcce72fbf13ce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004427594985748679,
+  "epoch": 0.0049810443589672635,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 6.638,
       "eval_steps_per_second": 0.83,
       "step": 40
+    },
+    {
+      "epoch": 0.004648974735036113,
+      "grad_norm": 3.1589062213897705,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3215,
+      "step": 42
+    },
+    {
+      "epoch": 0.0049810443589672635,
+      "grad_norm": 7.741284370422363,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2969,
+      "step": 45
+    },
+    {
+      "epoch": 0.0049810443589672635,
+      "eval_loss": 0.3100440800189972,
+      "eval_runtime": 2289.1555,
+      "eval_samples_per_second": 6.647,
+      "eval_steps_per_second": 0.831,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.10249059024896e+17,
+  "total_flos": 1.24030191403008e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null