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:a6c3fd9f0fdff0bcfb727eff940512956ed7ac9065eefd424981736d98c077a1
+oid sha256:f6b56923beec83daf4b026ee2133d040a519081a62e227296483cd8df272210f
 size 891333320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df26dd98ff29335a5d71a1bfc954981ed3932cb4b377aa7b171e7fbb2223bc9b
+oid sha256:4f37a9a57c9c4be5cff76268cd1a529e45c82fcd8a86b9154525a2af946d9382
 size 452984596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36722ed5f777da61ae6a7eaf2e2d59932bbb3d9c7b68693751e54837eefbc9ca
+oid sha256:f07634e13278ce60c6592f28cbbf6ad4cbc5a47fd1171ae4cc47ef803f82b3e4
 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": 0.0577825929938606,
+  "epoch": 0.06500541711809317,
   "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": 2.569,
       "eval_steps_per_second": 0.322,
       "step": 40
+    },
+    {
+      "epoch": 0.06067172264355363,
+      "grad_norm": 1.0478241443634033,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.003,
+      "step": 42
+    },
+    {
+      "epoch": 0.06500541711809317,
+      "grad_norm": 0.04418126866221428,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.001,
+      "step": 45
+    },
+    {
+      "epoch": 0.06500541711809317,
+      "eval_loss": 0.0003434412938077003,
+      "eval_runtime": 454.0191,
+      "eval_samples_per_second": 2.568,
+      "eval_steps_per_second": 0.322,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.20498118049792e+17,
+  "total_flos": 2.48060382806016e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null