Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:325555fe95a544a4fd4587e3142f16ea17a6055dee5032f9bb138e4f52ad6d51
+oid sha256:71a3bcec245e9bacb9705acb8464005f9b167684fd5abf38f960eedf0fd1a515
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ce7b0b319fa389582f8725e47b94dd285f86693e6e7c75d88f61263102e8f7
+oid sha256:79ae6083463b577b2086f470d99f3defc1a873def7ff86ed61317c3f0453b937
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f62191465ca13746dac1bcf041d5664f2ed639d8f8ca9d2cd2c4c72ca0db69e
+oid sha256:f4e4977166362ff4825c86c829e9e5a8ae75df9ab05f42e119bdb7c534fc843e
 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": 0.010407857932739219,
+  "epoch": 0.01170884017433162,
   "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": 9.007,
       "eval_steps_per_second": 1.127,
       "step": 40
+    },
+    {
+      "epoch": 0.01092825082937618,
+      "grad_norm": 1.7873488664627075,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.1959,
+      "step": 42
+    },
+    {
+      "epoch": 0.01170884017433162,
+      "grad_norm": 1.3194762468338013,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0076,
+      "step": 45
+    },
+    {
+      "epoch": 0.01170884017433162,
+      "eval_loss": 0.3401791751384735,
+      "eval_runtime": 718.6993,
+      "eval_samples_per_second": 9.007,
+      "eval_steps_per_second": 1.127,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0368525268942848e+17,
+  "total_flos": 1.1656540830302208e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null