Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eae2c909c0b188f49a6174da336a26b8164b53795806f0dc85846f5f04ecdd7
+oid sha256:b97da3dee8f926f10a0755f2a580e1147fb1e5e97d9db0c71b8f9b39fecfca6d
 size 3029024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b56b378748cad9a1f8656a0f8649e37e5290ef6a0fa18f2936ef649581a1a35d
+oid sha256:820e02faed666f6f41e40a8b97b2fff9be920ddef4250d5fc5dd84ad419c3136
 size 1663290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784084ca83b073e0e7a3fe1d78d5b6638cd532c397fbb70771b4126ed8891454
+oid sha256:d0897a16a47e7eef56851f281f3b9135740b6fdb7cb031a3f0df1601e9c11710
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.39886039886039887,
+  "epoch": 0.45584045584045585,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 117.256,
       "eval_steps_per_second": 15.053,
       "step": 35
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 4.275054454803467,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.4953,
+      "step": 36
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 3.2638161182403564,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.3914,
+      "step": 39
+    },
+    {
+      "epoch": 0.45584045584045585,
+      "eval_loss": 2.357823610305786,
+      "eval_runtime": 1.262,
+      "eval_samples_per_second": 117.27,
+      "eval_steps_per_second": 15.055,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 29271989944320.0,
+  "total_flos": 33033195356160.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null