Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6814fd73c806a7b6d0f11e1c854e97526e2ff803abd47b8f161d19132b374a
+oid sha256:ba234e4c910c52320f65ff75ce9c73ab2a93e7f7e19aad997db5e3cbdb07dc49
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1f3b210ea2a055f8ef8d57b09f3267c3505fe43787f532e0ec69de05649300
+oid sha256:8f7f9a62f2eda1e52acf5261893a9fa8541678dbfcec7b815c27b5bd92efd04a
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11babdea246a4e24996953deb155282010c386374754f4f502873f43203aed39
+oid sha256:4f4738ee211f4f50b9ad38da261c4a2ad61f02566b527c754ac2d36d925fa919
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0462085308056872,
+  "epoch": 0.05924170616113744,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 20.313,
       "eval_steps_per_second": 2.54,
       "step": 30
+    },
+    {
+      "epoch": 0.04739336492890995,
+      "grad_norm": 0.2652459740638733,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.1065,
+      "step": 40
+    },
+    {
+      "epoch": 0.04739336492890995,
+      "eval_loss": 2.1241848468780518,
+      "eval_runtime": 279.8581,
+      "eval_samples_per_second": 20.317,
+      "eval_steps_per_second": 2.541,
+      "step": 40
+    },
+    {
+      "epoch": 0.05924170616113744,
+      "grad_norm": 0.28252074122428894,
+      "learning_rate": 0.0,
+      "loss": 2.127,
+      "step": 50
+    },
+    {
+      "epoch": 0.05924170616113744,
+      "eval_loss": 2.1221628189086914,
+      "eval_runtime": 278.9085,
+      "eval_samples_per_second": 20.387,
+      "eval_steps_per_second": 2.549,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0163395270331597e+17,
+  "total_flos": 1.302999393632256e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null