Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6813fdbe8bdc8489de4b64f15ce24261dd873e6b848088555a29a119ace00a54
+oid sha256:7008ff38ae46be7c3a5e62fe27ae4709fb6866384ed10bbf219f94cd12cad737
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5905f32d61f5500b36cdf11068219588a57abff5c8fb51ea2dbb46eaacce0605
+oid sha256:38ce80a2152eb639310dffd7b92e4a75c37124ef352c410a6114d1004a63f222
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a42c33445a7e2c9138790db707c29bb8500bafdae7c74040b6354c5f251439
+oid sha256:fed120440b6875f99cd3aa80cc375b968f1df799f3d3c11c1bef77e318695614
 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": 0.1080706615864219,
+  "epoch": 0.13855213023900242,
   "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": 41.085,
       "eval_steps_per_second": 5.138,
       "step": 30
+    },
+    {
+      "epoch": 0.11084170419120194,
+      "grad_norm": 0.7959256768226624,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.3263,
+      "step": 40
+    },
+    {
+      "epoch": 0.11084170419120194,
+      "eval_loss": 2.277695655822754,
+      "eval_runtime": 59.3343,
+      "eval_samples_per_second": 40.971,
+      "eval_steps_per_second": 5.124,
+      "step": 40
+    },
+    {
+      "epoch": 0.13855213023900242,
+      "grad_norm": 0.8115575909614563,
+      "learning_rate": 0.0,
+      "loss": 2.2721,
+      "step": 50
+    },
+    {
+      "epoch": 0.13855213023900242,
+      "eval_loss": 2.2608070373535156,
+      "eval_runtime": 58.9517,
+      "eval_samples_per_second": 41.237,
+      "eval_steps_per_second": 5.157,
+      "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": 3.0209032631353344e+16,
+  "total_flos": 3.880364310056141e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null