Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:880fcf1e03761ecee16a6befa0f8986c01ef3f5dbc24261a07f4378846bd6134
+oid sha256:98d96bacd2447f02440b12d8c7ac65a4ae1c3dbdc873ec9730910a4f9d6e98aa
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83853a69c12335dedc5b8c0553a2dd7a0f362e7032d85996414939c7f3c98d9b
+oid sha256:4b2fd18fc8ed10ef9df58e360b333319014076e16a26a7c33ed533780e7a7002
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbba3e37f3da5eebd20241eda5b6317a6fa8037aef8c40511f6d82de78527891
+oid sha256:fada5e344878f23dd097d459027d43e07f5d3ae885d86019aeb3993928c4dea4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017729287419024888,
+  "epoch": 0.022729855665416524,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 8.2646,
       "step": 35
+    },
+    {
+      "epoch": 0.01818388453233322,
+      "grad_norm": 126.23807525634766,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.3377,
+      "step": 40
+    },
+    {
+      "epoch": 0.01818388453233322,
+      "eval_loss": 2.0046887397766113,
+      "eval_runtime": 16.597,
+      "eval_samples_per_second": 55.853,
+      "eval_steps_per_second": 27.957,
+      "step": 40
+    },
+    {
+      "epoch": 0.020456870098874872,
+      "grad_norm": 74.23300170898438,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.1037,
+      "step": 45
+    },
+    {
+      "epoch": 0.022729855665416524,
+      "grad_norm": 93.17680358886719,
+      "learning_rate": 0.0,
+      "loss": 8.0593,
+      "step": 50
+    },
+    {
+      "epoch": 0.022729855665416524,
+      "eval_loss": 1.976387858390808,
+      "eval_runtime": 16.7276,
+      "eval_samples_per_second": 55.418,
+      "eval_steps_per_second": 27.739,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 342141406543872.0,
+  "total_flos": 438642828902400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null