Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85942fb63a0c7aa5bc27281bb304db8956f9985e2c52f7ff54d57886d037f73a
+oid sha256:e25fc4a1cf95283a2d2d49968e6830b00a161b0240ceccf0070bce3710ffb573
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:934572e373881eb1e1d16fd3f78781ee070d9a075d890834ec64865c3c9c7201
+oid sha256:b334733038de319c1349da445cb4fdfba98c5e619a149236d0201382193e47a1
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36abdc6c73965de75759448e0157f0ee2ec4bf7614b46a0c0631a26ac44221cf
+oid sha256:8ea319b876fad14d48ddcbda44f3eceb645df0c7a5351456c260914114c0ce1b
 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": 0.010146341463414634,
+  "epoch": 0.013008130081300813,
   "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": 0.4895,
       "step": 35
+    },
+    {
+      "epoch": 0.01040650406504065,
+      "grad_norm": 0.9892436265945435,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5728,
+      "step": 40
+    },
+    {
+      "epoch": 0.01040650406504065,
+      "eval_loss": 0.4556264877319336,
+      "eval_runtime": 140.766,
+      "eval_samples_per_second": 11.501,
+      "eval_steps_per_second": 5.754,
+      "step": 40
+    },
+    {
+      "epoch": 0.011707317073170732,
+      "grad_norm": 1.071173906326294,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.527,
+      "step": 45
+    },
+    {
+      "epoch": 0.013008130081300813,
+      "grad_norm": 1.2692747116088867,
+      "learning_rate": 0.0,
+      "loss": 0.4899,
+      "step": 50
+    },
+    {
+      "epoch": 0.013008130081300813,
+      "eval_loss": 0.4491496980190277,
+      "eval_runtime": 141.0117,
+      "eval_samples_per_second": 11.481,
+      "eval_steps_per_second": 5.744,
+      "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": 9540932352344064.0,
+  "total_flos": 1.241628182839296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null