Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:643409aef7ae8fdc7c0ecb48aae95dd12dcf9f22127e36af50a3fa2fa5ccbb76
+oid sha256:fe9affef2ead2317b04b248df9698ff35979541bc6443e05fd669f0d5dcf19ef
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c7ee695ce87265309526696713e762db59cc8cea91b15464759e3201bd9ecb
+oid sha256:c0986b3cbb9ff4c0977374c9b9dea9f6e25791b01e8e1a4e1cb0602e692e31b8
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f8b59091c8d425e240482287455f7be57abb004555866878d0982c21a39257f
+oid sha256:c943b16d91ca8b283d2380afa45ed4c6e2bd02915f08279545f83c26cafdd58d
 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": 0.0031754432389521038,
+  "epoch": 0.0040710810755796205,
   "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": 6.3411,
       "step": 35
+    },
+    {
+      "epoch": 0.0032568648604636963,
+      "grad_norm": 5.8388895988464355,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.4617,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032568648604636963,
+      "eval_loss": 1.772756576538086,
+      "eval_runtime": 659.8056,
+      "eval_samples_per_second": 7.839,
+      "eval_steps_per_second": 3.919,
+      "step": 40
+    },
+    {
+      "epoch": 0.003663972968021658,
+      "grad_norm": 5.17460823059082,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.0335,
+      "step": 45
+    },
+    {
+      "epoch": 0.0040710810755796205,
+      "grad_norm": 6.099168300628662,
+      "learning_rate": 0.0,
+      "loss": 7.0876,
+      "step": 50
+    },
+    {
+      "epoch": 0.0040710810755796205,
+      "eval_loss": 1.7677820920944214,
+      "eval_runtime": 659.1629,
+      "eval_samples_per_second": 7.846,
+      "eval_steps_per_second": 3.923,
+      "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": 6609264319660032.0,
+  "total_flos": 8536966412894208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null