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:a8c2bca795ac8c0d734b7573c887b80baef78ddddfa3ba097c8b5c2372b8cec8
+oid sha256:53e157e15b8509ef720250a26879a9e2f0b1c46a61c032813c9a4948181ae559
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae60fec0a57435e5dda6f18274bf9bb815cb30efdbac7d0c18a2619146741710
+oid sha256:d0e5739e5fcb9ec77d84640de85ce48ad7d1543f8aae60150937c10504a9fd61
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f13021e7482341471484d4aad9781f09fe01c38a6c563464f0daec79b33a22
+oid sha256:ebb686c169d359644c0666597924084ed694573d8d7e24d2e989ad01f93f2734
 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": 0.008920912677989364,
+  "epoch": 0.0114370675358838,
   "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": 6.0896,
       "step": 35
+    },
+    {
+      "epoch": 0.00914965402870704,
+      "grad_norm": 8.473782539367676,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.616,
+      "step": 40
+    },
+    {
+      "epoch": 0.00914965402870704,
+      "eval_loss": 1.759209394454956,
+      "eval_runtime": 219.2241,
+      "eval_samples_per_second": 8.398,
+      "eval_steps_per_second": 4.201,
+      "step": 40
+    },
+    {
+      "epoch": 0.010293360782295419,
+      "grad_norm": 9.23664665222168,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.9458,
+      "step": 45
+    },
+    {
+      "epoch": 0.0114370675358838,
+      "grad_norm": 7.948398590087891,
+      "learning_rate": 0.0,
+      "loss": 7.2517,
+      "step": 50
+    },
+    {
+      "epoch": 0.0114370675358838,
+      "eval_loss": 1.743358850479126,
+      "eval_runtime": 219.1872,
+      "eval_samples_per_second": 8.399,
+      "eval_steps_per_second": 4.202,
+      "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": 1.32497327259648e+16,
+  "total_flos": 1.698683682816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null