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:d4ac61e817b307e5e1bf31615ee0b270bd43b6771eeb539615022161899528b0
+oid sha256:fe7e110df95347e20515e87d1a5bfb318f75e8d8db3a89dc301649c0069b8a3b
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26adc8ca14273664cdfecb2f832e5098b43f7c7278342cc3eddf09299409c8aa
+oid sha256:7de681a14d7a3fa3474e3602d4702b6a91142507a0f7be890a07e0a7a3583924
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c3e567c74affae7478911fb166aed9b97f670988a0accdc6e7382bc1b315cf
+oid sha256:19c3a950b1db5e5a53ee1807fed513e1459650c81b28057a7dd9e7f6eb2c4dc2
 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": 0.5182724252491694,
+  "epoch": 0.6644518272425249,
   "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": 2.2405,
       "step": 35
+    },
+    {
+      "epoch": 0.53156146179402,
+      "grad_norm": 2.478245735168457,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0135,
+      "step": 40
+    },
+    {
+      "epoch": 0.53156146179402,
+      "eval_loss": 2.1549835205078125,
+      "eval_runtime": 1.181,
+      "eval_samples_per_second": 27.095,
+      "eval_steps_per_second": 13.548,
+      "step": 40
+    },
+    {
+      "epoch": 0.5980066445182725,
+      "grad_norm": 2.6744627952575684,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7333,
+      "step": 45
+    },
+    {
+      "epoch": 0.6644518272425249,
+      "grad_norm": 2.8500657081604004,
+      "learning_rate": 0.0,
+      "loss": 1.8794,
+      "step": 50
+    },
+    {
+      "epoch": 0.6644518272425249,
+      "eval_loss": 2.1422481536865234,
+      "eval_runtime": 1.1288,
+      "eval_samples_per_second": 28.349,
+      "eval_steps_per_second": 14.175,
+      "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": 299222830153728.0,
+  "total_flos": 383619013017600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null