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:dc6b654ff14e976d522e251b01091a3bbeae59f4fff69f9a5ecf3db921da8a5f
+oid sha256:5f249318ac71cdfbe5db2d0ef7ac7b3c113681e87ed2946692970516636b3ef3
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b970652f113f071dd04123a2f677a8fade3a165d164867626a49060d903474b
+oid sha256:efb3559e9f318abfde41776905000019fd8a0d3f14b00389e6376ad9b1d2a455
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5563048afcc16f4f0723f94a4657fc683031fc640e6031a09b62d44c93264f19
+oid sha256:4ca606616cd9ffbf90e56c8d6a0e4c55e159ee27b4c3b6b1f43b0b83b1100957
 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": 0.06884377758164166,
+  "epoch": 0.088261253309797,
   "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": 0.3658,
       "step": 35
+    },
+    {
+      "epoch": 0.0706090026478376,
+      "grad_norm": 8.900777816772461,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.36,
+      "step": 40
+    },
+    {
+      "epoch": 0.0706090026478376,
+      "eval_loss": 0.3891545236110687,
+      "eval_runtime": 62.9107,
+      "eval_samples_per_second": 3.799,
+      "eval_steps_per_second": 1.907,
+      "step": 40
+    },
+    {
+      "epoch": 0.0794351279788173,
+      "grad_norm": 6.1990203857421875,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.405,
+      "step": 45
+    },
+    {
+      "epoch": 0.088261253309797,
+      "grad_norm": 2.5258963108062744,
+      "learning_rate": 0.0,
+      "loss": 0.4746,
+      "step": 50
+    },
+    {
+      "epoch": 0.088261253309797,
+      "eval_loss": 0.3904491364955902,
+      "eval_runtime": 63.425,
+      "eval_samples_per_second": 3.768,
+      "eval_steps_per_second": 1.892,
+      "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": 1.490651304689664e+16,
+  "total_flos": 1.9110914162688e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null