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:d0656f88f14a7f6913701059545fb83645066378a3e6670d7325b4efd7385598
+oid sha256:24f0d500627bbfbefaecc3871b3eb4855b37dd529648ec2648ff44550538235b
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd71899b0b185bc6ecb1d292dcbf6cae25bd56806eb73b76d334e3aca87cf29
+oid sha256:a47b8d274b892e160a9c7aa9f177b88246bbd9c90fa50fb5f4ce8e28fbedb425
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1039e96a4ec12087edaa8ab2d18eba7c359b91687856664d415beaa872acc5
+oid sha256:19a5c3c72e60ff810542ede55f7b859d77b4dd5935294cc01a9f9bf4d605e2e8
 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": 0.0029047574713713807,
+  "epoch": 0.003724048040219719,
   "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": 11.9312,
       "step": 35
+    },
+    {
+      "epoch": 0.002979238432175775,
+      "grad_norm": 0.023682741448283195,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9328,
+      "step": 40
+    },
+    {
+      "epoch": 0.002979238432175775,
+      "eval_loss": 11.93016242980957,
+      "eval_runtime": 50.4237,
+      "eval_samples_per_second": 112.13,
+      "eval_steps_per_second": 56.065,
+      "step": 40
+    },
+    {
+      "epoch": 0.0033516432361977468,
+      "grad_norm": 0.04054044187068939,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9268,
+      "step": 45
+    },
+    {
+      "epoch": 0.003724048040219719,
+      "grad_norm": 0.02140682004392147,
+      "learning_rate": 0.0,
+      "loss": 11.9285,
+      "step": 50
+    },
+    {
+      "epoch": 0.003724048040219719,
+      "eval_loss": 11.930160522460938,
+      "eval_runtime": 49.6627,
+      "eval_samples_per_second": 113.848,
+      "eval_steps_per_second": 56.924,
+      "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": 4608294912.0,
+  "total_flos": 5908070400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null