Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0c100f091b8f8643c3b3555eed1017f8a0b4dd899d7afc7b5c7916ff5c3435
+oid sha256:bef471f9fc541d1c1d61bc7c067e6e28d77e6571f6f6c32c7aa00fc522d1dd9f
 size 2185308216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0ef73754c34f04dd01b58b0ad807ca06d00b47dd9b0e6771cb94424ad5dea8
+oid sha256:97de93867d36ffdf76b646297c0f0cd640894996caa8091d9ca8bd9a00c0c74e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a1f3155b537276c540b4b359f6f1735227a9b243af29aedc24435ca462f4e6
+oid sha256:185c6777879539a9f22be57c224b405abde7e14139e163784ea7475d86392d87
 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": 0.017651052274270197,
+  "epoch": 0.022629554197782304,
   "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": 0.3407,
       "step": 35
+    },
+    {
+      "epoch": 0.018103643358225844,
+      "grad_norm": 0.36751681566238403,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2876,
+      "step": 40
+    },
+    {
+      "epoch": 0.018103643358225844,
+      "eval_loss": 0.32187148928642273,
+      "eval_runtime": 121.8496,
+      "eval_samples_per_second": 7.641,
+      "eval_steps_per_second": 3.824,
+      "step": 40
+    },
+    {
+      "epoch": 0.020366598778004074,
+      "grad_norm": 0.35453692078590393,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3371,
+      "step": 45
+    },
+    {
+      "epoch": 0.022629554197782304,
+      "grad_norm": 0.3624661862850189,
+      "learning_rate": 0.0,
+      "loss": 0.3531,
+      "step": 50
+    },
+    {
+      "epoch": 0.022629554197782304,
+      "eval_loss": 0.32060080766677856,
+      "eval_runtime": 121.6604,
+      "eval_samples_per_second": 7.652,
+      "eval_steps_per_second": 3.83,
+      "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": 1.4149174199058432e+16,
+  "total_flos": 1.8171978628202496e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null