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:d0a2b5a7c67fa1ae98ddd2f2513df3ebbc0d1f275df2e9444871b74113622749
+oid sha256:8e139c88617587c38d37ed8bd702d95c5ee5f3808fe8e837f21f1339143d8434
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b65c15bad5cf4f0174f17cbac5ddca8c8b29ab81ebd9f6f9e881d0dd16bb0164
+oid sha256:66dbcc6fcad8e1974656808f8d12c4fb5d74ab50faefe1b0e4d6ffc6d9a77f21
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.004579480405107882,
+  "epoch": 0.005871128724497285,
   "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": 10.3154,
       "step": 35
+    },
+    {
+      "epoch": 0.0046969029795978275,
+      "grad_norm": 0.37088799476623535,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3154,
+      "step": 40
+    },
+    {
+      "epoch": 0.0046969029795978275,
+      "eval_loss": 10.316349983215332,
+      "eval_runtime": 16.3383,
+      "eval_samples_per_second": 219.485,
+      "eval_steps_per_second": 109.742,
+      "step": 40
+    },
+    {
+      "epoch": 0.005284015852047556,
+      "grad_norm": 0.44121769070625305,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3127,
+      "step": 45
+    },
+    {
+      "epoch": 0.005871128724497285,
+      "grad_norm": 0.4111413061618805,
+      "learning_rate": 0.0,
+      "loss": 10.3136,
+      "step": 50
+    },
+    {
+      "epoch": 0.005871128724497285,
+      "eval_loss": 10.31576156616211,
+      "eval_runtime": 16.2078,
+      "eval_samples_per_second": 221.252,
+      "eval_steps_per_second": 110.626,
+      "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": 507538145280.0,
+  "total_flos": 649778135040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null