Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f1eb1634c8998654c9504660f0b78cc19472725d701a770e06ddb76f43c995
+oid sha256:42b656b7b34de90d5123e157a4899a98f13a899c7db858145f3d76df7cc8eb08
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd5df7a564746ba80f53b6d2fb9091349408b8036596280ec3cb851e2eea66d
+oid sha256:e02edeac2fb9f069086187b74a4d3af3da30a2b8c32a2d2caa9b1add2ae9dc80
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8a57b16105d89a92c6b60131b22466981bed9bff249764f2bc8f5f737ce159
+oid sha256:7f20d1ad162bf64380ab42603ff091f581ebe7690a65b8cdc258392817bc87ec
 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": 0.0017047689819469337,
+  "epoch": 0.0021856012589063253,
   "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": 0.7107,
       "step": 35
+    },
+    {
+      "epoch": 0.0017484810071250602,
+      "grad_norm": 0.746074914932251,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6164,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017484810071250602,
+      "eval_loss": 0.6708393096923828,
+      "eval_runtime": 640.1819,
+      "eval_samples_per_second": 15.047,
+      "eval_steps_per_second": 7.524,
+      "step": 40
+    },
+    {
+      "epoch": 0.0019670411330156927,
+      "grad_norm": 0.7383710145950317,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6593,
+      "step": 45
+    },
+    {
+      "epoch": 0.0021856012589063253,
+      "grad_norm": 0.6844217777252197,
+      "learning_rate": 0.0,
+      "loss": 0.7104,
+      "step": 50
+    },
+    {
+      "epoch": 0.0021856012589063253,
+      "eval_loss": 0.6683721542358398,
+      "eval_runtime": 639.7051,
+      "eval_samples_per_second": 15.059,
+      "eval_steps_per_second": 7.53,
+      "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": 2913066951376896.0,
+  "total_flos": 3725725113778176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null