Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380c37a83db3d53139b4eb8bea3fcefce1869b381a163f09533fd791d5b9751e
+oid sha256:63935c426e388b54ec93fa786397c139d077a72e2583134e85f5d84edefc035c
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d89849a3615b4005de7ad7be7bfa0d376da8451f8422b7c7871275916d5e3f
+oid sha256:b3ec5d39df23e3d976ade897caf93ecc6adfae6a282c9ca49c6eb2a1b66b77c1
 size 71718

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": 0.002662297767765718,
+  "epoch": 0.003413202266366305,
   "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": 41.4861,
       "step": 35
+    },
+    {
+      "epoch": 0.0027305618130930437,
+      "grad_norm": 0.4662351608276367,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 41.4965,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027305618130930437,
+      "eval_loss": 10.374078750610352,
+      "eval_runtime": 37.1565,
+      "eval_samples_per_second": 166.001,
+      "eval_steps_per_second": 83.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0030718820397296746,
+      "grad_norm": 0.47756487131118774,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 41.5004,
+      "step": 45
+    },
+    {
+      "epoch": 0.003413202266366305,
+      "grad_norm": 0.49399423599243164,
+      "learning_rate": 0.0,
+      "loss": 41.4887,
+      "step": 50
+    },
+    {
+      "epoch": 0.003413202266366305,
+      "eval_loss": 10.373979568481445,
+      "eval_runtime": 37.1596,
+      "eval_samples_per_second": 165.987,
+      "eval_steps_per_second": 82.993,
+      "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": 1385900015616.0,
+  "total_flos": 1751623630848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null