Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9faccc82f73b21201d719ccb0d3d9fe598bcf7e8e4d94a01926812f2004e304a
+oid sha256:6a45fac63b6b39cd567e50ef531e128e881acc85c7b130901b427f77b4bff905
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fed1de8a6d94324a1f1971916c11e424031f2f8cf87c91cea7551f4ff248b935
+oid sha256:d01de3f458588c338972e0e1927b636495f2269cac787269622509153c44fe19
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253104289d38b5d339446cc893bbdca245a542c491e999866182dd34b3ba90db
+oid sha256:6793a29c78165d9473679468fc5aa85fc2373c34ac5d6165d73c36d408798005
 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": 0.03877703206562267,
+  "epoch": 0.049714143673875215,
   "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": 1.3827,
       "step": 35
+    },
+    {
+      "epoch": 0.039771314939100175,
+      "grad_norm": 0.3954694867134094,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3236,
+      "step": 40
+    },
+    {
+      "epoch": 0.039771314939100175,
+      "eval_loss": 1.3565930128097534,
+      "eval_runtime": 41.8602,
+      "eval_samples_per_second": 10.129,
+      "eval_steps_per_second": 5.064,
+      "step": 40
+    },
+    {
+      "epoch": 0.0447427293064877,
+      "grad_norm": 0.3389461934566498,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1909,
+      "step": 45
+    },
+    {
+      "epoch": 0.049714143673875215,
+      "grad_norm": 0.37343329191207886,
+      "learning_rate": 0.0,
+      "loss": 1.3179,
+      "step": 50
+    },
+    {
+      "epoch": 0.049714143673875215,
+      "eval_loss": 1.3546466827392578,
+      "eval_runtime": 41.7489,
+      "eval_samples_per_second": 10.156,
+      "eval_steps_per_second": 5.078,
+      "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": 1.1543228687843328e+16,
+  "total_flos": 1.4706319822946304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null