Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:271707a1a580993b8452e97ef49a13555c54acd32a96cd3fb082c624d074cea0
+oid sha256:1a215b362fcec3857813715f0b7338cc130498fd0563f4fe15f01a0d4d951b02
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06673f0855936211bcf269b625ce489080f3d2fc7efa26a334f1e055a7f9bad2
+oid sha256:a7bc9be6c5c4b5361356ba4acc4849bfc6211e2fb259e9cd229797d828983726
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b07aa35a7eb737575574b00d5982b79fc48d8b4e9034418643b299a029c8f74d
+oid sha256:664ba616c7ff338d257bbb3bbd4de970c055847396dcb34edd570dd2757bef64
 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": 0.014088322947710648,
+  "epoch": 0.018061952497064934,
   "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": 1.4312,
       "step": 35
+    },
+    {
+      "epoch": 0.014449561997651947,
+      "grad_norm": 1.2177129983901978,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3246,
+      "step": 40
+    },
+    {
+      "epoch": 0.014449561997651947,
+      "eval_loss": 1.3524723052978516,
+      "eval_runtime": 74.708,
+      "eval_samples_per_second": 15.607,
+      "eval_steps_per_second": 7.804,
+      "step": 40
+    },
+    {
+      "epoch": 0.01625575724735844,
+      "grad_norm": 0.9966343641281128,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3325,
+      "step": 45
+    },
+    {
+      "epoch": 0.018061952497064934,
+      "grad_norm": 1.0290477275848389,
+      "learning_rate": 0.0,
+      "loss": 1.3277,
+      "step": 50
+    },
+    {
+      "epoch": 0.018061952497064934,
+      "eval_loss": 1.3431111574172974,
+      "eval_runtime": 74.7647,
+      "eval_samples_per_second": 15.596,
+      "eval_steps_per_second": 7.798,
+      "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": 3548714002022400.0,
+  "total_flos": 4552143478456320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null