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:aec266f79f6d24d26e525a728eecdb9f8227a708607026bd0cd6093d38be3005
+oid sha256:c70ee7372980138b4fbddf3f73a8be52d53bce9c95561b35fb8114d8ac7f9bea
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5d495a04ebfbfeaed430625dca647bce67b8d2c27be8c2201b3026d7d56586
+oid sha256:136363dc35ba288cd37a2f3ed1e2b02a41a4f1df96fbfe7e87459936b2be9e06
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f73a7f94cc8d884e27d6e5e3c1a8c08d2b909c93f19f6d763ca72e74ecec766
+oid sha256:9af62c5ca99473361bcc0ab1f72267b3a2b8d1de6c846b8fb3da04dbe9e5f4aa
 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": 0.0016957627671369871,
+  "epoch": 0.002174054829662804,
   "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": 1.2185,
       "step": 35
+    },
+    {
+      "epoch": 0.0017392438637302433,
+      "grad_norm": 0.9062265157699585,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1935,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017392438637302433,
+      "eval_loss": 1.1781949996948242,
+      "eval_runtime": 783.3477,
+      "eval_samples_per_second": 12.362,
+      "eval_steps_per_second": 6.181,
+      "step": 40
+    },
+    {
+      "epoch": 0.001956649346696524,
+      "grad_norm": 0.7248935103416443,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.134,
+      "step": 45
+    },
+    {
+      "epoch": 0.002174054829662804,
+      "grad_norm": 0.8981196880340576,
+      "learning_rate": 0.0,
+      "loss": 1.1538,
+      "step": 50
+    },
+    {
+      "epoch": 0.002174054829662804,
+      "eval_loss": 1.1734018325805664,
+      "eval_runtime": 782.847,
+      "eval_samples_per_second": 12.37,
+      "eval_steps_per_second": 6.185,
+      "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": 6695894221062144.0,
+  "total_flos": 8626612186644480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null