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:c0ceb591b37791fc71da6e30e0871bea5a950ef58d9bf395ccb7b3290cdd4890
+oid sha256:ede3fb0f48741a1ac6d036c6c7305365fd5b8489ff230b8933a24a8c03c63d56
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005f5949b5dd7dde9c854f984861b7c2bd7f037bb355b81cb386a0b4f08768ad
+oid sha256:ec2661c09981f2874d6827e96d18c161b945a3d914865a9aeb45fb8ccd14dbe6
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d52990953d1b8a81a00b7cecfd9c211b1ca6db6b881889b76e3a32894320cdb
+oid sha256:529c9e51cf346c9538de8a198d0e350de38ac30f5061dd3c6b0f0716ac464501
 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": 0.01800761860787256,
+  "epoch": 0.02308669052291354,
   "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": 1.2822,
       "step": 35
+    },
+    {
+      "epoch": 0.018469352418330833,
+      "grad_norm": 4.96974515914917,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0735,
+      "step": 40
+    },
+    {
+      "epoch": 0.018469352418330833,
+      "eval_loss": 1.0105435848236084,
+      "eval_runtime": 54.1627,
+      "eval_samples_per_second": 16.838,
+      "eval_steps_per_second": 8.419,
+      "step": 40
+    },
+    {
+      "epoch": 0.020778021470622188,
+      "grad_norm": 7.320389270782471,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5978,
+      "step": 45
+    },
+    {
+      "epoch": 0.02308669052291354,
+      "grad_norm": 6.576738357543945,
+      "learning_rate": 0.0,
+      "loss": 1.0794,
+      "step": 50
+    },
+    {
+      "epoch": 0.02308669052291354,
+      "eval_loss": 0.9964532256126404,
+      "eval_runtime": 53.3667,
+      "eval_samples_per_second": 17.089,
+      "eval_steps_per_second": 8.545,
+      "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": 6352063155929088.0,
+  "total_flos": 8143670712729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null