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:f05f2b717b1c242ca9586e79af4580630c4b364b3eed9fbd8822aca84fa255ef
+oid sha256:e0fb93711bb6bec5348ac3691d30038e21bddf897744867c885c805ec2c1f44f
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f87b6d6e0524b53da6365ed0626aa484324722ce834fc4d60622d15609e1d7
+oid sha256:969e7def6f9b9e7ec2628d30fec4075f6016381d492eaa96a4d57252a13131ad
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a24991bea02210129036dcfcc79bc9b5f7668a5d0213c1ac7852e33cc700633
+oid sha256:37debab1143e0a2411f4fb5b4812b0936ac504e679025e39bd6d674a0d6a75b9
 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": 0.11370262390670553,
+  "epoch": 0.1457725947521866,
   "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": 0.3802,
       "step": 35
+    },
+    {
+      "epoch": 0.11661807580174927,
+      "grad_norm": 0.6949646472930908,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4526,
+      "step": 40
+    },
+    {
+      "epoch": 0.11661807580174927,
+      "eval_loss": 0.40451228618621826,
+      "eval_runtime": 7.7124,
+      "eval_samples_per_second": 18.801,
+      "eval_steps_per_second": 9.465,
+      "step": 40
+    },
+    {
+      "epoch": 0.13119533527696792,
+      "grad_norm": 0.4946649372577667,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4593,
+      "step": 45
+    },
+    {
+      "epoch": 0.1457725947521866,
+      "grad_norm": 0.533318042755127,
+      "learning_rate": 0.0,
+      "loss": 0.4382,
+      "step": 50
+    },
+    {
+      "epoch": 0.1457725947521866,
+      "eval_loss": 0.40053504705429077,
+      "eval_runtime": 7.7542,
+      "eval_samples_per_second": 18.7,
+      "eval_steps_per_second": 9.414,
+      "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": 3793452898713600.0,
+  "total_flos": 4870304044154880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null