Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1c0c8768490de1b71a8d6aa62757fe5c5344376d07d3c26a87efbd57be03f8
+oid sha256:b4af45b620f40852cd13470025724772b3a2a6feee2180b0608579466e2b62f4
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04baf4a68cba8fcdb22540f701e659162cd2d6d364f7f0ffd6eb50b855f0bd4c
+oid sha256:c8ff08cbbb504fffb2b25dfa3b98cb1ee436d9950853421fc90b48dc7c348bd6
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b31f7d62b4fddb1b290b1fb584d058ae1673461decd9afda53b83ac0cd051a5
+oid sha256:e5827d7f88cc9632535abac6f5aa380cb2eccf839733d59423c25a6cdfcbef0e
 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": 0.10554803788903924,
+  "epoch": 0.13531799729364005,
   "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": 1.2409,
       "step": 35
+    },
+    {
+      "epoch": 0.10825439783491204,
+      "grad_norm": 0.5214589834213257,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2773,
+      "step": 40
+    },
+    {
+      "epoch": 0.10825439783491204,
+      "eval_loss": 1.2332532405853271,
+      "eval_runtime": 7.5664,
+      "eval_samples_per_second": 20.617,
+      "eval_steps_per_second": 10.309,
+      "step": 40
+    },
+    {
+      "epoch": 0.12178619756427606,
+      "grad_norm": 0.5683117508888245,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2716,
+      "step": 45
+    },
+    {
+      "epoch": 0.13531799729364005,
+      "grad_norm": 0.47812074422836304,
+      "learning_rate": 0.0,
+      "loss": 1.2547,
+      "step": 50
+    },
+    {
+      "epoch": 0.13531799729364005,
+      "eval_loss": 1.2298351526260376,
+      "eval_runtime": 7.5132,
+      "eval_samples_per_second": 20.763,
+      "eval_steps_per_second": 10.382,
+      "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": 4346257924423680.0,
+  "total_flos": 5432822405529600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null