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:b68874c92f53bf4d5e384591492bd14834f2fe84e6d8574b20848a0f5bb058ab
+oid sha256:eb0fe1e72e7a9362ada063aed49ccaa00743785c891c0b1725536415b502b21c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e127110806dcb9e0695c168108a2897eeda7c56875d568a36ad75714e123f2f
+oid sha256:e5203332012b272597190c161af4ce5530e3ad58b3db27181daf91556943dea9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38014aaf5e7ca31db5a114a6e30aaa55681efe9da7ef87ac89cdcd5b7216e0fe
+oid sha256:2ad10b0445c4e5df218bf881d92cb452dbecc738c393fa525aa6d7f4fa3b47d1
 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": 0.0018656716417910447,
+  "epoch": 0.002391886720244929,
   "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": 1.2995,
       "step": 35
+    },
+    {
+      "epoch": 0.0019135093761959434,
+      "grad_norm": 4.5769829750061035,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5716,
+      "step": 40
+    },
+    {
+      "epoch": 0.0019135093761959434,
+      "eval_loss": 1.482947587966919,
+      "eval_runtime": 929.9055,
+      "eval_samples_per_second": 9.465,
+      "eval_steps_per_second": 4.733,
+      "step": 40
+    },
+    {
+      "epoch": 0.002152698048220436,
+      "grad_norm": 3.27357816696167,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7455,
+      "step": 45
+    },
+    {
+      "epoch": 0.002391886720244929,
+      "grad_norm": 4.553426265716553,
+      "learning_rate": 0.0,
+      "loss": 1.5679,
+      "step": 50
+    },
+    {
+      "epoch": 0.002391886720244929,
+      "eval_loss": 1.4763922691345215,
+      "eval_runtime": 928.2878,
+      "eval_samples_per_second": 9.482,
+      "eval_steps_per_second": 4.741,
+      "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": 1.2114645825355776e+16,
+  "total_flos": 1.5628817896833024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null