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:d3076c9e4b22ccda1d157440309438592bd72e05f4fcb3b12d5ab6457c5abb65
+oid sha256:3c490ccbbfa41cc1869e8390116295c44cfcbd21fe9cbceb49028057ec3a7d4a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1d1a459d78a0be1cdb36430c753a112c19893ee10cfe16d8aa3e8fe1062728
+oid sha256:81e8ce55da4768ea2798993a66929e17b5190b64e98ed5ec963746b6af921aa5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a1f3155b537276c540b4b359f6f1735227a9b243af29aedc24435ca462f4e6
+oid sha256:185c6777879539a9f22be57c224b405abde7e14139e163784ea7475d86392d87
 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": 0.0016437490121700648,
+  "epoch": 0.00210737052842316,
   "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": 3.5432,
       "step": 35
+    },
+    {
+      "epoch": 0.001685896422738528,
+      "grad_norm": 3.976745843887329,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.3801,
+      "step": 40
+    },
+    {
+      "epoch": 0.001685896422738528,
+      "eval_loss": 0.8637235164642334,
+      "eval_runtime": 1152.7349,
+      "eval_samples_per_second": 8.666,
+      "eval_steps_per_second": 4.333,
+      "step": 40
+    },
+    {
+      "epoch": 0.001896633475580844,
+      "grad_norm": 4.84131383895874,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.6084,
+      "step": 45
+    },
+    {
+      "epoch": 0.00210737052842316,
+      "grad_norm": 3.9473683834075928,
+      "learning_rate": 0.0,
+      "loss": 3.4833,
+      "step": 50
+    },
+    {
+      "epoch": 0.00210737052842316,
+      "eval_loss": 0.8623529672622681,
+      "eval_runtime": 1152.6945,
+      "eval_samples_per_second": 8.667,
+      "eval_steps_per_second": 4.333,
+      "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": 1.3407923862503424e+16,
+  "total_flos": 1.7219980646940672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null