Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154802d9cd6752a4f3dd86e7ff97ec92faaeb69b900f2fb330227f34a4d75ab0
+oid sha256:686eec4f9e3cffe9c7d4b0622c18ae772bf3223468346c22da1479150ce17b78
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f013fe94f3a41f69bae485fa6733876252e3980170d27db5ba0681f6106f60b7
+oid sha256:5cdf9b5bcb2f154e6220d883504e506edd1d866ef6013e2e51661eb4e1238b84
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16323fd94c5f93c7b898aea1b7201e4c33097c4408e1a12d2fc5fee549b670c4
+oid sha256:6e4cdc3b0446661980d16c051a9c550ba61e0031d1b5527cd29b366b44c24bd9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457a0a52259cced6b76c949d89a7eea5b5ea9329c8fcb41a32547784be1dd99e
+oid sha256:3cd3f6e9267a2b7ffad41dddfa33b74e45aa7c480b8283eebbe1a013b2da49f9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2727272727272725,
+  "epoch": 3.0,
   "eval_steps": 3,
-  "global_step": 25,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -254,6 +254,86 @@
       "learning_rate": 2.6996748113442394e-05,
       "loss": 2.7016,
       "step": 25
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.32994455099105835,
+      "learning_rate": 2.1165983894256647e-05,
+      "loss": 2.9381,
+      "step": 26
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.34595945477485657,
+      "learning_rate": 1.5872342839067306e-05,
+      "loss": 2.6949,
+      "step": 27
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "eval_loss": 1.3376667499542236,
+      "eval_runtime": 2.7171,
+      "eval_samples_per_second": 3.68,
+      "eval_steps_per_second": 0.736,
+      "step": 27
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.3484823703765869,
+      "learning_rate": 1.1214435464779006e-05,
+      "loss": 2.7007,
+      "step": 28
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 0.3723781704902649,
+      "learning_rate": 7.2790297726755716e-06,
+      "loss": 2.5917,
+      "step": 29
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.39661362767219543,
+      "learning_rate": 4.139434924727359e-06,
+      "loss": 2.7226,
+      "step": 30
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "eval_loss": 1.3286577463150024,
+      "eval_runtime": 2.7162,
+      "eval_samples_per_second": 3.682,
+      "eval_steps_per_second": 0.736,
+      "step": 30
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 0.45583441853523254,
+      "learning_rate": 1.8541356326100433e-06,
+      "loss": 2.5628,
+      "step": 31
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.3815874755382538,
+      "learning_rate": 4.6570269818346224e-07,
+      "loss": 2.663,
+      "step": 32
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.39601853489875793,
+      "learning_rate": 0.0,
+      "loss": 2.635,
+      "step": 33
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.3268665075302124,
+      "eval_runtime": 2.718,
+      "eval_samples_per_second": 3.679,
+      "eval_steps_per_second": 0.736,
+      "step": 33
     }
   ],
   "logging_steps": 1,
@@ -268,12 +348,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.3478299623424e+16,
+  "total_flos": 8.379135550291968e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null