Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94604d0ac5a7faa0e0f018719b7c4a560d37563e3f6cd70ce113caed39bcec57
+oid sha256:dbfd703e714024f209b47f7506c497132c492cf141d4acc0c7cc3335ebc71002
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b84d9b8c791d81e177f648f579b576c9f48dcbdd409675bb3569035769e6e77
+oid sha256:a7cc673e6e18b6409bb7a5056537b354297503d2024d54a1e1b97fc3fd46ab0b
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0209f05921de0136274ef4a05372901b598b75fa0e874253841db8c206ccaa41
+oid sha256:ec716528044712e0e5e0979b8a3976516403dbbe916d32e54d09aee0b99fc842
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
+oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.041407867494824016,
+  "epoch": 0.062111801242236024,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,92 @@
       "eval_samples_per_second": 108.89,
       "eval_steps_per_second": 27.223,
       "step": 20
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 2.526733875274658,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 4.6537,
+      "step": 21
+    },
+    {
+      "epoch": 0.045548654244306416,
+      "grad_norm": 2.275500774383545,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 4.4672,
+      "step": 22
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 2.3670482635498047,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 4.9217,
+      "step": 23
+    },
+    {
+      "epoch": 0.049689440993788817,
+      "grad_norm": 2.560924768447876,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 4.5278,
+      "step": 24
+    },
+    {
+      "epoch": 0.049689440993788817,
+      "eval_loss": 4.797541618347168,
+      "eval_runtime": 1.8879,
+      "eval_samples_per_second": 108.058,
+      "eval_steps_per_second": 27.015,
+      "step": 24
+    },
+    {
+      "epoch": 0.051759834368530024,
+      "grad_norm": 2.1704139709472656,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 4.5078,
+      "step": 25
+    },
+    {
+      "epoch": 0.053830227743271224,
+      "grad_norm": 2.6542437076568604,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 4.7914,
+      "step": 26
+    },
+    {
+      "epoch": 0.055900621118012424,
+      "grad_norm": 2.3289077281951904,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 4.5987,
+      "step": 27
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "grad_norm": 2.1212592124938965,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 4.6118,
+      "step": 28
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "eval_loss": 4.797481060028076,
+      "eval_runtime": 1.9317,
+      "eval_samples_per_second": 105.609,
+      "eval_steps_per_second": 26.402,
+      "step": 28
+    },
+    {
+      "epoch": 0.060041407867494824,
+      "grad_norm": 2.5971341133117676,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 4.8593,
+      "step": 29
+    },
+    {
+      "epoch": 0.062111801242236024,
+      "grad_norm": 2.5996856689453125,
+      "learning_rate": 0.0,
+      "loss": 4.8716,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,12 +295,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 138837586083840.0,
+  "total_flos": 208256379125760.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null