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:f416c03053b4ca16288fd699a69bbb08a0f2acdc49c5124664312342faa3abc5
+oid sha256:38c34560ee8de70125e40184931ea29189216bf28dc992e6d5366c98c05923de
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc38125d19fc986d795ef07338260455cc67ee44e7a13b8699c17a4cba913d55
+oid sha256:d0b4d222be0dc33ac23cdad799549991c4bedc7edcfb3b25a7b9812f7e057a3d
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359d0ddb346e1a051d153b9361e52227f5a93bfd11d7d59f8d34fe81bcaff9e5
+oid sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.044444444444444446,
+  "epoch": 0.06666666666666667,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 10.5127,
       "step": 18
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 3.910113573074341,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.2341,
+      "step": 21
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 3.3914926052093506,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.0756,
+      "step": 24
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "eval_loss": 10.00505256652832,
+      "eval_runtime": 3.0557,
+      "eval_samples_per_second": 62.178,
+      "eval_steps_per_second": 31.089,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.1708614826202393,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 9.9692,
+      "step": 27
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 3.2920045852661133,
+      "learning_rate": 0.0,
+      "loss": 9.9368,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5328093315072.0,
+  "total_flos": 7907297722368.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null