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:e9febd91d8b250a757e5e20db0c17dd31f8328ca1cfba5e912c4b08b48122391
+oid sha256:e9e681aa9df6e96b0d15e24e380eb3be9455f679858ef053f15e8e8f2b5f175c
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ef61f8fa772fe7317ee1d17adea4b9916a57ad1a7b5c586a8693362c9775e53
+oid sha256:73447659b251d097a6d38c0102cb4e21f7180069900979a9f44a61c43d4f5972
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9cc1499efa28713149ad18377e13339f183229e13346e4cf268c0279e8760b
+oid sha256:12c8df53bedaf4fc7622a5b3ec954c3ebcc07000e902549b31e3b44210ac6cc6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.27645788336933047,
+  "epoch": 0.34557235421166305,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,48 @@
       "eval_samples_per_second": 5.533,
       "eval_steps_per_second": 2.785,
       "step": 24
+    },
+    {
+      "epoch": 0.28797696184305255,
+      "grad_norm": 13.395209312438965,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4717,
+      "step": 25
+    },
+    {
+      "epoch": 0.2994960403167747,
+      "grad_norm": 11.832671165466309,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.4415,
+      "step": 26
+    },
+    {
+      "epoch": 0.31101511879049676,
+      "grad_norm": 13.087400436401367,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.4317,
+      "step": 27
+    },
+    {
+      "epoch": 0.32253419726421884,
+      "grad_norm": 13.915994644165039,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.6166,
+      "step": 28
+    },
+    {
+      "epoch": 0.33405327573794097,
+      "grad_norm": 14.689959526062012,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 2.4773,
+      "step": 29
+    },
+    {
+      "epoch": 0.34557235421166305,
+      "grad_norm": 13.360550880432129,
+      "learning_rate": 0.0,
+      "loss": 2.2851,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +263,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4724371741618995e+17,
+  "total_flos": 1.8405464677023744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null