Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eada732e346e878e42c7d8fa75b9f0172115415614d3764563c15a5d9e64e7ff
+oid sha256:35625325b37bdb1aa820832ffaf9859b989843dfadd73dd2f5d9dad03abd5335
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a826e40b0b99b1a035c9ad5844aeb6bd779e310329dc9a9084ed12391aaa2dd
+oid sha256:1f22af04af6a7dce74c7b7209a110fdb14991b5dd633f97f06b5fd34aeb41b6c
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c325a5b88aa7600e783ee566917eff9758a4ec707c33c129463258bf687aee2
+oid sha256:318d5daa1e33a35543249e590b5fd9b28d4e2137de5e81940e98782aeff96166
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:842484d97bbf42f9f92b7e7c8dcf4fda5e0b0607fec45e60ed168e6d3a7f3132
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016886543535620053,
+  "epoch": 0.0021108179419525065,
   "eval_steps": 3,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,57 @@
       "learning_rate": 1.4644660940672627e-05,
       "loss": 0.1891,
       "step": 20
+    },
+    {
+      "epoch": 0.0017730870712401056,
+      "grad_norm": 5.619901180267334,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1357,
+      "step": 21
+    },
+    {
+      "epoch": 0.0017730870712401056,
+      "eval_loss": 0.21679861843585968,
+      "eval_runtime": 422.402,
+      "eval_samples_per_second": 11.806,
+      "eval_steps_per_second": 5.904,
+      "step": 21
+    },
+    {
+      "epoch": 0.001857519788918206,
+      "grad_norm": 8.403288841247559,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.2989,
+      "step": 22
+    },
+    {
+      "epoch": 0.001941952506596306,
+      "grad_norm": 2.9916210174560547,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0602,
+      "step": 23
+    },
+    {
+      "epoch": 0.0020263852242744062,
+      "grad_norm": 4.566269874572754,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.1002,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020263852242744062,
+      "eval_loss": 0.20803606510162354,
+      "eval_runtime": 422.4259,
+      "eval_samples_per_second": 11.806,
+      "eval_steps_per_second": 5.904,
+      "step": 24
+    },
+    {
+      "epoch": 0.0021108179419525065,
+      "grad_norm": 3.1905064582824707,
+      "learning_rate": 0.0,
+      "loss": 0.0737,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -217,12 +268,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7398256992583680.0,
+  "total_flos": 9247821240729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null