Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d3d66c11e2b360be88ecd5f57f13cd8ab0e7c866c5f89498ac8bd752a17dd6e
+oid sha256:a0bbff38b690e4837c6145cfbdfc3a0cdfb195ab2252e518c480be91e060c07e
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d2deb92e8011485052f8ecfd0965b2af0649fdf25aa2d17559da76000c60aa
+oid sha256:8c49bad6c482888c0a867e893d36c7902626f69601640a39530204e519cc2a7f
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a216e76306077697fce369babc722d934631ceab06c507d0d26aa9b1335b22
+oid sha256:05e22fba92b29c1f5f0cd59a19fdf634f506ef846ae85ca8af68d60096387010
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011933174224343675,
+  "epoch": 0.02386634844868735,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 0.6874,
       "step": 5
+    },
+    {
+      "epoch": 0.014319809069212411,
+      "grad_norm": 0.5783711671829224,
+      "learning_rate": 0.00012,
+      "loss": 0.7382,
+      "step": 6
+    },
+    {
+      "epoch": 0.014319809069212411,
+      "eval_loss": 0.8450251817703247,
+      "eval_runtime": 53.7347,
+      "eval_samples_per_second": 3.294,
+      "eval_steps_per_second": 1.656,
+      "step": 6
+    },
+    {
+      "epoch": 0.016706443914081145,
+      "grad_norm": 0.48139792680740356,
+      "learning_rate": 0.00014,
+      "loss": 0.7345,
+      "step": 7
+    },
+    {
+      "epoch": 0.01909307875894988,
+      "grad_norm": 0.659209132194519,
+      "learning_rate": 0.00016,
+      "loss": 0.9507,
+      "step": 8
+    },
+    {
+      "epoch": 0.021479713603818614,
+      "grad_norm": 0.3521082401275635,
+      "learning_rate": 0.00018,
+      "loss": 0.6469,
+      "step": 9
+    },
+    {
+      "epoch": 0.021479713603818614,
+      "eval_loss": 0.7874255776405334,
+      "eval_runtime": 54.1173,
+      "eval_samples_per_second": 3.271,
+      "eval_steps_per_second": 1.645,
+      "step": 9
+    },
+    {
+      "epoch": 0.02386634844868735,
+      "grad_norm": 0.33297309279441833,
+      "learning_rate": 0.0002,
+      "loss": 0.6382,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2794842929233920.0,
+  "total_flos": 5589685858467840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null