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:b30aab81a2c73ff179cf5cd5c7ef7a1fc2fc31593baa88ca724f3f56ec142ccd
+oid sha256:aef13c7d3ab0cc7d9711429383d5126660176e63e43e44789e9cb4a2b74b191b
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78c5948cc77970bfa90af60300a5aa1acbcbc4ac7f078590d1bfbbcde8fd1be
+oid sha256:9f4e9893d6c5dc96495cd92b2b45d819299c665c7d76886c642fe84f01fe4f71
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5422e431132fda45ce41e11245df931d4ae299f8b0106b13fe4320143a9aa79
+oid sha256:e997acc915bc31159bea4a64d3eeca625535d0aa21ae0b5409f6eb4e471dc04c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20151133501259447,
+  "epoch": 0.2518891687657431,
   "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": 5.000000000000002e-05,
       "loss": 11.7715,
       "step": 20
+    },
+    {
+      "epoch": 0.21158690176322417,
+      "grad_norm": 0.13320545852184296,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 11.7673,
+      "step": 21
+    },
+    {
+      "epoch": 0.21158690176322417,
+      "eval_loss": 11.770564079284668,
+      "eval_runtime": 1.4506,
+      "eval_samples_per_second": 57.906,
+      "eval_steps_per_second": 28.953,
+      "step": 21
+    },
+    {
+      "epoch": 0.2216624685138539,
+      "grad_norm": 0.1167505532503128,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 11.7674,
+      "step": 22
+    },
+    {
+      "epoch": 0.23173803526448364,
+      "grad_norm": 0.11704544723033905,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 11.7747,
+      "step": 23
+    },
+    {
+      "epoch": 0.24181360201511334,
+      "grad_norm": 0.14804768562316895,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 11.7682,
+      "step": 24
+    },
+    {
+      "epoch": 0.24181360201511334,
+      "eval_loss": 11.770421028137207,
+      "eval_runtime": 1.4338,
+      "eval_samples_per_second": 58.584,
+      "eval_steps_per_second": 29.292,
+      "step": 24
+    },
+    {
+      "epoch": 0.2518891687657431,
+      "grad_norm": 0.1328144669532776,
+      "learning_rate": 0.0,
+      "loss": 11.7815,
+      "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": 8148001751040.0,
+  "total_flos": 10185002188800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null