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:f3eaf45ca20a20ebf97cfc7e12382be92343f85a1b7b6729388bdbdec38baecb
+oid sha256:229fb0a7b323ccaa152b171525fe3e606d5647c13fbdd5715a531aa0c85f3d1c
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:230ce319e60049de4229d9d1daad32392139099ec42ffaccf49eff6953dea670
+oid sha256:c3cfde1c96307631dff04a01c8b00f05bbd2cbd9a2091f28bc662e14a50f72fb
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ad7cb6a9a6a6cb8855e757ef54e7e17dc102320a000e95c9c6e704ea6edfc4
+oid sha256:2a960fcf48a9fd9c1d06e88cfc7075be777139c0820cceefddfffca392715396
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
+oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006840413160954922,
+  "epoch": 0.0010260619741432383,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,92 @@
       "eval_samples_per_second": 4.798,
       "eval_steps_per_second": 1.2,
       "step": 20
+    },
+    {
+      "epoch": 0.0007182433819002668,
+      "grad_norm": 5.748673439025879,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 9.2619,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007524454477050414,
+      "grad_norm": 5.746485233306885,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 8.7318,
+      "step": 22
+    },
+    {
+      "epoch": 0.000786647513509816,
+      "grad_norm": 4.3517255783081055,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 6.9672,
+      "step": 23
+    },
+    {
+      "epoch": 0.0008208495793145906,
+      "grad_norm": 4.058344841003418,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 7.4406,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008208495793145906,
+      "eval_loss": 3.7231340408325195,
+      "eval_runtime": 2566.6279,
+      "eval_samples_per_second": 4.797,
+      "eval_steps_per_second": 1.199,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008550516451193652,
+      "grad_norm": 5.805904865264893,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 7.5462,
+      "step": 25
+    },
+    {
+      "epoch": 0.0008892537109241398,
+      "grad_norm": 5.130537986755371,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 7.2794,
+      "step": 26
+    },
+    {
+      "epoch": 0.0009234557767289145,
+      "grad_norm": 5.133691310882568,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 7.9919,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009576578425336891,
+      "grad_norm": 5.328059196472168,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 7.8922,
+      "step": 28
+    },
+    {
+      "epoch": 0.0009576578425336891,
+      "eval_loss": 3.712865114212036,
+      "eval_runtime": 2567.0389,
+      "eval_samples_per_second": 4.796,
+      "eval_steps_per_second": 1.199,
+      "step": 28
+    },
+    {
+      "epoch": 0.0009918599083384636,
+      "grad_norm": 5.650175094604492,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 8.2262,
+      "step": 29
+    },
+    {
+      "epoch": 0.0010260619741432383,
+      "grad_norm": 4.0064263343811035,
+      "learning_rate": 0.0,
+      "loss": 6.046,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,12 +295,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.26956599246848e+16,
+  "total_flos": 1.90434898870272e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null