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:e9de5c0cff3a418ea09054aff17061ed469b97bca80354f6a15c9af4a0a10e31
+oid sha256:befd22b5a3f9ec1d1fddb8e6defa14282f3292b707c3782a6e5884f2d1bc00e7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe10cf55653b79dd28ee7687344e0e8511875460d6606dcd87a5d9989b15b44
+oid sha256:1df43b9e11bda8404ab36cdac0528b2ee5cdb566a4474f5b95623710a305f493
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f34ff3f85f439db0dd0572e71b22e640785f8b9a2abbcf4a689d3d6950f0ef7
+oid sha256:f0730f9d2eae3218a46b4cbc2f92cae54abcf73add6c551ac5e7062f90b7be81
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005743206863132201,
+  "epoch": 0.0008614810294698302,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 2.027,
       "step": 18
+    },
+    {
+      "epoch": 0.0006030367206288812,
+      "grad_norm": 2.3975160121917725,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.9556,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006891848235758642,
+      "grad_norm": 1.2486457824707031,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.8344,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006891848235758642,
+      "eval_loss": 0.44342318177223206,
+      "eval_runtime": 3966.1386,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 1.849,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007753329265228472,
+      "grad_norm": 1.603333592414856,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.6793,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008614810294698302,
+      "grad_norm": 1.5062958002090454,
+      "learning_rate": 0.0,
+      "loss": 1.9452,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7031294986813440.0,
+  "total_flos": 1.054694248022016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null