Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3233c67b06d19a42c258d1e1b79d8ef1ea8e0206ce418bf49d77af1131b2d770
+oid sha256:7f7dca198e3651254bfa77c8df55a570cf838f67cded5facf13e9860700d1545
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de6198ffdeb4b60fcfbfffe116fb13152442004123eb627ef6c0c0866944991
+oid sha256:7db2adfc0b7f89f5fd89238ec4f8d76678f7a592fd063d6acf15cc762eb59e00
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
+oid sha256:98d249c44d2043ac3faca89a38c200b16da869b2b95fda57466053e0556cdb5a
 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": 0.0014169323414806943,
+  "epoch": 0.0021253985122210413,
   "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": 6.961,
       "eval_steps_per_second": 1.74,
       "step": 20
+    },
+    {
+      "epoch": 0.001487778958554729,
+      "grad_norm": 17.12288475036621,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 6.8697,
+      "step": 21
+    },
+    {
+      "epoch": 0.0015586255756287637,
+      "grad_norm": 12.52187442779541,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 5.9574,
+      "step": 22
+    },
+    {
+      "epoch": 0.0016294721927027985,
+      "grad_norm": 14.923164367675781,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 8.2413,
+      "step": 23
+    },
+    {
+      "epoch": 0.0017003188097768332,
+      "grad_norm": 13.699613571166992,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 7.6529,
+      "step": 24
+    },
+    {
+      "epoch": 0.0017003188097768332,
+      "eval_loss": 6.94155216217041,
+      "eval_runtime": 854.7337,
+      "eval_samples_per_second": 6.954,
+      "eval_steps_per_second": 1.739,
+      "step": 24
+    },
+    {
+      "epoch": 0.001771165426850868,
+      "grad_norm": 15.484549522399902,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 5.9348,
+      "step": 25
+    },
+    {
+      "epoch": 0.0018420120439249026,
+      "grad_norm": 15.122868537902832,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 6.1889,
+      "step": 26
+    },
+    {
+      "epoch": 0.0019128586609989374,
+      "grad_norm": 17.317827224731445,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 7.4455,
+      "step": 27
+    },
+    {
+      "epoch": 0.001983705278072972,
+      "grad_norm": 14.604246139526367,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 5.7908,
+      "step": 28
+    },
+    {
+      "epoch": 0.001983705278072972,
+      "eval_loss": 6.888062000274658,
+      "eval_runtime": 853.8107,
+      "eval_samples_per_second": 6.962,
+      "eval_steps_per_second": 1.74,
+      "step": 28
+    },
+    {
+      "epoch": 0.002054551895147007,
+      "grad_norm": 14.61190414428711,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 6.7001,
+      "step": 29
+    },
+    {
+      "epoch": 0.0021253985122210413,
+      "grad_norm": 12.80364990234375,
+      "learning_rate": 0.0,
+      "loss": 6.8942,
+      "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": 9644534686285824.0,
+  "total_flos": 1.4466802029428736e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null