Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656c536d8e36c4680fec0a21fcc1ecdf6f2d175f0fdc2f118e0ab08d789075fc
+oid sha256:a4c9f8f38c6c48b7687f9756bbfbd8a3844326d1678a82a64bb9c808277d3fc0
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b8b9c918405982148cb6d3faa665d4673cbfa9a81bff1aad42fd09e6d99455e
+oid sha256:feb3ce02f3655a5c156b1f72cdbf9950c708a8814f52f8ef304b7aa85f6663b4
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:263c014c1c50d686dc987cdfdbccc2295858a7520df05ec7ee86fa2ca892e2e9
+oid sha256:9ee6b12187dd773b06e1a5bfabe1287c666f537b4c4545893a4ce19a48f7c6ce
 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": 0.020844189682126108,
+  "epoch": 0.031266284523189164,
   "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": 53.26,
       "eval_steps_per_second": 13.414,
       "step": 20
+    },
+    {
+      "epoch": 0.021886399166232414,
+      "grad_norm": 4.278845310211182,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 7.0912,
+      "step": 21
+    },
+    {
+      "epoch": 0.022928608650338717,
+      "grad_norm": 3.364438533782959,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 5.6775,
+      "step": 22
+    },
+    {
+      "epoch": 0.023970818134445022,
+      "grad_norm": 3.926478147506714,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 6.3461,
+      "step": 23
+    },
+    {
+      "epoch": 0.02501302761855133,
+      "grad_norm": 3.684072494506836,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 6.1135,
+      "step": 24
+    },
+    {
+      "epoch": 0.02501302761855133,
+      "eval_loss": 6.589331150054932,
+      "eval_runtime": 7.635,
+      "eval_samples_per_second": 53.045,
+      "eval_steps_per_second": 13.36,
+      "step": 24
+    },
+    {
+      "epoch": 0.026055237102657634,
+      "grad_norm": 4.822241306304932,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 6.6333,
+      "step": 25
+    },
+    {
+      "epoch": 0.02709744658676394,
+      "grad_norm": 4.0621337890625,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 6.4992,
+      "step": 26
+    },
+    {
+      "epoch": 0.028139656070870246,
+      "grad_norm": 4.09130334854126,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 6.168,
+      "step": 27
+    },
+    {
+      "epoch": 0.02918186555497655,
+      "grad_norm": 3.6915745735168457,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 6.2581,
+      "step": 28
+    },
+    {
+      "epoch": 0.02918186555497655,
+      "eval_loss": 6.585674285888672,
+      "eval_runtime": 7.5851,
+      "eval_samples_per_second": 53.394,
+      "eval_steps_per_second": 13.447,
+      "step": 28
+    },
+    {
+      "epoch": 0.030224075039082855,
+      "grad_norm": 4.406257152557373,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 6.4602,
+      "step": 29
+    },
+    {
+      "epoch": 0.031266284523189164,
+      "grad_norm": 3.4768879413604736,
+      "learning_rate": 0.0,
+      "loss": 6.4004,
+      "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": 277675172167680.0,
+  "total_flos": 413041818599424.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null