Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3dc27e36bc73390c29d9b72756ed36902f52fc372ac03f4fd55865f8b76db2
+oid sha256:d7542456d19f78e4157e4fd392cbbd2e66310d665194487361cfd7bf381421dc
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b1075c0f0990fdbd82c007b2d212dc9b365ae6584903d04f0aa75a80a1dfda
+oid sha256:b650b8ea1255f96365bcf375868feaaeda5c62723c3a831e89cd4c626b08d924
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63076df0e2f5c2eff0ee92071ec83ec94c981f8fbd2f640764417db149cee50d
+oid sha256:8a09ad7e826d10efce700906e00267beeb0fde82aeff880f7721e7c0c6d184a9
 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": 0.09345794392523364,
+  "epoch": 0.14018691588785046,
   "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": 240.465,
       "eval_steps_per_second": 61.452,
       "step": 20
+    },
+    {
+      "epoch": 0.09813084112149532,
+      "grad_norm": 0.021352330222725868,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 10.376,
+      "step": 21
+    },
+    {
+      "epoch": 0.102803738317757,
+      "grad_norm": 0.021228916943073273,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 10.3777,
+      "step": 22
+    },
+    {
+      "epoch": 0.10747663551401869,
+      "grad_norm": 0.022248834371566772,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 10.3831,
+      "step": 23
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "grad_norm": 0.02273450419306755,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 10.3764,
+      "step": 24
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "eval_loss": 10.380095481872559,
+      "eval_runtime": 0.3898,
+      "eval_samples_per_second": 230.9,
+      "eval_steps_per_second": 59.008,
+      "step": 24
+    },
+    {
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.02754243090748787,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 10.3803,
+      "step": 25
+    },
+    {
+      "epoch": 0.12149532710280374,
+      "grad_norm": 0.030890116468071938,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 10.3773,
+      "step": 26
+    },
+    {
+      "epoch": 0.1261682242990654,
+      "grad_norm": 0.02476532757282257,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 10.3786,
+      "step": 27
+    },
+    {
+      "epoch": 0.1308411214953271,
+      "grad_norm": 0.025537991896271706,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 10.3779,
+      "step": 28
+    },
+    {
+      "epoch": 0.1308411214953271,
+      "eval_loss": 10.38009262084961,
+      "eval_runtime": 0.4325,
+      "eval_samples_per_second": 208.081,
+      "eval_steps_per_second": 53.176,
+      "step": 28
+    },
+    {
+      "epoch": 0.13551401869158877,
+      "grad_norm": 0.022880561649799347,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 10.3801,
+      "step": 29
+    },
+    {
+      "epoch": 0.14018691588785046,
+      "grad_norm": 0.02900991402566433,
+      "learning_rate": 0.0,
+      "loss": 10.3815,
+      "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": 523024465920.0,
+  "total_flos": 784536698880.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null