Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9ee0bbf7b4e260fd1450e06e3f818fb3dba13f638b00ed67f529ed6a4f1bf9
+oid sha256:3f2cd9775d55e8ff82ac31ac351d5a39fe205fa6631acd56c5dbb7e8f46cc717
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c81717470719b3831c829726d60a115a46d6c3448764917910983a0794c38a97
+oid sha256:380297e19e72620e603aa5cb12112cf8e295e1b3c78caaf9e41f0b3c4d769063
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe77826af30856cd2bbe2036f15ecbd8d23e0de5186f5ebe288cba20ce21bbf
+oid sha256:21d15ecb64c1043495034231e12e1f6eaf7a066c06d428258074e1e177cfd5dc
 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": 0.027285129604365622,
+  "epoch": 0.040927694406548434,
   "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": 136.006,
       "eval_steps_per_second": 34.332,
       "step": 20
+    },
+    {
+      "epoch": 0.0286493860845839,
+      "grad_norm": 0.8405572772026062,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 22.2375,
+      "step": 21
+    },
+    {
+      "epoch": 0.030013642564802184,
+      "grad_norm": 0.8356078863143921,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 22.2348,
+      "step": 22
+    },
+    {
+      "epoch": 0.03137789904502047,
+      "grad_norm": 0.8963086605072021,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 22.2307,
+      "step": 23
+    },
+    {
+      "epoch": 0.03274215552523874,
+      "grad_norm": 0.8370237946510315,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 22.2573,
+      "step": 24
+    },
+    {
+      "epoch": 0.03274215552523874,
+      "eval_loss": 11.115113258361816,
+      "eval_runtime": 2.0089,
+      "eval_samples_per_second": 153.812,
+      "eval_steps_per_second": 38.826,
+      "step": 24
+    },
+    {
+      "epoch": 0.034106412005457026,
+      "grad_norm": 0.782231867313385,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 22.2062,
+      "step": 25
+    },
+    {
+      "epoch": 0.03547066848567531,
+      "grad_norm": 0.8036414384841919,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 22.1891,
+      "step": 26
+    },
+    {
+      "epoch": 0.036834924965893585,
+      "grad_norm": 0.7980690002441406,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 22.1769,
+      "step": 27
+    },
+    {
+      "epoch": 0.03819918144611187,
+      "grad_norm": 0.765007495880127,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 22.2746,
+      "step": 28
+    },
+    {
+      "epoch": 0.03819918144611187,
+      "eval_loss": 11.115106582641602,
+      "eval_runtime": 2.2892,
+      "eval_samples_per_second": 134.981,
+      "eval_steps_per_second": 34.073,
+      "step": 28
+    },
+    {
+      "epoch": 0.03956343792633015,
+      "grad_norm": 0.7230098843574524,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 22.2417,
+      "step": 29
+    },
+    {
+      "epoch": 0.040927694406548434,
+      "grad_norm": 0.7598402500152588,
+      "learning_rate": 0.0,
+      "loss": 22.229,
+      "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": 415991070720.0,
+  "total_flos": 623986606080.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null