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:eb25dea12d86720250cdd29c893800a32603ec911c5b425f703ffea99426431d
+oid sha256:88cfd88218a0ed57ad5f6787f01a8ef902000733592d007cca823e4e3532b207
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe049f446f3a52fe1377974d043fe50d900690ecb6d68e5c0d78ae0f164f67cb
+oid sha256:526e62afa3082aae3b245a0c2de23fb364b20fe25e4fc5fbc2fa150d75c31ffb
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f369a1a2e948f2c53ac30209de73baa6120e649316d2b303076e26e0a73f80
+oid sha256:3f56eb6ecb6e555dd51f2deae6cfd47b557bb3a64e89cc250c9761b67db105aa
 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": 0.0006487503446486206,
+  "epoch": 0.0009731255169729309,
   "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": 4.845,
       "eval_steps_per_second": 1.211,
       "step": 20
+    },
+    {
+      "epoch": 0.0006811878618810516,
+      "grad_norm": 1.4249883890151978,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 2.6742,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007136253791134826,
+      "grad_norm": 1.4055988788604736,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 1.7784,
+      "step": 22
+    },
+    {
+      "epoch": 0.0007460628963459136,
+      "grad_norm": 0.928236186504364,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 1.0199,
+      "step": 23
+    },
+    {
+      "epoch": 0.0007785004135783448,
+      "grad_norm": 1.2876646518707275,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 1.2437,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007785004135783448,
+      "eval_loss": 1.4463685750961304,
+      "eval_runtime": 2679.3905,
+      "eval_samples_per_second": 4.845,
+      "eval_steps_per_second": 1.211,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008109379308107758,
+      "grad_norm": 0.9354816675186157,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.9898,
+      "step": 25
+    },
+    {
+      "epoch": 0.0008433754480432068,
+      "grad_norm": 1.0255235433578491,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 1.0339,
+      "step": 26
+    },
+    {
+      "epoch": 0.0008758129652756378,
+      "grad_norm": 1.0746634006500244,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 1.3377,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009082504825080689,
+      "grad_norm": 1.349865436553955,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 1.2269,
+      "step": 28
+    },
+    {
+      "epoch": 0.0009082504825080689,
+      "eval_loss": 1.4437816143035889,
+      "eval_runtime": 2679.4324,
+      "eval_samples_per_second": 4.845,
+      "eval_steps_per_second": 1.211,
+      "step": 28
+    },
+    {
+      "epoch": 0.0009406879997404999,
+      "grad_norm": 1.3086576461791992,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 1.2352,
+      "step": 29
+    },
+    {
+      "epoch": 0.0009731255169729309,
+      "grad_norm": 1.2033103704452515,
+      "learning_rate": 0.0,
+      "loss": 1.7437,
+      "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": 8853834826776576.0,
+  "total_flos": 1.3795510078930944e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null