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:bfad655b9cc8d6fbd0e305354582b18080be9471abeb55c3f3e2ae800d68ff87
+oid sha256:6a07ebee0ed35c2c64e8ba62c0e7e3e477821d9b5e7762c01375a1ca15209118
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a5fca5f0879440800f4e6d7359ad9362dad40401c78b712074a1ba7b5f57ea
+oid sha256:1ff5f59242ca993fc95667da31231f28061438482efd6d066f3b08345481f908
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2972d332e3d5fa4abdd6b0429885a3ecc36eabdf15f91d3aebed7cea929537a
+oid sha256:9651cf822486034420437c791f4ec2317d0a774d1a54b1d0661a1c1cac338931
 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": 0.0014187918986982584,
+  "epoch": 0.0021281878480473877,
   "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": 10.389,
       "eval_steps_per_second": 2.597,
       "step": 20
+    },
+    {
+      "epoch": 0.0014897314936331714,
+      "grad_norm": 15.290266036987305,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 12.2422,
+      "step": 21
+    },
+    {
+      "epoch": 0.0015606710885680843,
+      "grad_norm": 20.042848587036133,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 12.2315,
+      "step": 22
+    },
+    {
+      "epoch": 0.0016316106835029972,
+      "grad_norm": 18.54485511779785,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 10.9287,
+      "step": 23
+    },
+    {
+      "epoch": 0.00170255027843791,
+      "grad_norm": 13.682432174682617,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 9.4619,
+      "step": 24
+    },
+    {
+      "epoch": 0.00170255027843791,
+      "eval_loss": 5.023678779602051,
+      "eval_runtime": 572.14,
+      "eval_samples_per_second": 10.375,
+      "eval_steps_per_second": 2.594,
+      "step": 24
+    },
+    {
+      "epoch": 0.0017734898733728231,
+      "grad_norm": 18.009124755859375,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 8.3285,
+      "step": 25
+    },
+    {
+      "epoch": 0.001844429468307736,
+      "grad_norm": 13.645432472229004,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 10.0566,
+      "step": 26
+    },
+    {
+      "epoch": 0.0019153690632426488,
+      "grad_norm": 18.476457595825195,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 12.3408,
+      "step": 27
+    },
+    {
+      "epoch": 0.001986308658177562,
+      "grad_norm": 12.815871238708496,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 10.3213,
+      "step": 28
+    },
+    {
+      "epoch": 0.001986308658177562,
+      "eval_loss": 5.011484146118164,
+      "eval_runtime": 571.8616,
+      "eval_samples_per_second": 10.38,
+      "eval_steps_per_second": 2.595,
+      "step": 28
+    },
+    {
+      "epoch": 0.002057248253112475,
+      "grad_norm": 13.162454605102539,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 7.7106,
+      "step": 29
+    },
+    {
+      "epoch": 0.0021281878480473877,
+      "grad_norm": 11.562494277954102,
+      "learning_rate": 0.0,
+      "loss": 8.1572,
+      "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": 6534582019031040.0,
+  "total_flos": 9801873028546560.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null