Training in progress, step 420, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:204a349fb5f2880ebc9716e2c999f98555ac7db9085761fb01ccb8be60805c18
+oid sha256:6030cdfec156be32c0ce5ce5c733e922acd059040b45ccb4972e725954306c40
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f474ba23721d4d9a1c85d01088a42d6297ce6fce23f3e15e68800d582b9d412b
+oid sha256:6abef001eb5046117ec6eee464e1792aa5acbda3c0d305591284db66b9017c9d
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b43a77608e3595ef8ce792c3fd5462a71b9b7958002088c96e8d041e0e2ab5b
+oid sha256:601d3cd30158a5ec1e80bcf2fe124c9ff7d378ee828c7f46d1e57e335b5624be
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac207b57c6cefba3838e335ba7ebf320ffdaee8162f1c0afc72ea9ad9f0725f
+oid sha256:b9507fdefdfac1d5dbc7a23a3aeb675b6dd3cc22a3762b7e85ff02a1c9c43105
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.231270358306189,
+  "epoch": 1.3680781758957654,
   "eval_steps": 42,
-  "global_step": 378,
+  "global_step": 420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -969,6 +969,112 @@
       "eval_samples_per_second": 23.31,
       "eval_steps_per_second": 5.861,
       "step": 378
+    },
+    {
+      "epoch": 1.241042345276873,
+      "grad_norm": 2.3673043251037598,
+      "learning_rate": 1.3860256808630428e-05,
+      "loss": 0.8592,
+      "step": 381
+    },
+    {
+      "epoch": 1.2508143322475571,
+      "grad_norm": 2.451141357421875,
+      "learning_rate": 1.3202379370768252e-05,
+      "loss": 0.7932,
+      "step": 384
+    },
+    {
+      "epoch": 1.2605863192182412,
+      "grad_norm": 2.4431982040405273,
+      "learning_rate": 1.2558115014363592e-05,
+      "loss": 0.7265,
+      "step": 387
+    },
+    {
+      "epoch": 1.2703583061889252,
+      "grad_norm": 2.317182779312134,
+      "learning_rate": 1.1927702081543279e-05,
+      "loss": 0.7116,
+      "step": 390
+    },
+    {
+      "epoch": 1.2801302931596092,
+      "grad_norm": 2.2101731300354004,
+      "learning_rate": 1.1311373790174657e-05,
+      "loss": 0.7642,
+      "step": 393
+    },
+    {
+      "epoch": 1.2899022801302933,
+      "grad_norm": 2.8971657752990723,
+      "learning_rate": 1.0709358147587884e-05,
+      "loss": 0.7537,
+      "step": 396
+    },
+    {
+      "epoch": 1.2996742671009773,
+      "grad_norm": 2.7442216873168945,
+      "learning_rate": 1.0121877866225781e-05,
+      "loss": 0.765,
+      "step": 399
+    },
+    {
+      "epoch": 1.3094462540716614,
+      "grad_norm": 2.479196310043335,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.8282,
+      "step": 402
+    },
+    {
+      "epoch": 1.3192182410423452,
+      "grad_norm": 2.463113307952881,
+      "learning_rate": 8.991387270152201e-06,
+      "loss": 0.8097,
+      "step": 405
+    },
+    {
+      "epoch": 1.3289902280130292,
+      "grad_norm": 2.4927496910095215,
+      "learning_rate": 8.448795174344804e-06,
+      "loss": 0.8298,
+      "step": 408
+    },
+    {
+      "epoch": 1.3387622149837133,
+      "grad_norm": 2.711042881011963,
+      "learning_rate": 7.921574722852343e-06,
+      "loss": 0.7205,
+      "step": 411
+    },
+    {
+      "epoch": 1.3485342019543973,
+      "grad_norm": 2.803149938583374,
+      "learning_rate": 7.409920958039795e-06,
+      "loss": 0.7575,
+      "step": 414
+    },
+    {
+      "epoch": 1.3583061889250814,
+      "grad_norm": 2.474118232727051,
+      "learning_rate": 6.9140231634602485e-06,
+      "loss": 0.7231,
+      "step": 417
+    },
+    {
+      "epoch": 1.3680781758957654,
+      "grad_norm": 2.5949273109436035,
+      "learning_rate": 6.43406479383053e-06,
+      "loss": 0.8594,
+      "step": 420
+    },
+    {
+      "epoch": 1.3680781758957654,
+      "eval_loss": 1.3078192472457886,
+      "eval_runtime": 22.1879,
+      "eval_samples_per_second": 23.301,
+      "eval_steps_per_second": 5.859,
+      "step": 420
     }
   ],
   "logging_steps": 3,
@@ -988,7 +1094,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8506192533363098e+17,
+  "total_flos": 3.1674071048729395e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null