Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e5b99b8812279ae6e92ba2624b4c3b73cbcc988be58e28436ba4ce19a2f3c55
+oid sha256:e825662c902d295b9f887d5d2e0f79563f09da923b76ca8b25ef6b8ba5664b43
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da00d1a61426ffb822cb82515acd5c32e54793e907f09714d0775f0f0c2b3b8e
+oid sha256:89a4f62afbe72fdfde4c37b8cb4d9c4d365809ff2f19426f584976fff969f26f
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e74327a670fdb4f6d8981c7b37bfa0e3757d975977955213b3e2b0de12f48481
+oid sha256:93e6290402166ed2241be4a06c8e32ac781d6f0df02275fc302ddb121aa7e174
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1454898157129001,
+  "epoch": 0.19398642095053345,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 0.3118,
       "step": 75
+    },
+    {
+      "epoch": 0.14742967992240544,
+      "grad_norm": 1.5707823038101196,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.329,
+      "step": 76
+    },
+    {
+      "epoch": 0.14936954413191075,
+      "grad_norm": 0.8776403069496155,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.2757,
+      "step": 77
+    },
+    {
+      "epoch": 0.1513094083414161,
+      "grad_norm": 1.9407877922058105,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.348,
+      "step": 78
+    },
+    {
+      "epoch": 0.15324927255092144,
+      "grad_norm": 1.6693557500839233,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.3072,
+      "step": 79
+    },
+    {
+      "epoch": 0.15518913676042678,
+      "grad_norm": 0.9786368608474731,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.2356,
+      "step": 80
+    },
+    {
+      "epoch": 0.1571290009699321,
+      "grad_norm": 1.0574125051498413,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.1978,
+      "step": 81
+    },
+    {
+      "epoch": 0.1571290009699321,
+      "eval_loss": 0.2722632586956024,
+      "eval_runtime": 7.7369,
+      "eval_samples_per_second": 56.095,
+      "eval_steps_per_second": 7.109,
+      "step": 81
+    },
+    {
+      "epoch": 0.15906886517943744,
+      "grad_norm": 1.628749966621399,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2687,
+      "step": 82
+    },
+    {
+      "epoch": 0.16100872938894278,
+      "grad_norm": 1.5231091976165771,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.307,
+      "step": 83
+    },
+    {
+      "epoch": 0.1629485935984481,
+      "grad_norm": 0.9854992032051086,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.183,
+      "step": 84
+    },
+    {
+      "epoch": 0.16488845780795344,
+      "grad_norm": 1.5809539556503296,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2977,
+      "step": 85
+    },
+    {
+      "epoch": 0.16682832201745879,
+      "grad_norm": 1.4216303825378418,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.275,
+      "step": 86
+    },
+    {
+      "epoch": 0.1687681862269641,
+      "grad_norm": 1.5944830179214478,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.296,
+      "step": 87
+    },
+    {
+      "epoch": 0.17070805043646944,
+      "grad_norm": 1.6960701942443848,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.3684,
+      "step": 88
+    },
+    {
+      "epoch": 0.1726479146459748,
+      "grad_norm": 1.3024052381515503,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.304,
+      "step": 89
+    },
+    {
+      "epoch": 0.17458777885548013,
+      "grad_norm": 1.6905990839004517,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.3042,
+      "step": 90
+    },
+    {
+      "epoch": 0.17458777885548013,
+      "eval_loss": 0.26292115449905396,
+      "eval_runtime": 7.7439,
+      "eval_samples_per_second": 56.044,
+      "eval_steps_per_second": 7.102,
+      "step": 90
+    },
+    {
+      "epoch": 0.17652764306498545,
+      "grad_norm": 1.0282114744186401,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.227,
+      "step": 91
+    },
+    {
+      "epoch": 0.1784675072744908,
+      "grad_norm": 1.2541886568069458,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.2273,
+      "step": 92
+    },
+    {
+      "epoch": 0.18040737148399613,
+      "grad_norm": 1.7235442399978638,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3701,
+      "step": 93
+    },
+    {
+      "epoch": 0.18234723569350145,
+      "grad_norm": 1.2627227306365967,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3245,
+      "step": 94
+    },
+    {
+      "epoch": 0.1842870999030068,
+      "grad_norm": 1.996457815170288,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.3793,
+      "step": 95
+    },
+    {
+      "epoch": 0.18622696411251213,
+      "grad_norm": 1.1682064533233643,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.2895,
+      "step": 96
+    },
+    {
+      "epoch": 0.18816682832201745,
+      "grad_norm": 0.9628655910491943,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.2685,
+      "step": 97
+    },
+    {
+      "epoch": 0.1901066925315228,
+      "grad_norm": 1.4077612161636353,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.2579,
+      "step": 98
+    },
+    {
+      "epoch": 0.19204655674102813,
+      "grad_norm": 1.1800073385238647,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.2709,
+      "step": 99
+    },
+    {
+      "epoch": 0.19204655674102813,
+      "eval_loss": 0.26203885674476624,
+      "eval_runtime": 7.7497,
+      "eval_samples_per_second": 56.002,
+      "eval_steps_per_second": 7.097,
+      "step": 99
+    },
+    {
+      "epoch": 0.19398642095053345,
+      "grad_norm": 1.5470740795135498,
+      "learning_rate": 0.0,
+      "loss": 0.2969,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1936784325869568.0,
+  "total_flos": 2596262859767808.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null