Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9ad5d64a03166c9bc524ad8d174996cf90d43192abaf327c997d4242ed6b6a
+oid sha256:98fa0e12d35450ceeecdcbdc4573f6bb4f1d313fb9d48d3ccf3f0f6ffc3de8f4
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae808ff75202262c58fb5518155b1610a757f83dcb74ffa7177051c3a66bf76
+oid sha256:d687b5d99c9b35c578c7057366d7b9de6c7889b4e9367161fcb4afb213c85bd9
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408e56684290fc2d4d62af6818d9eed799690d481ec8a8ead29730102632763f
+oid sha256:faac1656e758e8dc521d5b3ce272931901186027e782eb031f8a28a6467d6ac1
 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": 0.001684655038803221,
+  "epoch": 0.0022462067184042945,
   "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": 3.3569,
       "step": 75
+    },
+    {
+      "epoch": 0.001707117105987264,
+      "grad_norm": 1.6450163125991821,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 4.1236,
+      "step": 76
+    },
+    {
+      "epoch": 0.001729579173171307,
+      "grad_norm": 1.7483961582183838,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 3.4614,
+      "step": 77
+    },
+    {
+      "epoch": 0.00175204124035535,
+      "grad_norm": 1.6474915742874146,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 3.6418,
+      "step": 78
+    },
+    {
+      "epoch": 0.0017745033075393928,
+      "grad_norm": 1.821834921836853,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 3.7526,
+      "step": 79
+    },
+    {
+      "epoch": 0.0017969653747234359,
+      "grad_norm": 1.957961082458496,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.4547,
+      "step": 80
+    },
+    {
+      "epoch": 0.0018194274419074787,
+      "grad_norm": 1.7345044612884521,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 3.4015,
+      "step": 81
+    },
+    {
+      "epoch": 0.0018194274419074787,
+      "eval_loss": 1.7359950542449951,
+      "eval_runtime": 3689.1959,
+      "eval_samples_per_second": 10.162,
+      "eval_steps_per_second": 1.27,
+      "step": 81
+    },
+    {
+      "epoch": 0.0018418895090915217,
+      "grad_norm": 1.4380539655685425,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.8638,
+      "step": 82
+    },
+    {
+      "epoch": 0.0018643515762755646,
+      "grad_norm": 1.7943803071975708,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 3.9001,
+      "step": 83
+    },
+    {
+      "epoch": 0.0018868136434596076,
+      "grad_norm": 1.9069151878356934,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.5066,
+      "step": 84
+    },
+    {
+      "epoch": 0.0019092757106436505,
+      "grad_norm": 1.470371961593628,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.9766,
+      "step": 85
+    },
+    {
+      "epoch": 0.0019317377778276935,
+      "grad_norm": 1.998091697692871,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.3901,
+      "step": 86
+    },
+    {
+      "epoch": 0.0019541998450117366,
+      "grad_norm": 1.914188027381897,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 3.6886,
+      "step": 87
+    },
+    {
+      "epoch": 0.001976661912195779,
+      "grad_norm": 1.7242233753204346,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.8862,
+      "step": 88
+    },
+    {
+      "epoch": 0.0019991239793798223,
+      "grad_norm": 2.258370876312256,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 3.637,
+      "step": 89
+    },
+    {
+      "epoch": 0.0020215860465638653,
+      "grad_norm": 1.4420782327651978,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.3784,
+      "step": 90
+    },
+    {
+      "epoch": 0.0020215860465638653,
+      "eval_loss": 1.7353334426879883,
+      "eval_runtime": 3683.2503,
+      "eval_samples_per_second": 10.179,
+      "eval_steps_per_second": 1.273,
+      "step": 90
+    },
+    {
+      "epoch": 0.0020440481137479084,
+      "grad_norm": 1.5986779928207397,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.7943,
+      "step": 91
+    },
+    {
+      "epoch": 0.002066510180931951,
+      "grad_norm": 1.8626093864440918,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.2405,
+      "step": 92
+    },
+    {
+      "epoch": 0.002088972248115994,
+      "grad_norm": 1.8892990350723267,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 3.6672,
+      "step": 93
+    },
+    {
+      "epoch": 0.002111434315300037,
+      "grad_norm": 1.4795621633529663,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.5423,
+      "step": 94
+    },
+    {
+      "epoch": 0.00213389638248408,
+      "grad_norm": 1.5005255937576294,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 3.5053,
+      "step": 95
+    },
+    {
+      "epoch": 0.0021563584496681228,
+      "grad_norm": 1.7678977251052856,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.5019,
+      "step": 96
+    },
+    {
+      "epoch": 0.002178820516852166,
+      "grad_norm": 2.1480631828308105,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 3.2112,
+      "step": 97
+    },
+    {
+      "epoch": 0.002201282584036209,
+      "grad_norm": 1.2812981605529785,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 3.7643,
+      "step": 98
+    },
+    {
+      "epoch": 0.002223744651220252,
+      "grad_norm": 1.8966565132141113,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 3.2049,
+      "step": 99
+    },
+    {
+      "epoch": 0.002223744651220252,
+      "eval_loss": 1.7351884841918945,
+      "eval_runtime": 3690.552,
+      "eval_samples_per_second": 10.158,
+      "eval_steps_per_second": 1.27,
+      "step": 99
+    },
+    {
+      "epoch": 0.0022462067184042945,
+      "grad_norm": 1.917539119720459,
+      "learning_rate": 0.0,
+      "loss": 3.8109,
+      "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": 4.90093651427328e+16,
+  "total_flos": 6.53458201903104e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null