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:f6e5c64f72918c5e267c96c1c6d9e79364d73dc15cea25431c37f4368ffc1ac4
+oid sha256:bcdd36f2fb681b1dd09df3d4ab4f2ae12af5e3161e384952f804758c286acfe6
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b65d227dba14bcdd21e3c07fc30cd702ab28746377f13eca6105d768d2f58c83
+oid sha256:a3e148a1403292405902fa8fb2be2df75d659e94d65262df9658b3348b7042ee
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074e8690a8d61dba7a66649463fc8a03dc8e3c47ce5a5c77b759d178ed3f5ec7
+oid sha256:8a9386662c626731526f1abdeed2bdc3abd9cd0423f5b4ce3bfa3fae95d59602
 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": 3.349,
       "step": 75
+    },
+    {
+      "epoch": 0.001707117105987264,
+      "grad_norm": 1.6613136529922485,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 4.1282,
+      "step": 76
+    },
+    {
+      "epoch": 0.001729579173171307,
+      "grad_norm": 1.7891541719436646,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 3.4591,
+      "step": 77
+    },
+    {
+      "epoch": 0.00175204124035535,
+      "grad_norm": 1.6895219087600708,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 3.639,
+      "step": 78
+    },
+    {
+      "epoch": 0.0017745033075393928,
+      "grad_norm": 1.7939364910125732,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 3.7528,
+      "step": 79
+    },
+    {
+      "epoch": 0.0017969653747234359,
+      "grad_norm": 1.9432029724121094,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.4584,
+      "step": 80
+    },
+    {
+      "epoch": 0.0018194274419074787,
+      "grad_norm": 1.8174926042556763,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 3.3959,
+      "step": 81
+    },
+    {
+      "epoch": 0.0018194274419074787,
+      "eval_loss": 1.736003041267395,
+      "eval_runtime": 1632.5563,
+      "eval_samples_per_second": 22.964,
+      "eval_steps_per_second": 2.871,
+      "step": 81
+    },
+    {
+      "epoch": 0.0018418895090915217,
+      "grad_norm": 1.5173909664154053,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.8656,
+      "step": 82
+    },
+    {
+      "epoch": 0.0018643515762755646,
+      "grad_norm": 1.859105110168457,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 3.914,
+      "step": 83
+    },
+    {
+      "epoch": 0.0018868136434596076,
+      "grad_norm": 2.0400619506835938,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.5052,
+      "step": 84
+    },
+    {
+      "epoch": 0.0019092757106436505,
+      "grad_norm": 1.5139789581298828,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.9755,
+      "step": 85
+    },
+    {
+      "epoch": 0.0019317377778276935,
+      "grad_norm": 1.9782215356826782,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.3867,
+      "step": 86
+    },
+    {
+      "epoch": 0.0019541998450117366,
+      "grad_norm": 2.021449327468872,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 3.6848,
+      "step": 87
+    },
+    {
+      "epoch": 0.001976661912195779,
+      "grad_norm": 1.7191298007965088,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.8803,
+      "step": 88
+    },
+    {
+      "epoch": 0.0019991239793798223,
+      "grad_norm": 2.1756093502044678,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 3.6223,
+      "step": 89
+    },
+    {
+      "epoch": 0.0020215860465638653,
+      "grad_norm": 1.4715290069580078,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.3865,
+      "step": 90
+    },
+    {
+      "epoch": 0.0020215860465638653,
+      "eval_loss": 1.7353254556655884,
+      "eval_runtime": 1632.2234,
+      "eval_samples_per_second": 22.969,
+      "eval_steps_per_second": 2.872,
+      "step": 90
+    },
+    {
+      "epoch": 0.0020440481137479084,
+      "grad_norm": 1.6335053443908691,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.797,
+      "step": 91
+    },
+    {
+      "epoch": 0.002066510180931951,
+      "grad_norm": 1.8039343357086182,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.244,
+      "step": 92
+    },
+    {
+      "epoch": 0.002088972248115994,
+      "grad_norm": 1.8326294422149658,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 3.6564,
+      "step": 93
+    },
+    {
+      "epoch": 0.002111434315300037,
+      "grad_norm": 1.3844493627548218,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.5496,
+      "step": 94
+    },
+    {
+      "epoch": 0.00213389638248408,
+      "grad_norm": 1.5978397130966187,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 3.5101,
+      "step": 95
+    },
+    {
+      "epoch": 0.0021563584496681228,
+      "grad_norm": 1.7243602275848389,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.5035,
+      "step": 96
+    },
+    {
+      "epoch": 0.002178820516852166,
+      "grad_norm": 2.2073657512664795,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 3.2104,
+      "step": 97
+    },
+    {
+      "epoch": 0.002201282584036209,
+      "grad_norm": 1.385772943496704,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 3.7669,
+      "step": 98
+    },
+    {
+      "epoch": 0.002223744651220252,
+      "grad_norm": 1.9135991334915161,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 3.1943,
+      "step": 99
+    },
+    {
+      "epoch": 0.002223744651220252,
+      "eval_loss": 1.7351237535476685,
+      "eval_runtime": 1632.3963,
+      "eval_samples_per_second": 22.966,
+      "eval_steps_per_second": 2.871,
+      "step": 99
+    },
+    {
+      "epoch": 0.0022462067184042945,
+      "grad_norm": 2.1019656658172607,
+      "learning_rate": 0.0,
+      "loss": 3.8132,
+      "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