Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:009a4577ea9f39ac432b86286d492354281723bf3499d281e3142b4d7a01e9b6
+oid sha256:ce8cb85268a84a0266d18d8a580b783846d1731c6b8beb80f78067c4c365e408
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d119c656e6b5819f5214e6ecbf80c1aeaa8e2cceaf763dcc7d498652468e6f7
+oid sha256:7bf7d29b21e86948aaee0ed397eec1e6bbb2e1943a1dc1c4a86c3413a21c6ad5
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c2a2b6c14c41c8ac1cc853bb5193f411312de8e64dc95fc7f6bdf424a267af
+oid sha256:f75a460e621a1b8d5d369f61a4d5a854d679d979759e85e31e5ba3a94dfe5240
 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": 0.02031969655919805,
+  "epoch": 0.0270929287455974,
   "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": 3.2972,
       "step": 75
+    },
+    {
+      "epoch": 0.020590625846654022,
+      "grad_norm": 2.1070995330810547,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.8003,
+      "step": 76
+    },
+    {
+      "epoch": 0.020861555134109998,
+      "grad_norm": 1.7353930473327637,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.8643,
+      "step": 77
+    },
+    {
+      "epoch": 0.02113248442156597,
+      "grad_norm": 1.5347745418548584,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 3.3596,
+      "step": 78
+    },
+    {
+      "epoch": 0.021403413709021945,
+      "grad_norm": 2.028477668762207,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 3.304,
+      "step": 79
+    },
+    {
+      "epoch": 0.02167434299647792,
+      "grad_norm": 2.2143213748931885,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.6186,
+      "step": 80
+    },
+    {
+      "epoch": 0.021945272283933892,
+      "grad_norm": 1.5614761114120483,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.5853,
+      "step": 81
+    },
+    {
+      "epoch": 0.021945272283933892,
+      "eval_loss": 1.5685601234436035,
+      "eval_runtime": 234.3138,
+      "eval_samples_per_second": 13.264,
+      "eval_steps_per_second": 1.66,
+      "step": 81
+    },
+    {
+      "epoch": 0.022216201571389867,
+      "grad_norm": 2.075254201889038,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.9721,
+      "step": 82
+    },
+    {
+      "epoch": 0.022487130858845843,
+      "grad_norm": 1.7247716188430786,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 3.0975,
+      "step": 83
+    },
+    {
+      "epoch": 0.022758060146301815,
+      "grad_norm": 1.402299165725708,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.0619,
+      "step": 84
+    },
+    {
+      "epoch": 0.02302898943375779,
+      "grad_norm": 1.8681529760360718,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.9484,
+      "step": 85
+    },
+    {
+      "epoch": 0.02329991872121376,
+      "grad_norm": 1.9394612312316895,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.5302,
+      "step": 86
+    },
+    {
+      "epoch": 0.023570848008669737,
+      "grad_norm": 2.028913974761963,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 3.3207,
+      "step": 87
+    },
+    {
+      "epoch": 0.023841777296125712,
+      "grad_norm": 2.744318962097168,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.9265,
+      "step": 88
+    },
+    {
+      "epoch": 0.024112706583581684,
+      "grad_norm": 1.7354165315628052,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 3.1633,
+      "step": 89
+    },
+    {
+      "epoch": 0.02438363587103766,
+      "grad_norm": 1.4790713787078857,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.5952,
+      "step": 90
+    },
+    {
+      "epoch": 0.02438363587103766,
+      "eval_loss": 1.565293312072754,
+      "eval_runtime": 233.712,
+      "eval_samples_per_second": 13.298,
+      "eval_steps_per_second": 1.664,
+      "step": 90
+    },
+    {
+      "epoch": 0.024654565158493635,
+      "grad_norm": 2.140333890914917,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 3.3539,
+      "step": 91
+    },
+    {
+      "epoch": 0.024925494445949607,
+      "grad_norm": 1.8280593156814575,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.2755,
+      "step": 92
+    },
+    {
+      "epoch": 0.025196423733405582,
+      "grad_norm": 1.7533349990844727,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 3.144,
+      "step": 93
+    },
+    {
+      "epoch": 0.025467353020861554,
+      "grad_norm": 1.1463032960891724,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.7731,
+      "step": 94
+    },
+    {
+      "epoch": 0.02573828230831753,
+      "grad_norm": 2.131800651550293,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 3.745,
+      "step": 95
+    },
+    {
+      "epoch": 0.026009211595773504,
+      "grad_norm": 1.580354928970337,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.718,
+      "step": 96
+    },
+    {
+      "epoch": 0.026280140883229476,
+      "grad_norm": 1.5779976844787598,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.9536,
+      "step": 97
+    },
+    {
+      "epoch": 0.02655107017068545,
+      "grad_norm": 1.7121436595916748,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 3.272,
+      "step": 98
+    },
+    {
+      "epoch": 0.026821999458141427,
+      "grad_norm": 1.9496688842773438,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 3.1555,
+      "step": 99
+    },
+    {
+      "epoch": 0.026821999458141427,
+      "eval_loss": 1.5646346807479858,
+      "eval_runtime": 233.9547,
+      "eval_samples_per_second": 13.285,
+      "eval_steps_per_second": 1.663,
+      "step": 99
+    },
+    {
+      "epoch": 0.0270929287455974,
+      "grad_norm": 2.362600088119507,
+      "learning_rate": 0.0,
+      "loss": 3.1908,
+      "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": 9.83913644163072e+16,
+  "total_flos": 1.301305142280192e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null