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:a121253d889923a72d084ca49b30e9b94acd92806835676d6441f8e2427cc44b
+oid sha256:2e426acdc01dc2f31bcafaf6ec4cbbde4c9dc0c2002e983ebf4ad35d9c3d27df
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a19fe7ff71ef30281ef4a4b3aa6266d4dc5b85aace6b3e9879dbccb6563854
+oid sha256:f8767e8d65ef705c7fa2c80607148e0c84fe8bb5950fd0b77ae77f68578c4fad
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1902eeb51fe92d3e250c39d6fbb85959781ab19bfc1376401ea409486445eba3
+oid sha256:176a5e6ad56a0c7dbf29dbb91cf09e759c3129690e4d273738e657f00d6ddb75
 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": 0.2180232558139535,
+  "epoch": 0.29069767441860467,
   "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": 0.0331,
       "step": 75
+    },
+    {
+      "epoch": 0.22093023255813954,
+      "grad_norm": 0.19937089085578918,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0324,
+      "step": 76
+    },
+    {
+      "epoch": 0.2238372093023256,
+      "grad_norm": 0.20462292432785034,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0236,
+      "step": 77
+    },
+    {
+      "epoch": 0.22674418604651161,
+      "grad_norm": 0.28567931056022644,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0276,
+      "step": 78
+    },
+    {
+      "epoch": 0.22965116279069767,
+      "grad_norm": 0.4329880475997925,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0775,
+      "step": 79
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 0.4729216992855072,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0266,
+      "step": 80
+    },
+    {
+      "epoch": 0.23546511627906977,
+      "grad_norm": 0.19957783818244934,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0197,
+      "step": 81
+    },
+    {
+      "epoch": 0.23546511627906977,
+      "eval_loss": 0.04431019350886345,
+      "eval_runtime": 31.87,
+      "eval_samples_per_second": 9.099,
+      "eval_steps_per_second": 1.161,
+      "step": 81
+    },
+    {
+      "epoch": 0.23837209302325582,
+      "grad_norm": 0.3341924846172333,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0913,
+      "step": 82
+    },
+    {
+      "epoch": 0.24127906976744187,
+      "grad_norm": 0.18140165507793427,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0353,
+      "step": 83
+    },
+    {
+      "epoch": 0.2441860465116279,
+      "grad_norm": 0.2153806984424591,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0243,
+      "step": 84
+    },
+    {
+      "epoch": 0.24709302325581395,
+      "grad_norm": 0.2617124617099762,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.09424830228090286,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0089,
+      "step": 86
+    },
+    {
+      "epoch": 0.25290697674418605,
+      "grad_norm": 0.25709268450737,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0519,
+      "step": 87
+    },
+    {
+      "epoch": 0.2558139534883721,
+      "grad_norm": 0.5080177783966064,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0525,
+      "step": 88
+    },
+    {
+      "epoch": 0.25872093023255816,
+      "grad_norm": 0.39113932847976685,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0497,
+      "step": 89
+    },
+    {
+      "epoch": 0.2616279069767442,
+      "grad_norm": 0.22805412113666534,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0343,
+      "step": 90
+    },
+    {
+      "epoch": 0.2616279069767442,
+      "eval_loss": 0.044002652168273926,
+      "eval_runtime": 31.8503,
+      "eval_samples_per_second": 9.105,
+      "eval_steps_per_second": 1.162,
+      "step": 90
+    },
+    {
+      "epoch": 0.26453488372093026,
+      "grad_norm": 0.24416109919548035,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0488,
+      "step": 91
+    },
+    {
+      "epoch": 0.26744186046511625,
+      "grad_norm": 0.2086295783519745,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0329,
+      "step": 92
+    },
+    {
+      "epoch": 0.2703488372093023,
+      "grad_norm": 0.20100471377372742,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0207,
+      "step": 93
+    },
+    {
+      "epoch": 0.27325581395348836,
+      "grad_norm": 0.28016161918640137,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0322,
+      "step": 94
+    },
+    {
+      "epoch": 0.2761627906976744,
+      "grad_norm": 0.32431530952453613,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0382,
+      "step": 95
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 0.2922443449497223,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0363,
+      "step": 96
+    },
+    {
+      "epoch": 0.2819767441860465,
+      "grad_norm": 0.34880465269088745,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0443,
+      "step": 97
+    },
+    {
+      "epoch": 0.28488372093023256,
+      "grad_norm": 0.882049560546875,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0361,
+      "step": 98
+    },
+    {
+      "epoch": 0.2877906976744186,
+      "grad_norm": 0.5549324750900269,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0871,
+      "step": 99
+    },
+    {
+      "epoch": 0.2877906976744186,
+      "eval_loss": 0.043825071305036545,
+      "eval_runtime": 31.844,
+      "eval_samples_per_second": 9.107,
+      "eval_steps_per_second": 1.162,
+      "step": 99
+    },
+    {
+      "epoch": 0.29069767441860467,
+      "grad_norm": 0.2323886752128601,
+      "learning_rate": 0.0,
+      "loss": 0.0321,
+      "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": 5.675437719237427e+16,
+  "total_flos": 7.530155928138547e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null