Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d84899b73d2e7ac6cf01c0017bb15f12d47ea94f94d274fef3a64515bb3fda8
+oid sha256:55a452d8e9b208841e7566bc1719cfcb640e444a9600203cbd007aff0f4a65cd
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620cdb0308da5c52f853243089c17ed848ef45723f636b13494d182846d7be93
+oid sha256:8c3038ff158b78e1c496779294cb77858d3c30b290d005ee749931eb58110ad6
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beff99274e577d5544cd3c26596454c41d1ae8c4ebea9d6ec296a947e69bd8d1
+oid sha256:649923c7539689216b57dad4a619a2344ec4785f724ecc16043c4b292d763ad9
 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": 0.13297872340425532,
+  "epoch": 0.1773049645390071,
   "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": 0.2336,
       "step": 75
+    },
+    {
+      "epoch": 0.1347517730496454,
+      "grad_norm": 0.4144452214241028,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2263,
+      "step": 76
+    },
+    {
+      "epoch": 0.13652482269503546,
+      "grad_norm": 0.5535529851913452,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.2731,
+      "step": 77
+    },
+    {
+      "epoch": 0.13829787234042554,
+      "grad_norm": 0.6666750907897949,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.2748,
+      "step": 78
+    },
+    {
+      "epoch": 0.1400709219858156,
+      "grad_norm": 0.5558615326881409,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.2561,
+      "step": 79
+    },
+    {
+      "epoch": 0.14184397163120568,
+      "grad_norm": 0.675848662853241,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3053,
+      "step": 80
+    },
+    {
+      "epoch": 0.14361702127659576,
+      "grad_norm": 0.6196485161781311,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.2637,
+      "step": 81
+    },
+    {
+      "epoch": 0.14361702127659576,
+      "eval_loss": 0.24386928975582123,
+      "eval_runtime": 85.2732,
+      "eval_samples_per_second": 5.57,
+      "eval_steps_per_second": 0.704,
+      "step": 81
+    },
+    {
+      "epoch": 0.1453900709219858,
+      "grad_norm": 0.7320723533630371,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3557,
+      "step": 82
+    },
+    {
+      "epoch": 0.14716312056737588,
+      "grad_norm": 0.6170211434364319,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.288,
+      "step": 83
+    },
+    {
+      "epoch": 0.14893617021276595,
+      "grad_norm": 0.5411659479141235,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.269,
+      "step": 84
+    },
+    {
+      "epoch": 0.15070921985815602,
+      "grad_norm": 0.6507031321525574,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2579,
+      "step": 85
+    },
+    {
+      "epoch": 0.1524822695035461,
+      "grad_norm": 0.4847683608531952,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2108,
+      "step": 86
+    },
+    {
+      "epoch": 0.15425531914893617,
+      "grad_norm": 0.5241921544075012,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.2421,
+      "step": 87
+    },
+    {
+      "epoch": 0.15602836879432624,
+      "grad_norm": 0.5839644074440002,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2381,
+      "step": 88
+    },
+    {
+      "epoch": 0.15780141843971632,
+      "grad_norm": 0.5057505965232849,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.2041,
+      "step": 89
+    },
+    {
+      "epoch": 0.1595744680851064,
+      "grad_norm": 0.5602439045906067,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2442,
+      "step": 90
+    },
+    {
+      "epoch": 0.1595744680851064,
+      "eval_loss": 0.24139147996902466,
+      "eval_runtime": 85.2729,
+      "eval_samples_per_second": 5.57,
+      "eval_steps_per_second": 0.704,
+      "step": 90
+    },
+    {
+      "epoch": 0.16134751773049646,
+      "grad_norm": 0.7721632122993469,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2454,
+      "step": 91
+    },
+    {
+      "epoch": 0.16312056737588654,
+      "grad_norm": 0.7036444544792175,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.2381,
+      "step": 92
+    },
+    {
+      "epoch": 0.16489361702127658,
+      "grad_norm": 0.6270337104797363,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.2547,
+      "step": 93
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.4347127676010132,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.222,
+      "step": 94
+    },
+    {
+      "epoch": 0.16843971631205673,
+      "grad_norm": 0.5513346791267395,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2501,
+      "step": 95
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 0.5058043003082275,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.2783,
+      "step": 96
+    },
+    {
+      "epoch": 0.17198581560283688,
+      "grad_norm": 0.5748170018196106,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.2392,
+      "step": 97
+    },
+    {
+      "epoch": 0.17375886524822695,
+      "grad_norm": 0.6403087377548218,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.2768,
+      "step": 98
+    },
+    {
+      "epoch": 0.17553191489361702,
+      "grad_norm": 0.5376163125038147,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.2586,
+      "step": 99
+    },
+    {
+      "epoch": 0.17553191489361702,
+      "eval_loss": 0.24068014323711395,
+      "eval_runtime": 85.2941,
+      "eval_samples_per_second": 5.569,
+      "eval_steps_per_second": 0.703,
+      "step": 99
+    },
+    {
+      "epoch": 0.1773049645390071,
+      "grad_norm": 0.5339375138282776,
+      "learning_rate": 0.0,
+      "loss": 0.2779,
+      "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": 3.523180448710656e+16,
+  "total_flos": 4.642695731478528e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null