Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13946f5153cfffe605d7dada89e9524858029bfe128cea35d2992dad8954cf85
+oid sha256:a614743403065c315f5fceef1afeee4e4aa0ef8b2f4ddf3cda91186f23b49d14
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ba03b6f01f56bcce4c761c15a6d6bd51867f7176a001d8afc606ab93b9274c
+oid sha256:9b9a791a1c45c8b7f6a81b35397a3fa2e87d619de92e1101ed5783abfcc5ac97
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4e42707bff3a01dd441022647b82d0d244a8f2409373d258e9184fc37cc91af
+oid sha256:71fc6bba3f242e88b85f33651f56380c544ca14fb09dd639b0ec5276ac7956e5
 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": 0.12468827930174564,
+  "epoch": 0.1662510390689942,
   "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": 11.7533,
       "step": 75
+    },
+    {
+      "epoch": 0.12635078969243557,
+      "grad_norm": 0.0871320515871048,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 11.759,
+      "step": 76
+    },
+    {
+      "epoch": 0.12801330008312553,
+      "grad_norm": 0.09251094609498978,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 11.7559,
+      "step": 77
+    },
+    {
+      "epoch": 0.12967581047381546,
+      "grad_norm": 0.08235142379999161,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 11.7498,
+      "step": 78
+    },
+    {
+      "epoch": 0.1313383208645054,
+      "grad_norm": 0.08003734797239304,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 11.7497,
+      "step": 79
+    },
+    {
+      "epoch": 0.13300083125519535,
+      "grad_norm": 0.06140708178281784,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 11.7542,
+      "step": 80
+    },
+    {
+      "epoch": 0.13466334164588528,
+      "grad_norm": 0.06575233489274979,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 11.7592,
+      "step": 81
+    },
+    {
+      "epoch": 0.13466334164588528,
+      "eval_loss": 11.754680633544922,
+      "eval_runtime": 10.852,
+      "eval_samples_per_second": 46.719,
+      "eval_steps_per_second": 5.898,
+      "step": 81
+    },
+    {
+      "epoch": 0.13632585203657524,
+      "grad_norm": 0.06072350591421127,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.7557,
+      "step": 82
+    },
+    {
+      "epoch": 0.13798836242726517,
+      "grad_norm": 0.07811221480369568,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 11.7565,
+      "step": 83
+    },
+    {
+      "epoch": 0.1396508728179551,
+      "grad_norm": 0.09204588085412979,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 11.7634,
+      "step": 84
+    },
+    {
+      "epoch": 0.14131338320864506,
+      "grad_norm": 0.07153452932834625,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.7585,
+      "step": 85
+    },
+    {
+      "epoch": 0.142975893599335,
+      "grad_norm": 0.08605170249938965,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 11.7568,
+      "step": 86
+    },
+    {
+      "epoch": 0.14463840399002495,
+      "grad_norm": 0.08406588435173035,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 11.7558,
+      "step": 87
+    },
+    {
+      "epoch": 0.14630091438071488,
+      "grad_norm": 0.07880561798810959,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 11.7556,
+      "step": 88
+    },
+    {
+      "epoch": 0.1479634247714048,
+      "grad_norm": 0.05538419634103775,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 11.7538,
+      "step": 89
+    },
+    {
+      "epoch": 0.14962593516209477,
+      "grad_norm": 0.07911358028650284,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 11.7514,
+      "step": 90
+    },
+    {
+      "epoch": 0.14962593516209477,
+      "eval_loss": 11.754559516906738,
+      "eval_runtime": 10.6897,
+      "eval_samples_per_second": 47.429,
+      "eval_steps_per_second": 5.987,
+      "step": 90
+    },
+    {
+      "epoch": 0.1512884455527847,
+      "grad_norm": 0.07232284545898438,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.7607,
+      "step": 91
+    },
+    {
+      "epoch": 0.15295095594347466,
+      "grad_norm": 0.09192491322755814,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 11.7541,
+      "step": 92
+    },
+    {
+      "epoch": 0.1546134663341646,
+      "grad_norm": 0.07534570246934891,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 11.7526,
+      "step": 93
+    },
+    {
+      "epoch": 0.15627597672485452,
+      "grad_norm": 0.09265202283859253,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 11.757,
+      "step": 94
+    },
+    {
+      "epoch": 0.15793848711554448,
+      "grad_norm": 0.10842297971248627,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 11.7572,
+      "step": 95
+    },
+    {
+      "epoch": 0.1596009975062344,
+      "grad_norm": 0.06330010294914246,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 11.7508,
+      "step": 96
+    },
+    {
+      "epoch": 0.16126350789692437,
+      "grad_norm": 0.08400006592273712,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 11.7589,
+      "step": 97
+    },
+    {
+      "epoch": 0.1629260182876143,
+      "grad_norm": 0.08327385783195496,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 11.7501,
+      "step": 98
+    },
+    {
+      "epoch": 0.16458852867830423,
+      "grad_norm": 0.08100760728120804,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 11.7602,
+      "step": 99
+    },
+    {
+      "epoch": 0.16458852867830423,
+      "eval_loss": 11.754537582397461,
+      "eval_runtime": 10.6869,
+      "eval_samples_per_second": 47.441,
+      "eval_steps_per_second": 5.989,
+      "step": 99
+    },
+    {
+      "epoch": 0.1662510390689942,
+      "grad_norm": 0.07855262607336044,
+      "learning_rate": 0.0,
+      "loss": 11.7542,
+      "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": 15277503283200.0,
+  "total_flos": 20370004377600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null