Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7db897091c403983d5b73a85d76a376de57da2de2b0164b135b9f73457ca9266
+oid sha256:bd97239a7926151915a957e7932bbf17f97aca9bca5bb763db26b31d3339b199
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e244b84c58e98ccdab7fdf65ea43314d196298f5e689bbc64f991c1466162c3f
+oid sha256:19748b414d4016d8e2592e5a3bd7f783073e9ba8868e4aea49b006e829b7bf09
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
+oid sha256:7d54c917256fd085e20e49081e8a953eee303e2ee34f089b2a4112eb45771b1c
 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": 0.22123893805309736,
+  "epoch": 0.2949852507374631,
   "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": 2.3507,
       "step": 75
+    },
+    {
+      "epoch": 0.22418879056047197,
+      "grad_norm": 4.007279872894287,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.1104,
+      "step": 76
+    },
+    {
+      "epoch": 0.22713864306784662,
+      "grad_norm": 1.9368032217025757,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.6227,
+      "step": 77
+    },
+    {
+      "epoch": 0.23008849557522124,
+      "grad_norm": 2.9845495223999023,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.7561,
+      "step": 78
+    },
+    {
+      "epoch": 0.23303834808259588,
+      "grad_norm": 2.2668330669403076,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.015,
+      "step": 79
+    },
+    {
+      "epoch": 0.2359882005899705,
+      "grad_norm": 1.9236528873443604,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.1305,
+      "step": 80
+    },
+    {
+      "epoch": 0.23893805309734514,
+      "grad_norm": 2.2773380279541016,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.778,
+      "step": 81
+    },
+    {
+      "epoch": 0.23893805309734514,
+      "eval_loss": 0.92861008644104,
+      "eval_runtime": 44.4064,
+      "eval_samples_per_second": 6.441,
+      "eval_steps_per_second": 0.811,
+      "step": 81
+    },
+    {
+      "epoch": 0.24188790560471976,
+      "grad_norm": 1.7460155487060547,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.777,
+      "step": 82
+    },
+    {
+      "epoch": 0.2448377581120944,
+      "grad_norm": 2.7454729080200195,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.1967,
+      "step": 83
+    },
+    {
+      "epoch": 0.24778761061946902,
+      "grad_norm": 2.0686800479888916,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.6214,
+      "step": 84
+    },
+    {
+      "epoch": 0.25073746312684364,
+      "grad_norm": 2.3937289714813232,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.7947,
+      "step": 85
+    },
+    {
+      "epoch": 0.2536873156342183,
+      "grad_norm": 2.584099054336548,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.4677,
+      "step": 86
+    },
+    {
+      "epoch": 0.25663716814159293,
+      "grad_norm": 3.2739224433898926,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.9313,
+      "step": 87
+    },
+    {
+      "epoch": 0.25958702064896755,
+      "grad_norm": 2.9258463382720947,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6279,
+      "step": 88
+    },
+    {
+      "epoch": 0.26253687315634217,
+      "grad_norm": 2.1165103912353516,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.1038,
+      "step": 89
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "grad_norm": 1.7193412780761719,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.9531,
+      "step": 90
+    },
+    {
+      "epoch": 0.26548672566371684,
+      "eval_loss": 0.928329586982727,
+      "eval_runtime": 44.365,
+      "eval_samples_per_second": 6.447,
+      "eval_steps_per_second": 0.811,
+      "step": 90
+    },
+    {
+      "epoch": 0.26843657817109146,
+      "grad_norm": 3.0313870906829834,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.409,
+      "step": 91
+    },
+    {
+      "epoch": 0.2713864306784661,
+      "grad_norm": 2.6027047634124756,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.8437,
+      "step": 92
+    },
+    {
+      "epoch": 0.2743362831858407,
+      "grad_norm": 1.7454715967178345,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.4698,
+      "step": 93
+    },
+    {
+      "epoch": 0.27728613569321536,
+      "grad_norm": 4.085173606872559,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5345,
+      "step": 94
+    },
+    {
+      "epoch": 0.28023598820059,
+      "grad_norm": 1.4964895248413086,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.0551,
+      "step": 95
+    },
+    {
+      "epoch": 0.2831858407079646,
+      "grad_norm": 2.6940832138061523,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.3975,
+      "step": 96
+    },
+    {
+      "epoch": 0.2861356932153392,
+      "grad_norm": 2.0973100662231445,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.1289,
+      "step": 97
+    },
+    {
+      "epoch": 0.2890855457227139,
+      "grad_norm": 2.0837435722351074,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.0609,
+      "step": 98
+    },
+    {
+      "epoch": 0.2920353982300885,
+      "grad_norm": 2.236985921859741,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.6664,
+      "step": 99
+    },
+    {
+      "epoch": 0.2920353982300885,
+      "eval_loss": 0.9275940656661987,
+      "eval_runtime": 44.3545,
+      "eval_samples_per_second": 6.448,
+      "eval_steps_per_second": 0.812,
+      "step": 99
+    },
+    {
+      "epoch": 0.2949852507374631,
+      "grad_norm": 2.534641981124878,
+      "learning_rate": 0.0,
+      "loss": 1.5521,
+      "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": 9.521684545536e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null