Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5268267aef0761bfab8b7d829175394952e3951230ed288abc7c95de90bd30a9
+oid sha256:4d3423f5e35412d7b56c5e0f21f44b76ae3a369be7648063ba51b7868dd22537
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35afe559fc0676b1b3388bdb446a13339c8d558a62fb49fb20fc8f5efc866485
+oid sha256:c48edb0ce1f17ba6fc6cb013a9d00586b07a4d7fd7383e38d2b763f318465747
 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": 0.0014038108785984352,
+  "epoch": 0.001871747838131247,
   "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": 10.2983,
       "step": 75
+    },
+    {
+      "epoch": 0.0014225283569797478,
+      "grad_norm": 0.314072847366333,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.304,
+      "step": 76
+    },
+    {
+      "epoch": 0.0014412458353610601,
+      "grad_norm": 0.3194397985935211,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.2998,
+      "step": 77
+    },
+    {
+      "epoch": 0.0014599633137423727,
+      "grad_norm": 0.3076654076576233,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3069,
+      "step": 78
+    },
+    {
+      "epoch": 0.001478680792123685,
+      "grad_norm": 0.29715707898139954,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.2996,
+      "step": 79
+    },
+    {
+      "epoch": 0.0014973982705049976,
+      "grad_norm": 0.3068283200263977,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.2932,
+      "step": 80
+    },
+    {
+      "epoch": 0.0015161157488863101,
+      "grad_norm": 0.2767265737056732,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.2972,
+      "step": 81
+    },
+    {
+      "epoch": 0.0015161157488863101,
+      "eval_loss": 10.300215721130371,
+      "eval_runtime": 299.1587,
+      "eval_samples_per_second": 150.388,
+      "eval_steps_per_second": 18.799,
+      "step": 81
+    },
+    {
+      "epoch": 0.0015348332272676225,
+      "grad_norm": 0.2779734134674072,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.2977,
+      "step": 82
+    },
+    {
+      "epoch": 0.001553550705648935,
+      "grad_norm": 0.31111666560173035,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.2987,
+      "step": 83
+    },
+    {
+      "epoch": 0.0015722681840302474,
+      "grad_norm": 0.3041585385799408,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.2968,
+      "step": 84
+    },
+    {
+      "epoch": 0.00159098566241156,
+      "grad_norm": 0.28511694073677063,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.2999,
+      "step": 85
+    },
+    {
+      "epoch": 0.0016097031407928725,
+      "grad_norm": 0.28556522727012634,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.2992,
+      "step": 86
+    },
+    {
+      "epoch": 0.0016284206191741848,
+      "grad_norm": 0.3389633297920227,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.2974,
+      "step": 87
+    },
+    {
+      "epoch": 0.0016471380975554973,
+      "grad_norm": 0.28096240758895874,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.2994,
+      "step": 88
+    },
+    {
+      "epoch": 0.0016658555759368097,
+      "grad_norm": 0.3122832477092743,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3047,
+      "step": 89
+    },
+    {
+      "epoch": 0.0016845730543181222,
+      "grad_norm": 0.3065173029899597,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.2971,
+      "step": 90
+    },
+    {
+      "epoch": 0.0016845730543181222,
+      "eval_loss": 10.29946231842041,
+      "eval_runtime": 299.883,
+      "eval_samples_per_second": 150.025,
+      "eval_steps_per_second": 18.754,
+      "step": 90
+    },
+    {
+      "epoch": 0.0017032905326994348,
+      "grad_norm": 0.3437938392162323,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.2954,
+      "step": 91
+    },
+    {
+      "epoch": 0.0017220080110807471,
+      "grad_norm": 0.2817475199699402,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3033,
+      "step": 92
+    },
+    {
+      "epoch": 0.0017407254894620597,
+      "grad_norm": 0.32707810401916504,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3018,
+      "step": 93
+    },
+    {
+      "epoch": 0.0017594429678433722,
+      "grad_norm": 0.2986222505569458,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3012,
+      "step": 94
+    },
+    {
+      "epoch": 0.0017781604462246846,
+      "grad_norm": 0.2933776378631592,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.2931,
+      "step": 95
+    },
+    {
+      "epoch": 0.0017968779246059971,
+      "grad_norm": 0.28214213252067566,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.2952,
+      "step": 96
+    },
+    {
+      "epoch": 0.0018155954029873095,
+      "grad_norm": 0.3439221680164337,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.2972,
+      "step": 97
+    },
+    {
+      "epoch": 0.001834312881368622,
+      "grad_norm": 0.3103925585746765,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3049,
+      "step": 98
+    },
+    {
+      "epoch": 0.0018530303597499346,
+      "grad_norm": 0.3452966809272766,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.2984,
+      "step": 99
+    },
+    {
+      "epoch": 0.0018530303597499346,
+      "eval_loss": 10.299317359924316,
+      "eval_runtime": 299.8349,
+      "eval_samples_per_second": 150.049,
+      "eval_steps_per_second": 18.757,
+      "step": 99
+    },
+    {
+      "epoch": 0.001871747838131247,
+      "grad_norm": 0.34136733412742615,
+      "learning_rate": 0.0,
+      "loss": 10.2995,
+      "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": 3922683494400.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null