Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307545629ec129618d98019da41be60a2f7ae2d1ad5bc0b70b5bdcf58f2c1116
+oid sha256:1da99304ab0d1370b66253cd4a435982a0647af9e4cbd774976e00870847a97a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31fc52270abf3c5ddafe86ad540ab286b83b3e0882b73847adc9e6d29c52336f
+oid sha256:9c392657cc00b9ca45ad2f990b6e0d505d767f8c3e61e57e4406b5d5e945af0a
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7a2bf7701d3c3304a78ccedc5ee566cf4dfa08472396e1f78f2396dff5e956
+oid sha256:58ad183856ba988578b644aeb18cf4d203e3e879a77ec5aa8224d3f0713c373d
 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": 0.0062447960033305576,
+  "epoch": 0.00832639467110741,
   "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": 0.9089,
       "step": 75
+    },
+    {
+      "epoch": 0.006328059950041632,
+      "grad_norm": 0.5378401875495911,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.7044,
+      "step": 76
+    },
+    {
+      "epoch": 0.006411323896752706,
+      "grad_norm": 0.5078656673431396,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.7109,
+      "step": 77
+    },
+    {
+      "epoch": 0.00649458784346378,
+      "grad_norm": 0.7006959319114685,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.431,
+      "step": 78
+    },
+    {
+      "epoch": 0.006577851790174854,
+      "grad_norm": 0.5978702306747437,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.5518,
+      "step": 79
+    },
+    {
+      "epoch": 0.006661115736885929,
+      "grad_norm": 0.5336026549339294,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.55,
+      "step": 80
+    },
+    {
+      "epoch": 0.006744379683597003,
+      "grad_norm": 0.4496859312057495,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.6881,
+      "step": 81
+    },
+    {
+      "epoch": 0.006744379683597003,
+      "eval_loss": 0.607624351978302,
+      "eval_runtime": 1874.8035,
+      "eval_samples_per_second": 5.395,
+      "eval_steps_per_second": 0.675,
+      "step": 81
+    },
+    {
+      "epoch": 0.006827643630308077,
+      "grad_norm": 0.5448951125144958,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7178,
+      "step": 82
+    },
+    {
+      "epoch": 0.00691090757701915,
+      "grad_norm": 0.5171974301338196,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.7393,
+      "step": 83
+    },
+    {
+      "epoch": 0.0069941715237302245,
+      "grad_norm": 0.3583661615848541,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.5103,
+      "step": 84
+    },
+    {
+      "epoch": 0.007077435470441299,
+      "grad_norm": 0.5829033851623535,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6899,
+      "step": 85
+    },
+    {
+      "epoch": 0.007160699417152373,
+      "grad_norm": 0.5309457182884216,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6061,
+      "step": 86
+    },
+    {
+      "epoch": 0.007243963363863447,
+      "grad_norm": 0.8489606976509094,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.4233,
+      "step": 87
+    },
+    {
+      "epoch": 0.007327227310574521,
+      "grad_norm": 0.6375559568405151,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.6815,
+      "step": 88
+    },
+    {
+      "epoch": 0.0074104912572855956,
+      "grad_norm": 0.6630268096923828,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.6326,
+      "step": 89
+    },
+    {
+      "epoch": 0.00749375520399667,
+      "grad_norm": 0.45221108198165894,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.4865,
+      "step": 90
+    },
+    {
+      "epoch": 0.00749375520399667,
+      "eval_loss": 0.6059922575950623,
+      "eval_runtime": 1878.4027,
+      "eval_samples_per_second": 5.384,
+      "eval_steps_per_second": 0.673,
+      "step": 90
+    },
+    {
+      "epoch": 0.007577019150707744,
+      "grad_norm": 0.5124365091323853,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.5778,
+      "step": 91
+    },
+    {
+      "epoch": 0.007660283097418817,
+      "grad_norm": 0.8342736959457397,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.609,
+      "step": 92
+    },
+    {
+      "epoch": 0.0077435470441298915,
+      "grad_norm": 0.4861484467983246,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.4582,
+      "step": 93
+    },
+    {
+      "epoch": 0.007826810990840967,
+      "grad_norm": 0.4907625913619995,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.7756,
+      "step": 94
+    },
+    {
+      "epoch": 0.00791007493755204,
+      "grad_norm": 0.49000653624534607,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.4203,
+      "step": 95
+    },
+    {
+      "epoch": 0.007993338884263113,
+      "grad_norm": 0.6092959046363831,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.524,
+      "step": 96
+    },
+    {
+      "epoch": 0.008076602830974187,
+      "grad_norm": 0.5685826539993286,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.5168,
+      "step": 97
+    },
+    {
+      "epoch": 0.008159866777685262,
+      "grad_norm": 0.7407828569412231,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.7229,
+      "step": 98
+    },
+    {
+      "epoch": 0.008243130724396336,
+      "grad_norm": 0.5559101104736328,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.8751,
+      "step": 99
+    },
+    {
+      "epoch": 0.008243130724396336,
+      "eval_loss": 0.6056489944458008,
+      "eval_runtime": 1877.0661,
+      "eval_samples_per_second": 5.388,
+      "eval_steps_per_second": 0.674,
+      "step": 99
+    },
+    {
+      "epoch": 0.00832639467110741,
+      "grad_norm": 0.5634000301361084,
+      "learning_rate": 0.0,
+      "loss": 0.3409,
+      "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": 8.693387637030912e+16,
+  "total_flos": 1.1602201751322624e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null