Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23162cc6fe68e94a782351200bc4f582fe7121e46af4bb6d156ad54b5bc681f6
+oid sha256:72a714fb97119ff4d4d34cca32995b0690dc2c3b7e2076676dc066a7c175bb01
 size 2269195160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a02de5b801b49a246b81ce16c11676fe0264bb369a12ba5f375a1b3f54c3e5a
+oid sha256:7e2d613453598e48242f3a055dece7b4f0614504548d4601b7c52f6546b73658
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ade794c9ae8f60a23a4e2303e71e00584e515f475138cbbe69c00a1df0a54eb
+oid sha256:2641fe94f6f5285a893d26b6a83b6bc1718c94cdba5b09f9fe77818d5a69d3a2
 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": 0.04324012683770539,
+  "epoch": 0.057653502450273855,
   "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": 0.6129,
       "step": 75
+    },
+    {
+      "epoch": 0.04381666186220813,
+      "grad_norm": 0.2374476194381714,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.5682,
+      "step": 76
+    },
+    {
+      "epoch": 0.04439319688671087,
+      "grad_norm": 0.25753456354141235,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.5805,
+      "step": 77
+    },
+    {
+      "epoch": 0.044969731911213603,
+      "grad_norm": 0.2336205244064331,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.5953,
+      "step": 78
+    },
+    {
+      "epoch": 0.04554626693571635,
+      "grad_norm": 0.30540937185287476,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.6858,
+      "step": 79
+    },
+    {
+      "epoch": 0.04612280196021908,
+      "grad_norm": 0.2815301716327667,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.8478,
+      "step": 80
+    },
+    {
+      "epoch": 0.04669933698472182,
+      "grad_norm": 0.23606453835964203,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.726,
+      "step": 81
+    },
+    {
+      "epoch": 0.04669933698472182,
+      "eval_loss": 0.7066140174865723,
+      "eval_runtime": 364.442,
+      "eval_samples_per_second": 4.009,
+      "eval_steps_per_second": 0.502,
+      "step": 81
+    },
+    {
+      "epoch": 0.04727587200922456,
+      "grad_norm": 0.264173299074173,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7206,
+      "step": 82
+    },
+    {
+      "epoch": 0.0478524070337273,
+      "grad_norm": 0.259550541639328,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.6457,
+      "step": 83
+    },
+    {
+      "epoch": 0.048428942058230035,
+      "grad_norm": 0.25564852356910706,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.5842,
+      "step": 84
+    },
+    {
+      "epoch": 0.04900547708273278,
+      "grad_norm": 0.2507416307926178,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6966,
+      "step": 85
+    },
+    {
+      "epoch": 0.049582012107235514,
+      "grad_norm": 0.22969740629196167,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6032,
+      "step": 86
+    },
+    {
+      "epoch": 0.05015854713173825,
+      "grad_norm": 0.2480449229478836,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.6458,
+      "step": 87
+    },
+    {
+      "epoch": 0.05073508215624099,
+      "grad_norm": 0.24502995610237122,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.6293,
+      "step": 88
+    },
+    {
+      "epoch": 0.05131161718074373,
+      "grad_norm": 0.2702799141407013,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.5813,
+      "step": 89
+    },
+    {
+      "epoch": 0.051888152205246466,
+      "grad_norm": 0.2640494704246521,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8735,
+      "step": 90
+    },
+    {
+      "epoch": 0.051888152205246466,
+      "eval_loss": 0.7058947682380676,
+      "eval_runtime": 364.3775,
+      "eval_samples_per_second": 4.01,
+      "eval_steps_per_second": 0.502,
+      "step": 90
+    },
+    {
+      "epoch": 0.05246468722974921,
+      "grad_norm": 0.23920738697052002,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.6639,
+      "step": 91
+    },
+    {
+      "epoch": 0.053041222254251945,
+      "grad_norm": 0.2456059753894806,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.694,
+      "step": 92
+    },
+    {
+      "epoch": 0.05361775727875468,
+      "grad_norm": 0.2731674909591675,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.8057,
+      "step": 93
+    },
+    {
+      "epoch": 0.054194292303257424,
+      "grad_norm": 0.2577863931655884,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.5574,
+      "step": 94
+    },
+    {
+      "epoch": 0.05477082732776016,
+      "grad_norm": 0.22670993208885193,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.6183,
+      "step": 95
+    },
+    {
+      "epoch": 0.0553473623522629,
+      "grad_norm": 0.2563611567020416,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.7729,
+      "step": 96
+    },
+    {
+      "epoch": 0.05592389737676564,
+      "grad_norm": 0.26697584986686707,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.8254,
+      "step": 97
+    },
+    {
+      "epoch": 0.056500432401268376,
+      "grad_norm": 0.23468847572803497,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.7771,
+      "step": 98
+    },
+    {
+      "epoch": 0.05707696742577112,
+      "grad_norm": 0.2329586148262024,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.6909,
+      "step": 99
+    },
+    {
+      "epoch": 0.05707696742577112,
+      "eval_loss": 0.7057739496231079,
+      "eval_runtime": 364.6184,
+      "eval_samples_per_second": 4.007,
+      "eval_steps_per_second": 0.502,
+      "step": 99
+    },
+    {
+      "epoch": 0.057653502450273855,
+      "grad_norm": 0.28871598839759827,
+      "learning_rate": 0.0,
+      "loss": 0.7902,
+      "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": 1.112831529320448e+17,
+  "total_flos": 1.483775372427264e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null