Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f823fa41edaf31301e81f880bbcd7ccc4788469933682fd0d660a6338f3b11
+oid sha256:4e666345555d573a11235fe47c898e15614d912a5b2c761f0a767a7ec58ba1d9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53bc9ac2529c64930a85cc4234a6bad34f2a1bcc5235a9ad9b50067bc6d3c97a
+oid sha256:96411806602b066fbf41e5df2e80f284672015ffc7173933a9aab0ba3639a164
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a46df28312037471585ba42c2ee255b9684e3686b742e4a58dc53096d0bb825
+oid sha256:dcba896448d1af3d7d8067246c5d38d7235050ee234bb504037a4c6185e7fa30
 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": 0.015563394895206474,
+  "epoch": 0.020751193193608634,
   "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": 1.7002,
       "step": 75
+    },
+    {
+      "epoch": 0.01577090682714256,
+      "grad_norm": 1.1597203016281128,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.5769,
+      "step": 76
+    },
+    {
+      "epoch": 0.01597841875907865,
+      "grad_norm": 1.0011721849441528,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.6495,
+      "step": 77
+    },
+    {
+      "epoch": 0.016185930691014733,
+      "grad_norm": 0.9478533864021301,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.5925,
+      "step": 78
+    },
+    {
+      "epoch": 0.01639344262295082,
+      "grad_norm": 0.9030246734619141,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.344,
+      "step": 79
+    },
+    {
+      "epoch": 0.016600954554886905,
+      "grad_norm": 0.9802048802375793,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.565,
+      "step": 80
+    },
+    {
+      "epoch": 0.016808466486822993,
+      "grad_norm": 0.9481618404388428,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.5097,
+      "step": 81
+    },
+    {
+      "epoch": 0.016808466486822993,
+      "eval_loss": 1.5992255210876465,
+      "eval_runtime": 236.6548,
+      "eval_samples_per_second": 17.147,
+      "eval_steps_per_second": 2.147,
+      "step": 81
+    },
+    {
+      "epoch": 0.017015978418759077,
+      "grad_norm": 0.9746353626251221,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6898,
+      "step": 82
+    },
+    {
+      "epoch": 0.017223490350695165,
+      "grad_norm": 0.8424410223960876,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.635,
+      "step": 83
+    },
+    {
+      "epoch": 0.017431002282631253,
+      "grad_norm": 0.9099277257919312,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.6312,
+      "step": 84
+    },
+    {
+      "epoch": 0.017638514214567337,
+      "grad_norm": 1.0718952417373657,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4818,
+      "step": 85
+    },
+    {
+      "epoch": 0.017846026146503425,
+      "grad_norm": 0.802363932132721,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0126,
+      "step": 86
+    },
+    {
+      "epoch": 0.01805353807843951,
+      "grad_norm": 0.9490446448326111,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.5363,
+      "step": 87
+    },
+    {
+      "epoch": 0.018261050010375597,
+      "grad_norm": 1.1205114126205444,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6728,
+      "step": 88
+    },
+    {
+      "epoch": 0.01846856194231168,
+      "grad_norm": 0.920365035533905,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.4411,
+      "step": 89
+    },
+    {
+      "epoch": 0.01867607387424777,
+      "grad_norm": 1.0277124643325806,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.6717,
+      "step": 90
+    },
+    {
+      "epoch": 0.01867607387424777,
+      "eval_loss": 1.5978589057922363,
+      "eval_runtime": 236.7157,
+      "eval_samples_per_second": 17.143,
+      "eval_steps_per_second": 2.146,
+      "step": 90
+    },
+    {
+      "epoch": 0.018883585806183857,
+      "grad_norm": 0.8812714219093323,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.5921,
+      "step": 91
+    },
+    {
+      "epoch": 0.01909109773811994,
+      "grad_norm": 0.7979960441589355,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.548,
+      "step": 92
+    },
+    {
+      "epoch": 0.01929860967005603,
+      "grad_norm": 0.9867696166038513,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.5016,
+      "step": 93
+    },
+    {
+      "epoch": 0.019506121601992114,
+      "grad_norm": 1.1134464740753174,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.4178,
+      "step": 94
+    },
+    {
+      "epoch": 0.0197136335339282,
+      "grad_norm": 0.9245745539665222,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.5979,
+      "step": 95
+    },
+    {
+      "epoch": 0.019921145465864286,
+      "grad_norm": 0.90775066614151,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.4747,
+      "step": 96
+    },
+    {
+      "epoch": 0.020128657397800374,
+      "grad_norm": 0.845889151096344,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.4275,
+      "step": 97
+    },
+    {
+      "epoch": 0.02033616932973646,
+      "grad_norm": 1.0823585987091064,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.5404,
+      "step": 98
+    },
+    {
+      "epoch": 0.020543681261672546,
+      "grad_norm": 0.9024697542190552,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.7078,
+      "step": 99
+    },
+    {
+      "epoch": 0.020543681261672546,
+      "eval_loss": 1.5974575281143188,
+      "eval_runtime": 236.5477,
+      "eval_samples_per_second": 17.155,
+      "eval_steps_per_second": 2.148,
+      "step": 99
+    },
+    {
+      "epoch": 0.020751193193608634,
+      "grad_norm": 1.1790575981140137,
+      "learning_rate": 0.0,
+      "loss": 1.6402,
+      "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": 6.120570089373696e+16,
+  "total_flos": 8.19785448334295e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null