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:cecd0404d3ccbc9c91770deaff7eb29aa0825de48fbcf2e4fcc6e30508522788
+oid sha256:e7faccbe92b97a78352817459a6e6c751a2c97add7b4bbf92165f17954bea39f
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de2aeb0d028d81b0e5442795604c2213dcfe5bf667d91f861aa2933a5ac647c7
+oid sha256:d2d08cc8b2b170fe3c717520be5b07b8dbb34fa15defe72be65a3f00c2de9d67
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c296ac81d2bf3d1344e432b93d2183f1d83398c4d0023c461042136570fadac1
+oid sha256:e3015bc477bf00067a286005ca1f0c55ee6265bf3c9e632bcf35614434263892
 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": 0.03837298541826554,
+  "epoch": 0.05116398055768739,
   "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": 1.2363,
       "step": 75
+    },
+    {
+      "epoch": 0.038884625223842416,
+      "grad_norm": 2.252734422683716,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.9702,
+      "step": 76
+    },
+    {
+      "epoch": 0.039396265029419286,
+      "grad_norm": 1.5854482650756836,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.4033,
+      "step": 77
+    },
+    {
+      "epoch": 0.039907904834996163,
+      "grad_norm": 2.2333011627197266,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.3619,
+      "step": 78
+    },
+    {
+      "epoch": 0.040419544640573034,
+      "grad_norm": 2.2637572288513184,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.3294,
+      "step": 79
+    },
+    {
+      "epoch": 0.04093118444614991,
+      "grad_norm": 2.184448003768921,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.3759,
+      "step": 80
+    },
+    {
+      "epoch": 0.04144282425172678,
+      "grad_norm": 2.1181156635284424,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.4547,
+      "step": 81
+    },
+    {
+      "epoch": 0.04144282425172678,
+      "eval_loss": 0.6984646916389465,
+      "eval_runtime": 274.0143,
+      "eval_samples_per_second": 6.007,
+      "eval_steps_per_second": 0.752,
+      "step": 81
+    },
+    {
+      "epoch": 0.04195446405730366,
+      "grad_norm": 2.124769926071167,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.711,
+      "step": 82
+    },
+    {
+      "epoch": 0.04246610386288053,
+      "grad_norm": 2.768644332885742,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.4417,
+      "step": 83
+    },
+    {
+      "epoch": 0.042977743668457406,
+      "grad_norm": 1.6614168882369995,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.1462,
+      "step": 84
+    },
+    {
+      "epoch": 0.04348938347403428,
+      "grad_norm": 1.6592438220977783,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1821,
+      "step": 85
+    },
+    {
+      "epoch": 0.044001023279611154,
+      "grad_norm": 2.4975907802581787,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.5,
+      "step": 86
+    },
+    {
+      "epoch": 0.044512663085188024,
+      "grad_norm": 1.9415825605392456,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.3181,
+      "step": 87
+    },
+    {
+      "epoch": 0.0450243028907649,
+      "grad_norm": 1.8416827917099,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.1157,
+      "step": 88
+    },
+    {
+      "epoch": 0.04553594269634178,
+      "grad_norm": 2.9629881381988525,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.6228,
+      "step": 89
+    },
+    {
+      "epoch": 0.04604758250191865,
+      "grad_norm": 1.538602590560913,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.2217,
+      "step": 90
+    },
+    {
+      "epoch": 0.04604758250191865,
+      "eval_loss": 0.6968083381652832,
+      "eval_runtime": 274.0049,
+      "eval_samples_per_second": 6.007,
+      "eval_steps_per_second": 0.752,
+      "step": 90
+    },
+    {
+      "epoch": 0.046559222307495526,
+      "grad_norm": 3.1427130699157715,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.4783,
+      "step": 91
+    },
+    {
+      "epoch": 0.0470708621130724,
+      "grad_norm": 1.9339940547943115,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3989,
+      "step": 92
+    },
+    {
+      "epoch": 0.047582501918649274,
+      "grad_norm": 1.509247899055481,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.277,
+      "step": 93
+    },
+    {
+      "epoch": 0.048094141724226144,
+      "grad_norm": 2.101160764694214,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.129,
+      "step": 94
+    },
+    {
+      "epoch": 0.04860578152980302,
+      "grad_norm": 1.8684135675430298,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.397,
+      "step": 95
+    },
+    {
+      "epoch": 0.04911742133537989,
+      "grad_norm": 2.9883639812469482,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.4069,
+      "step": 96
+    },
+    {
+      "epoch": 0.04962906114095677,
+      "grad_norm": 2.2074315547943115,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.4236,
+      "step": 97
+    },
+    {
+      "epoch": 0.05014070094653364,
+      "grad_norm": 2.8094723224639893,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4329,
+      "step": 98
+    },
+    {
+      "epoch": 0.05065234075211052,
+      "grad_norm": 1.6626664400100708,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.1333,
+      "step": 99
+    },
+    {
+      "epoch": 0.05065234075211052,
+      "eval_loss": 0.6963222026824951,
+      "eval_runtime": 274.0109,
+      "eval_samples_per_second": 6.007,
+      "eval_steps_per_second": 0.752,
+      "step": 99
+    },
+    {
+      "epoch": 0.05116398055768739,
+      "grad_norm": 2.4238545894622803,
+      "learning_rate": 0.0,
+      "loss": 1.3018,
+      "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": 9.8390740303872e+16,
+  "total_flos": 1.313992467283968e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null