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:f80f31c66cfcd979223772a01c415ed3429014477ba1eda834586f3faaff1fda
+oid sha256:161278bf0507c5ef407d5a5a56fc962f7f149a22560809f5bf349854a9da2fe9
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040d965d53986f166048d2421e1f5dd743a1fdf0c7dabde55d380ddb2e39c887
+oid sha256:10ce582d3f85885ce77e838bb19d17f641943c66bb70c811d766378f0639079f
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997b37e8e4d4313266e5aafe8f4d418b086633a9c94b4c13db86ae839aa09b15
+oid sha256:9246553064bea11894d1cdc342a12358c62b3d7caceee2321170ee68aed86db4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb167787cdd9594eed637547cf4a56f4a4d8ea359757a120c76bb5d91190782
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0380952380952381,
+  "epoch": 0.050793650793650794,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 4.021,
       "eval_steps_per_second": 2.013,
       "step": 75
+    },
+    {
+      "epoch": 0.038603174603174605,
+      "grad_norm": 0.28713932633399963,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.5865,
+      "step": 76
+    },
+    {
+      "epoch": 0.03911111111111111,
+      "grad_norm": 0.26906633377075195,
+      "learning_rate": 3.053416295410026e-05,
+      "loss": 1.1854,
+      "step": 77
+    },
+    {
+      "epoch": 0.039619047619047616,
+      "grad_norm": 0.4078941345214844,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 1.2432,
+      "step": 78
+    },
+    {
+      "epoch": 0.04012698412698413,
+      "grad_norm": 0.32490774989128113,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 1.4465,
+      "step": 79
+    },
+    {
+      "epoch": 0.040634920634920635,
+      "grad_norm": 0.30676373839378357,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 1.4783,
+      "step": 80
+    },
+    {
+      "epoch": 0.04114285714285714,
+      "grad_norm": 0.3845832943916321,
+      "learning_rate": 2.119892463932781e-05,
+      "loss": 1.3254,
+      "step": 81
+    },
+    {
+      "epoch": 0.041650793650793654,
+      "grad_norm": 0.41841885447502136,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.756,
+      "step": 82
+    },
+    {
+      "epoch": 0.04215873015873016,
+      "grad_norm": 0.26209527254104614,
+      "learning_rate": 1.7096242744495837e-05,
+      "loss": 1.1009,
+      "step": 83
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 0.4069371819496155,
+      "learning_rate": 1.5195190384357404e-05,
+      "loss": 1.3217,
+      "step": 84
+    },
+    {
+      "epoch": 0.04317460317460318,
+      "grad_norm": 0.29204556345939636,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.437,
+      "step": 85
+    },
+    {
+      "epoch": 0.043682539682539684,
+      "grad_norm": 0.36702778935432434,
+      "learning_rate": 1.1705240714107302e-05,
+      "loss": 1.2403,
+      "step": 86
+    },
+    {
+      "epoch": 0.04419047619047619,
+      "grad_norm": 0.2762695252895355,
+      "learning_rate": 1.0120595370083318e-05,
+      "loss": 1.2892,
+      "step": 87
+    },
+    {
+      "epoch": 0.044698412698412696,
+      "grad_norm": 0.30418360233306885,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.4427,
+      "step": 88
+    },
+    {
+      "epoch": 0.04520634920634921,
+      "grad_norm": 0.30312514305114746,
+      "learning_rate": 7.281614543321269e-06,
+      "loss": 1.4674,
+      "step": 89
+    },
+    {
+      "epoch": 0.045714285714285714,
+      "grad_norm": 0.36299508810043335,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 1.2849,
+      "step": 90
+    },
+    {
+      "epoch": 0.04622222222222222,
+      "grad_norm": 0.3190608024597168,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.3682,
+      "step": 91
+    },
+    {
+      "epoch": 0.04673015873015873,
+      "grad_norm": 0.27337679266929626,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 1.2428,
+      "step": 92
+    },
+    {
+      "epoch": 0.04723809523809524,
+      "grad_norm": 0.3793995976448059,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 1.9111,
+      "step": 93
+    },
+    {
+      "epoch": 0.047746031746031745,
+      "grad_norm": 0.3148786723613739,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.2274,
+      "step": 94
+    },
+    {
+      "epoch": 0.04825396825396826,
+      "grad_norm": 0.487860769033432,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 1.401,
+      "step": 95
+    },
+    {
+      "epoch": 0.04876190476190476,
+      "grad_norm": 0.2578515410423279,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 1.0545,
+      "step": 96
+    },
+    {
+      "epoch": 0.04926984126984127,
+      "grad_norm": 0.30165234208106995,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 1.0555,
+      "step": 97
+    },
+    {
+      "epoch": 0.049777777777777775,
+      "grad_norm": 0.27550289034843445,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 1.542,
+      "step": 98
+    },
+    {
+      "epoch": 0.05028571428571429,
+      "grad_norm": 0.21497561037540436,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 1.19,
+      "step": 99
+    },
+    {
+      "epoch": 0.050793650793650794,
+      "grad_norm": 0.5045850872993469,
+      "learning_rate": 0.0,
+      "loss": 1.5234,
+      "step": 100
+    },
+    {
+      "epoch": 0.050793650793650794,
+      "eval_loss": 1.4889129400253296,
+      "eval_runtime": 206.2008,
+      "eval_samples_per_second": 4.02,
+      "eval_steps_per_second": 2.013,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -578,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.88845956923392e+16,
+  "total_flos": 1.318461275897856e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null