Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:653def3a56a7c9abff698f1a3bc2c10eb7d81f853a5956440e2e32fa9f9ded1d
+oid sha256:5fcf1bc07f8764d10d33f7b7491fa834716ea8e05032d047b527acfbe280f109
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591be042cc141565d32c5a86f7b7423c0b7b2686a31628fedfd43bd0d9414cbf
+oid sha256:ebc820c9d264b28c19aa7faf68343b092e839127c824aef5a18f49dba8569920
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed6521e502b9fae3981312d1fb163e841e3771cafc226800f7073500e3c2611
+oid sha256:2666b4f37cf91d3e01a125bc53ca66ecb37a073486f7d4391bf232cc35395c2d
 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": 0.004679457182966776,
+  "epoch": 0.006239276243955701,
   "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": 2.7163,
       "step": 75
+    },
+    {
+      "epoch": 0.0047418499454063325,
+      "grad_norm": 0.24162887036800385,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.8103,
+      "step": 76
+    },
+    {
+      "epoch": 0.00480424270784589,
+      "grad_norm": 0.20586006343364716,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.8284,
+      "step": 77
+    },
+    {
+      "epoch": 0.004866635470285447,
+      "grad_norm": 0.20056748390197754,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.7737,
+      "step": 78
+    },
+    {
+      "epoch": 0.0049290282327250036,
+      "grad_norm": 0.20362982153892517,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.5924,
+      "step": 79
+    },
+    {
+      "epoch": 0.004991420995164561,
+      "grad_norm": 0.2123316526412964,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.7571,
+      "step": 80
+    },
+    {
+      "epoch": 0.005053813757604118,
+      "grad_norm": 0.21261170506477356,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.6899,
+      "step": 81
+    },
+    {
+      "epoch": 0.005053813757604118,
+      "eval_loss": 2.734262228012085,
+      "eval_runtime": 1115.9309,
+      "eval_samples_per_second": 12.095,
+      "eval_steps_per_second": 1.513,
+      "step": 81
+    },
+    {
+      "epoch": 0.005116206520043675,
+      "grad_norm": 0.18827006220817566,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.6273,
+      "step": 82
+    },
+    {
+      "epoch": 0.005178599282483232,
+      "grad_norm": 0.20026972889900208,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.6487,
+      "step": 83
+    },
+    {
+      "epoch": 0.005240992044922789,
+      "grad_norm": 0.2252115160226822,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.6427,
+      "step": 84
+    },
+    {
+      "epoch": 0.005303384807362346,
+      "grad_norm": 0.1962587833404541,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.6515,
+      "step": 85
+    },
+    {
+      "epoch": 0.005365777569801903,
+      "grad_norm": 0.21423345804214478,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.9249,
+      "step": 86
+    },
+    {
+      "epoch": 0.0054281703322414596,
+      "grad_norm": 0.22845454514026642,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.8634,
+      "step": 87
+    },
+    {
+      "epoch": 0.005490563094681017,
+      "grad_norm": 0.2254381626844406,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.7665,
+      "step": 88
+    },
+    {
+      "epoch": 0.005552955857120574,
+      "grad_norm": 0.18592028319835663,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.7603,
+      "step": 89
+    },
+    {
+      "epoch": 0.005615348619560131,
+      "grad_norm": 0.21733587980270386,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.8256,
+      "step": 90
+    },
+    {
+      "epoch": 0.005615348619560131,
+      "eval_loss": 2.733661413192749,
+      "eval_runtime": 1115.1994,
+      "eval_samples_per_second": 12.103,
+      "eval_steps_per_second": 1.514,
+      "step": 90
+    },
+    {
+      "epoch": 0.005677741381999688,
+      "grad_norm": 0.16702857613563538,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.6456,
+      "step": 91
+    },
+    {
+      "epoch": 0.005740134144439245,
+      "grad_norm": 0.2010262906551361,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.5598,
+      "step": 92
+    },
+    {
+      "epoch": 0.005802526906878802,
+      "grad_norm": 0.19193343818187714,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.445,
+      "step": 93
+    },
+    {
+      "epoch": 0.005864919669318359,
+      "grad_norm": 0.20489740371704102,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.7588,
+      "step": 94
+    },
+    {
+      "epoch": 0.005927312431757916,
+      "grad_norm": 0.2162730097770691,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.6484,
+      "step": 95
+    },
+    {
+      "epoch": 0.005989705194197473,
+      "grad_norm": 0.20689252018928528,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.6569,
+      "step": 96
+    },
+    {
+      "epoch": 0.00605209795663703,
+      "grad_norm": 0.21897724270820618,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.6725,
+      "step": 97
+    },
+    {
+      "epoch": 0.0061144907190765875,
+      "grad_norm": 0.18510043621063232,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.6073,
+      "step": 98
+    },
+    {
+      "epoch": 0.006176883481516144,
+      "grad_norm": 0.3167794346809387,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.645,
+      "step": 99
+    },
+    {
+      "epoch": 0.006176883481516144,
+      "eval_loss": 2.733522653579712,
+      "eval_runtime": 1115.2117,
+      "eval_samples_per_second": 12.103,
+      "eval_steps_per_second": 1.514,
+      "step": 99
+    },
+    {
+      "epoch": 0.006239276243955701,
+      "grad_norm": 0.22601968050003052,
+      "learning_rate": 0.0,
+      "loss": 2.7935,
+      "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": 1.8792767916343296e+16,
+  "total_flos": 2.512227655483392e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null