Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb6d26642e41b36ebcab20b6d27deee2bf7acbe453b4b7fa1a231d4fcd883bf
+oid sha256:dfcab73f16ac2f126ac0ab73726ff3065f292a7be1d803d465a38ae64a257f53
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d87fe03f5e98938d93e08babb25d9fbf091a807e758a930b3e823b13e604a5
+oid sha256:6a8308d735a26e52264d9a2ff8b58b8c457c4f3bcb879b22d442b86e3806800e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d1a1af9eebbad8de3e56c442429cad586fb9a079791f4de0e7491c83d28f99
+oid sha256:79805400eb08ac7f1d6f09edb95c9b79fec182274bd7004808e55c7bf1a0da14
 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": 0.0061578882548544685,
+  "epoch": 0.008210517673139291,
   "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": 1.629,
       "step": 75
+    },
+    {
+      "epoch": 0.006239993431585862,
+      "grad_norm": 0.6360693573951721,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.6415,
+      "step": 76
+    },
+    {
+      "epoch": 0.006322098608317254,
+      "grad_norm": 0.8207737803459167,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.3515,
+      "step": 77
+    },
+    {
+      "epoch": 0.006404203785048647,
+      "grad_norm": 0.8579248785972595,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.4226,
+      "step": 78
+    },
+    {
+      "epoch": 0.00648630896178004,
+      "grad_norm": 0.6944251656532288,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.4225,
+      "step": 79
+    },
+    {
+      "epoch": 0.006568414138511433,
+      "grad_norm": 0.6882073879241943,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.5884,
+      "step": 80
+    },
+    {
+      "epoch": 0.006650519315242826,
+      "grad_norm": 0.7763206362724304,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.4043,
+      "step": 81
+    },
+    {
+      "epoch": 0.006650519315242826,
+      "eval_loss": 1.4972970485687256,
+      "eval_runtime": 1412.9736,
+      "eval_samples_per_second": 7.259,
+      "eval_steps_per_second": 0.908,
+      "step": 81
+    },
+    {
+      "epoch": 0.006732624491974219,
+      "grad_norm": 0.7503749132156372,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6366,
+      "step": 82
+    },
+    {
+      "epoch": 0.006814729668705612,
+      "grad_norm": 0.6911786198616028,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.5811,
+      "step": 83
+    },
+    {
+      "epoch": 0.006896834845437004,
+      "grad_norm": 0.5811960101127625,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.6024,
+      "step": 84
+    },
+    {
+      "epoch": 0.006978940022168398,
+      "grad_norm": 0.7332911491394043,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5254,
+      "step": 85
+    },
+    {
+      "epoch": 0.007061045198899791,
+      "grad_norm": 0.9922388195991516,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.1505,
+      "step": 86
+    },
+    {
+      "epoch": 0.007143150375631183,
+      "grad_norm": 0.567830502986908,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.78,
+      "step": 87
+    },
+    {
+      "epoch": 0.0072252555523625766,
+      "grad_norm": 0.7100740075111389,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6115,
+      "step": 88
+    },
+    {
+      "epoch": 0.007307360729093969,
+      "grad_norm": 0.710722029209137,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.4315,
+      "step": 89
+    },
+    {
+      "epoch": 0.007389465905825362,
+      "grad_norm": 0.8105925917625427,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5851,
+      "step": 90
+    },
+    {
+      "epoch": 0.007389465905825362,
+      "eval_loss": 1.4960790872573853,
+      "eval_runtime": 1413.3933,
+      "eval_samples_per_second": 7.257,
+      "eval_steps_per_second": 0.908,
+      "step": 90
+    },
+    {
+      "epoch": 0.0074715710825567555,
+      "grad_norm": 0.6303733587265015,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.5841,
+      "step": 91
+    },
+    {
+      "epoch": 0.007553676259288148,
+      "grad_norm": 0.7646224498748779,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.7062,
+      "step": 92
+    },
+    {
+      "epoch": 0.007635781436019541,
+      "grad_norm": 0.9230985045433044,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.3967,
+      "step": 93
+    },
+    {
+      "epoch": 0.0077178866127509335,
+      "grad_norm": 0.6842741966247559,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5842,
+      "step": 94
+    },
+    {
+      "epoch": 0.007799991789482327,
+      "grad_norm": 0.6308616995811462,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.5846,
+      "step": 95
+    },
+    {
+      "epoch": 0.00788209696621372,
+      "grad_norm": 0.5984325408935547,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.5692,
+      "step": 96
+    },
+    {
+      "epoch": 0.007964202142945112,
+      "grad_norm": 0.7772747874259949,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.3807,
+      "step": 97
+    },
+    {
+      "epoch": 0.008046307319676505,
+      "grad_norm": 0.6606855392456055,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4403,
+      "step": 98
+    },
+    {
+      "epoch": 0.008128412496407899,
+      "grad_norm": 0.5787830948829651,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.7207,
+      "step": 99
+    },
+    {
+      "epoch": 0.008128412496407899,
+      "eval_loss": 1.4957927465438843,
+      "eval_runtime": 1413.4229,
+      "eval_samples_per_second": 7.257,
+      "eval_steps_per_second": 0.908,
+      "step": 99
+    },
+    {
+      "epoch": 0.008210517673139291,
+      "grad_norm": 0.6355916857719421,
+      "learning_rate": 0.0,
+      "loss": 1.3047,
+      "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": 7.307589743070413e+16,
+  "total_flos": 9.607440322107802e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null