Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8ae71ee2b92f1b49ade082d06d390ab39ca62227ac1ca6d6683d50f5a020c55
+oid sha256:9fb363d52f809e42ba14f4c5fa66d715569ec540d99d2f9059047060d5eb9c48
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7acffd2f607aba4f4c389554a93cccc720f993e6ae7b8e1f6e7e34dd372d09a2
+oid sha256:fe39e32a61a9c8e2f2e972a4523b0e7386e00d8bd33a6946e65da955afc882f4
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d902497bb10eeedb25039dc460c30be6a7ebed721edcdf01474b0ca8453fbde2
+oid sha256:26273becc6a8648e93d80c878bdc8c53b88305e9bd75c42025a44697539acb1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001459470504101112,
+  "epoch": 0.0021892057561516682,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 2.4015,
       "step": 50
+    },
+    {
+      "epoch": 0.0014886599141831344,
+      "grad_norm": 4.629258155822754,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.8155,
+      "step": 51
+    },
+    {
+      "epoch": 0.0015178493242651565,
+      "grad_norm": 3.993497371673584,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.2827,
+      "step": 52
+    },
+    {
+      "epoch": 0.001547038734347179,
+      "grad_norm": 4.616318702697754,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 2.6136,
+      "step": 53
+    },
+    {
+      "epoch": 0.001576228144429201,
+      "grad_norm": 3.513707399368286,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.0149,
+      "step": 54
+    },
+    {
+      "epoch": 0.001576228144429201,
+      "eval_loss": 1.1747256517410278,
+      "eval_runtime": 5143.0061,
+      "eval_samples_per_second": 5.61,
+      "eval_steps_per_second": 0.701,
+      "step": 54
+    },
+    {
+      "epoch": 0.0016054175545112232,
+      "grad_norm": 3.937657356262207,
+      "learning_rate": 5e-05,
+      "loss": 2.0302,
+      "step": 55
+    },
+    {
+      "epoch": 0.0016346069645932456,
+      "grad_norm": 5.150801658630371,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.5411,
+      "step": 56
+    },
+    {
+      "epoch": 0.0016637963746752677,
+      "grad_norm": 4.555789470672607,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.8977,
+      "step": 57
+    },
+    {
+      "epoch": 0.0016929857847572901,
+      "grad_norm": 3.8810622692108154,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.0767,
+      "step": 58
+    },
+    {
+      "epoch": 0.0017221751948393123,
+      "grad_norm": 4.165887832641602,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 2.3894,
+      "step": 59
+    },
+    {
+      "epoch": 0.0017513646049213346,
+      "grad_norm": 3.750863552093506,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.0504,
+      "step": 60
+    },
+    {
+      "epoch": 0.0017805540150033568,
+      "grad_norm": 2.934596538543701,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.9172,
+      "step": 61
+    },
+    {
+      "epoch": 0.001809743425085379,
+      "grad_norm": 3.5289196968078613,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.2315,
+      "step": 62
+    },
+    {
+      "epoch": 0.0018389328351674013,
+      "grad_norm": 4.346237659454346,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.2884,
+      "step": 63
+    },
+    {
+      "epoch": 0.0018389328351674013,
+      "eval_loss": 1.147663950920105,
+      "eval_runtime": 5144.0405,
+      "eval_samples_per_second": 5.608,
+      "eval_steps_per_second": 0.701,
+      "step": 63
+    },
+    {
+      "epoch": 0.0018681222452494235,
+      "grad_norm": 5.116072177886963,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.4416,
+      "step": 64
+    },
+    {
+      "epoch": 0.0018973116553314458,
+      "grad_norm": 3.6044180393218994,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.6073,
+      "step": 65
+    },
+    {
+      "epoch": 0.001926501065413468,
+      "grad_norm": 3.5492379665374756,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.714,
+      "step": 66
+    },
+    {
+      "epoch": 0.00195569047549549,
+      "grad_norm": 3.5761613845825195,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.8829,
+      "step": 67
+    },
+    {
+      "epoch": 0.0019848798855775125,
+      "grad_norm": 3.665513515472412,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.003,
+      "step": 68
+    },
+    {
+      "epoch": 0.002014069295659535,
+      "grad_norm": 4.549952030181885,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.0985,
+      "step": 69
+    },
+    {
+      "epoch": 0.002043258705741557,
+      "grad_norm": 6.244661808013916,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3304,
+      "step": 70
+    },
+    {
+      "epoch": 0.002072448115823579,
+      "grad_norm": 4.266684055328369,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 2.0038,
+      "step": 71
+    },
+    {
+      "epoch": 0.0021016375259056016,
+      "grad_norm": 4.135928153991699,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.1593,
+      "step": 72
+    },
+    {
+      "epoch": 0.0021016375259056016,
+      "eval_loss": 1.1359862089157104,
+      "eval_runtime": 5144.5001,
+      "eval_samples_per_second": 5.608,
+      "eval_steps_per_second": 0.701,
+      "step": 72
+    },
+    {
+      "epoch": 0.0021308269359876235,
+      "grad_norm": 4.030326843261719,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.9979,
+      "step": 73
+    },
+    {
+      "epoch": 0.002160016346069646,
+      "grad_norm": 4.288099765777588,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.3285,
+      "step": 74
+    },
+    {
+      "epoch": 0.0021892057561516682,
+      "grad_norm": 3.925044536590576,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.015,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.6173476364288e+16,
+  "total_flos": 1.1108631969792e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null