Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7273852a77a2532bd3a834b03e6e89dc0da5046a40ac24c36861b5ca68854d5d
+oid sha256:ca25e8d8ed72e3d3969b65198f8a313298bfeb54ad660790291d8ca454cb1583
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb5544b04b64d474e4720ecdc368b7dabb790e9ca14344a6ab50dd814ea8553
+oid sha256:4607eadcd03153fed57e9ca286157de311ebcd2de9c91691912f59c6e5ed8772
 size 295765866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289c91a104703c8e97fb5fda5cfad3d967557d7f0b5f8e64327c9ddcc4583c74
+oid sha256:83ae7ca7c789f639bcad38d8a60a69ba45e8e51fec98d8d94a5ef0c64a0eb2a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06387735547748323,
+  "epoch": 0.12775471095496646,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 23.379,
       "eval_steps_per_second": 11.69,
       "step": 25
+    },
+    {
+      "epoch": 0.06643244969658256,
+      "grad_norm": 1.4003750085830688,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.2388,
+      "step": 26
+    },
+    {
+      "epoch": 0.06898754391568189,
+      "grad_norm": 0.7332248091697693,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1133,
+      "step": 27
+    },
+    {
+      "epoch": 0.07154263813478122,
+      "grad_norm": 1.1896603107452393,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.2283,
+      "step": 28
+    },
+    {
+      "epoch": 0.07409773235388055,
+      "grad_norm": 1.1134674549102783,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.0962,
+      "step": 29
+    },
+    {
+      "epoch": 0.07665282657297988,
+      "grad_norm": 0.8824465274810791,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1033,
+      "step": 30
+    },
+    {
+      "epoch": 0.07920792079207921,
+      "grad_norm": 1.149545669555664,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0992,
+      "step": 31
+    },
+    {
+      "epoch": 0.08176301501117854,
+      "grad_norm": 1.4859205484390259,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.1449,
+      "step": 32
+    },
+    {
+      "epoch": 0.08431810923027787,
+      "grad_norm": 1.4090569019317627,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.1599,
+      "step": 33
+    },
+    {
+      "epoch": 0.0868732034493772,
+      "grad_norm": 0.9273414611816406,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0869,
+      "step": 34
+    },
+    {
+      "epoch": 0.08942829766847653,
+      "grad_norm": 1.5829126834869385,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0687,
+      "step": 35
+    },
+    {
+      "epoch": 0.09198339188757586,
+      "grad_norm": 0.9160271883010864,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0965,
+      "step": 36
+    },
+    {
+      "epoch": 0.09453848610667519,
+      "grad_norm": 0.6371787786483765,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0343,
+      "step": 37
+    },
+    {
+      "epoch": 0.09709358032577452,
+      "grad_norm": 1.1970824003219604,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0713,
+      "step": 38
+    },
+    {
+      "epoch": 0.09964867454487385,
+      "grad_norm": 1.2046923637390137,
+      "learning_rate": 5e-05,
+      "loss": 0.0583,
+      "step": 39
+    },
+    {
+      "epoch": 0.10220376876397318,
+      "grad_norm": 0.6077913045883179,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0248,
+      "step": 40
+    },
+    {
+      "epoch": 0.1047588629830725,
+      "grad_norm": 0.13593098521232605,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0041,
+      "step": 41
+    },
+    {
+      "epoch": 0.10731395720217184,
+      "grad_norm": 0.3258521854877472,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0045,
+      "step": 42
+    },
+    {
+      "epoch": 0.10986905142127117,
+      "grad_norm": 0.13207238912582397,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.005,
+      "step": 43
+    },
+    {
+      "epoch": 0.11242414564037048,
+      "grad_norm": 0.12057414650917053,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0018,
+      "step": 44
+    },
+    {
+      "epoch": 0.11497923985946981,
+      "grad_norm": 0.40026429295539856,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0105,
+      "step": 45
+    },
+    {
+      "epoch": 0.11753433407856914,
+      "grad_norm": 0.13764841854572296,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0017,
+      "step": 46
+    },
+    {
+      "epoch": 0.12008942829766847,
+      "grad_norm": 1.6517468690872192,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.055,
+      "step": 47
+    },
+    {
+      "epoch": 0.1226445225167678,
+      "grad_norm": 0.8555214405059814,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0113,
+      "step": 48
+    },
+    {
+      "epoch": 0.12519961673586713,
+      "grad_norm": 0.9184969663619995,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0174,
+      "step": 49
+    },
+    {
+      "epoch": 0.12775471095496646,
+      "grad_norm": 4.27571964263916,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.1238,
+      "step": 50
+    },
+    {
+      "epoch": 0.12775471095496646,
+      "eval_loss": 0.08126296103000641,
+      "eval_runtime": 14.1157,
+      "eval_samples_per_second": 23.378,
+      "eval_steps_per_second": 11.689,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6622102211788800.0,
+  "total_flos": 1.32442044235776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null