Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d4e0322331d9088e78fd7a022c4b6947934337338189a1646ea0cab447c7ddd
+oid sha256:3710f0f60bd7cb6d058599a45e570639c4865376c83b083bbf0de2dee1fece99
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b475effe5fb64ef33c755fea8e1518aae7f53f7c48700f0202e161c93231ffbf
+oid sha256:90ea9811620bc91214637c7826f5264ae6c0b2007b883076f881753ba290959f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8bb943b78597438abebef0ec790b3e252eb54101d94eb6c899d1de02c649b6a
+oid sha256:b94a20eee85d5c75b63ebc4d8909f64f2d180c1f85b77b7d16b1c4617b766e1e
 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": 0.07535795026375283,
+  "epoch": 0.11303692539562923,
   "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": 0.2822,
       "step": 50
+    },
+    {
+      "epoch": 0.07686510926902788,
+      "grad_norm": 0.7992674708366394,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.2198,
+      "step": 51
+    },
+    {
+      "epoch": 0.07837226827430294,
+      "grad_norm": 0.5225107669830322,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.1998,
+      "step": 52
+    },
+    {
+      "epoch": 0.07987942727957799,
+      "grad_norm": 0.5572648048400879,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.1562,
+      "step": 53
+    },
+    {
+      "epoch": 0.08138658628485305,
+      "grad_norm": 0.6357726454734802,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.1094,
+      "step": 54
+    },
+    {
+      "epoch": 0.08138658628485305,
+      "eval_loss": 0.15196655690670013,
+      "eval_runtime": 123.5572,
+      "eval_samples_per_second": 4.524,
+      "eval_steps_per_second": 0.567,
+      "step": 54
+    },
+    {
+      "epoch": 0.0828937452901281,
+      "grad_norm": 0.5080541372299194,
+      "learning_rate": 5e-05,
+      "loss": 0.1882,
+      "step": 55
+    },
+    {
+      "epoch": 0.08440090429540316,
+      "grad_norm": 0.5046006441116333,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.1819,
+      "step": 56
+    },
+    {
+      "epoch": 0.08590806330067823,
+      "grad_norm": 0.6285750865936279,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.1142,
+      "step": 57
+    },
+    {
+      "epoch": 0.08741522230595328,
+      "grad_norm": 0.6299275755882263,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.1164,
+      "step": 58
+    },
+    {
+      "epoch": 0.08892238131122833,
+      "grad_norm": 0.37507885694503784,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.1564,
+      "step": 59
+    },
+    {
+      "epoch": 0.0904295403165034,
+      "grad_norm": 0.546333372592926,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1532,
+      "step": 60
+    },
+    {
+      "epoch": 0.09193669932177845,
+      "grad_norm": 0.5628113150596619,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.1439,
+      "step": 61
+    },
+    {
+      "epoch": 0.0934438583270535,
+      "grad_norm": 0.31105494499206543,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0802,
+      "step": 62
+    },
+    {
+      "epoch": 0.09495101733232857,
+      "grad_norm": 0.2998591661453247,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.0895,
+      "step": 63
+    },
+    {
+      "epoch": 0.09495101733232857,
+      "eval_loss": 0.14642611145973206,
+      "eval_runtime": 123.5866,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 0.566,
+      "step": 63
+    },
+    {
+      "epoch": 0.09645817633760362,
+      "grad_norm": 0.34861132502555847,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0748,
+      "step": 64
+    },
+    {
+      "epoch": 0.09796533534287867,
+      "grad_norm": 0.3098653256893158,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.085,
+      "step": 65
+    },
+    {
+      "epoch": 0.09947249434815374,
+      "grad_norm": 2.6786906719207764,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.3102,
+      "step": 66
+    },
+    {
+      "epoch": 0.10097965335342879,
+      "grad_norm": 0.4055371582508087,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0964,
+      "step": 67
+    },
+    {
+      "epoch": 0.10248681235870384,
+      "grad_norm": 0.38335639238357544,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0683,
+      "step": 68
+    },
+    {
+      "epoch": 0.1039939713639789,
+      "grad_norm": 0.5514392852783203,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.1355,
+      "step": 69
+    },
+    {
+      "epoch": 0.10550113036925396,
+      "grad_norm": 0.4799521267414093,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1633,
+      "step": 70
+    },
+    {
+      "epoch": 0.10700828937452901,
+      "grad_norm": 0.7698957324028015,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.354,
+      "step": 71
+    },
+    {
+      "epoch": 0.10851544837980406,
+      "grad_norm": 0.33936837315559387,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0471,
+      "step": 72
+    },
+    {
+      "epoch": 0.10851544837980406,
+      "eval_loss": 0.14258287847042084,
+      "eval_runtime": 123.5915,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 0.566,
+      "step": 72
+    },
+    {
+      "epoch": 0.11002260738507913,
+      "grad_norm": 0.3643311560153961,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.1008,
+      "step": 73
+    },
+    {
+      "epoch": 0.11152976639035418,
+      "grad_norm": 0.6503349542617798,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.2444,
+      "step": 74
+    },
+    {
+      "epoch": 0.11303692539562923,
+      "grad_norm": 0.3921027183532715,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.1735,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.381778471426458e+16,
+  "total_flos": 1.1091214889228698e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null