Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51298c24d2cfa76b375c8a3ddaef5789d63fd628d2fe382769658e712dc0b467
+oid sha256:ffece9bc80de0559ec793dc414be18d052f1c36c4b4a5f59b0b1427a596b4ded
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f19fb35cf362ddd3eb4deb2cddbb114beb8e748b709ff43ddf648bb6f4892e2
+oid sha256:d49855e54587beaff1cbec791c4a25aa8f4ce0613ab14d49d5c9c98251c1c441
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be2a5769098af94d196fcad60e75c17cff94ec7e551cd0bf373fdd92858519d2
+oid sha256:b28716e0201d453dfccb8481130df36b8957e6f8e6d3cb2e37ebe0b0b0a6ffeb
 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": 0.021724961981316532,
+  "epoch": 0.0325874429719748,
   "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": 0.8024,
       "step": 50
+    },
+    {
+      "epoch": 0.022159461220942863,
+      "grad_norm": 0.7032544016838074,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.9822,
+      "step": 51
+    },
+    {
+      "epoch": 0.022593960460569194,
+      "grad_norm": 0.8667249083518982,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.7966,
+      "step": 52
+    },
+    {
+      "epoch": 0.023028459700195524,
+      "grad_norm": 0.7494419813156128,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.9368,
+      "step": 53
+    },
+    {
+      "epoch": 0.023462958939821855,
+      "grad_norm": 0.6607624888420105,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.8481,
+      "step": 54
+    },
+    {
+      "epoch": 0.023462958939821855,
+      "eval_loss": 0.4661303162574768,
+      "eval_runtime": 937.0866,
+      "eval_samples_per_second": 2.069,
+      "eval_steps_per_second": 0.259,
+      "step": 54
+    },
+    {
+      "epoch": 0.023897458179448185,
+      "grad_norm": 1.3510135412216187,
+      "learning_rate": 5e-05,
+      "loss": 0.955,
+      "step": 55
+    },
+    {
+      "epoch": 0.024331957419074516,
+      "grad_norm": 0.7510749101638794,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.8116,
+      "step": 56
+    },
+    {
+      "epoch": 0.024766456658700847,
+      "grad_norm": 0.7377657294273376,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.8809,
+      "step": 57
+    },
+    {
+      "epoch": 0.025200955898327177,
+      "grad_norm": 0.6575254201889038,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.9222,
+      "step": 58
+    },
+    {
+      "epoch": 0.025635455137953508,
+      "grad_norm": 0.7421597242355347,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.009,
+      "step": 59
+    },
+    {
+      "epoch": 0.02606995437757984,
+      "grad_norm": 0.6919296383857727,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.8832,
+      "step": 60
+    },
+    {
+      "epoch": 0.02650445361720617,
+      "grad_norm": 0.7524620294570923,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.0048,
+      "step": 61
+    },
+    {
+      "epoch": 0.0269389528568325,
+      "grad_norm": 0.7775732278823853,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.9253,
+      "step": 62
+    },
+    {
+      "epoch": 0.02737345209645883,
+      "grad_norm": 0.7206799387931824,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.9962,
+      "step": 63
+    },
+    {
+      "epoch": 0.02737345209645883,
+      "eval_loss": 0.4474518597126007,
+      "eval_runtime": 938.4115,
+      "eval_samples_per_second": 2.066,
+      "eval_steps_per_second": 0.259,
+      "step": 63
+    },
+    {
+      "epoch": 0.02780795133608516,
+      "grad_norm": 0.7352960705757141,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8807,
+      "step": 64
+    },
+    {
+      "epoch": 0.02824245057571149,
+      "grad_norm": 0.6605808138847351,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.7756,
+      "step": 65
+    },
+    {
+      "epoch": 0.028676949815337822,
+      "grad_norm": 0.76267409324646,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.8257,
+      "step": 66
+    },
+    {
+      "epoch": 0.029111449054964152,
+      "grad_norm": 0.739069938659668,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.9447,
+      "step": 67
+    },
+    {
+      "epoch": 0.029545948294590483,
+      "grad_norm": 0.8183147311210632,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.8142,
+      "step": 68
+    },
+    {
+      "epoch": 0.029980447534216813,
+      "grad_norm": 0.8828584551811218,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.8426,
+      "step": 69
+    },
+    {
+      "epoch": 0.030414946773843144,
+      "grad_norm": 0.8308943510055542,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0606,
+      "step": 70
+    },
+    {
+      "epoch": 0.030849446013469478,
+      "grad_norm": 0.7810403108596802,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.7237,
+      "step": 71
+    },
+    {
+      "epoch": 0.03128394525309581,
+      "grad_norm": 0.8019788861274719,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.0645,
+      "step": 72
+    },
+    {
+      "epoch": 0.03128394525309581,
+      "eval_loss": 0.43661898374557495,
+      "eval_runtime": 937.5407,
+      "eval_samples_per_second": 2.068,
+      "eval_steps_per_second": 0.259,
+      "step": 72
+    },
+    {
+      "epoch": 0.03171844449272214,
+      "grad_norm": 0.7618681192398071,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.859,
+      "step": 73
+    },
+    {
+      "epoch": 0.03215294373234847,
+      "grad_norm": 0.8050389885902405,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.9631,
+      "step": 74
+    },
+    {
+      "epoch": 0.0325874429719748,
+      "grad_norm": 0.8176538944244385,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.9906,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2124355228073984e+17,
+  "total_flos": 1.8281750291546112e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null