Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80bfe2d688ac44392280baa5fdad87d14de201541df9c16bb0d8163c43035b58
+oid sha256:c695e3601405e549134d7ea49799417e7ed642916c9c8601b702e3818fdc7e5e
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064f987673a140b70d424d59b8daf0e8621e71ba532ad148748861f58bf57093
+oid sha256:1e6a24fc92a7e6954091a81e1c64741b28f0ade8dd5f33b440729eb3008a865b
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
+oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
 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": 0.051440329218107,
+  "epoch": 0.07716049382716049,
   "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": 10.3743,
       "step": 50
+    },
+    {
+      "epoch": 0.05246913580246913,
+      "grad_norm": 0.033705513924360275,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3749,
+      "step": 51
+    },
+    {
+      "epoch": 0.053497942386831275,
+      "grad_norm": 0.03999943658709526,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3671,
+      "step": 52
+    },
+    {
+      "epoch": 0.05452674897119342,
+      "grad_norm": 0.043624721467494965,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3708,
+      "step": 53
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 0.036783572286367416,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3684,
+      "step": 54
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "eval_loss": 10.370903015136719,
+      "eval_runtime": 4.3048,
+      "eval_samples_per_second": 190.254,
+      "eval_steps_per_second": 23.927,
+      "step": 54
+    },
+    {
+      "epoch": 0.056584362139917695,
+      "grad_norm": 0.036852557212114334,
+      "learning_rate": 5e-05,
+      "loss": 10.3715,
+      "step": 55
+    },
+    {
+      "epoch": 0.05761316872427984,
+      "grad_norm": 0.036059990525245667,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3685,
+      "step": 56
+    },
+    {
+      "epoch": 0.05864197530864197,
+      "grad_norm": 0.04546878859400749,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3685,
+      "step": 57
+    },
+    {
+      "epoch": 0.059670781893004114,
+      "grad_norm": 0.045334216207265854,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3677,
+      "step": 58
+    },
+    {
+      "epoch": 0.060699588477366256,
+      "grad_norm": 0.046929437667131424,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3717,
+      "step": 59
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 0.041340090334415436,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3723,
+      "step": 60
+    },
+    {
+      "epoch": 0.06275720164609054,
+      "grad_norm": 0.042488716542720795,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.3692,
+      "step": 61
+    },
+    {
+      "epoch": 0.06378600823045268,
+      "grad_norm": 0.03854437917470932,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3682,
+      "step": 62
+    },
+    {
+      "epoch": 0.06481481481481481,
+      "grad_norm": 0.03789610043168068,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3731,
+      "step": 63
+    },
+    {
+      "epoch": 0.06481481481481481,
+      "eval_loss": 10.370210647583008,
+      "eval_runtime": 4.6613,
+      "eval_samples_per_second": 175.703,
+      "eval_steps_per_second": 22.097,
+      "step": 63
+    },
+    {
+      "epoch": 0.06584362139917696,
+      "grad_norm": 0.044738225638866425,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3694,
+      "step": 64
+    },
+    {
+      "epoch": 0.0668724279835391,
+      "grad_norm": 0.040270205587148666,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3669,
+      "step": 65
+    },
+    {
+      "epoch": 0.06790123456790123,
+      "grad_norm": 0.04272771254181862,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3651,
+      "step": 66
+    },
+    {
+      "epoch": 0.06893004115226338,
+      "grad_norm": 0.043519698083400726,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3693,
+      "step": 67
+    },
+    {
+      "epoch": 0.06995884773662552,
+      "grad_norm": 0.03874226659536362,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3727,
+      "step": 68
+    },
+    {
+      "epoch": 0.07098765432098765,
+      "grad_norm": 0.05196073278784752,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3709,
+      "step": 69
+    },
+    {
+      "epoch": 0.0720164609053498,
+      "grad_norm": 0.04321382939815521,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3718,
+      "step": 70
+    },
+    {
+      "epoch": 0.07304526748971193,
+      "grad_norm": 0.046473391354084015,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3715,
+      "step": 71
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.04274188354611397,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3679,
+      "step": 72
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "eval_loss": 10.369702339172363,
+      "eval_runtime": 4.6514,
+      "eval_samples_per_second": 176.078,
+      "eval_steps_per_second": 22.144,
+      "step": 72
+    },
+    {
+      "epoch": 0.07510288065843622,
+      "grad_norm": 0.03789234161376953,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3722,
+      "step": 73
+    },
+    {
+      "epoch": 0.07613168724279835,
+      "grad_norm": 0.04123846814036369,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.3666,
+      "step": 74
+    },
+    {
+      "epoch": 0.07716049382716049,
+      "grad_norm": 0.043930958956480026,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3657,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2615122329600.0,
+  "total_flos": 3922683494400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null