Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a344d33150feeb3b0c7a8f74503cbf8c841199e2054a23e8a80bdb3a68e7f96
+oid sha256:307545629ec129618d98019da41be60a2f7ae2d1ad5bc0b70b5bdcf58f2c1116
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e621add0d1561ab07e6c26ccbea9b6c92ee2d3da4eb67e472da06744f36f4d24
+oid sha256:31fc52270abf3c5ddafe86ad540ab286b83b3e0882b73847adc9e6d29c52336f
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76dcd7b68300c0d7541cd1a56d1c5df9bcb44ed28f7d7ba9c624efd22537c4bc
+oid sha256:7f7a2bf7701d3c3304a78ccedc5ee566cf4dfa08472396e1f78f2396dff5e956
 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": 0.004163197335553705,
+  "epoch": 0.0062447960033305576,
   "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": 0.7052,
       "step": 50
+    },
+    {
+      "epoch": 0.004246461282264779,
+      "grad_norm": 0.5144871473312378,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.6276,
+      "step": 51
+    },
+    {
+      "epoch": 0.0043297252289758534,
+      "grad_norm": 0.7938607931137085,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.6172,
+      "step": 52
+    },
+    {
+      "epoch": 0.004412989175686928,
+      "grad_norm": 0.559364378452301,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.9424,
+      "step": 53
+    },
+    {
+      "epoch": 0.004496253122398002,
+      "grad_norm": 0.5549708604812622,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.5619,
+      "step": 54
+    },
+    {
+      "epoch": 0.004496253122398002,
+      "eval_loss": 0.6263570785522461,
+      "eval_runtime": 1874.081,
+      "eval_samples_per_second": 5.397,
+      "eval_steps_per_second": 0.675,
+      "step": 54
+    },
+    {
+      "epoch": 0.004579517069109076,
+      "grad_norm": 0.6072118282318115,
+      "learning_rate": 5e-05,
+      "loss": 0.5964,
+      "step": 55
+    },
+    {
+      "epoch": 0.00466278101582015,
+      "grad_norm": 0.5688763856887817,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.7724,
+      "step": 56
+    },
+    {
+      "epoch": 0.004746044962531224,
+      "grad_norm": 0.6150090098381042,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.6189,
+      "step": 57
+    },
+    {
+      "epoch": 0.004829308909242298,
+      "grad_norm": 0.5213116407394409,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.6805,
+      "step": 58
+    },
+    {
+      "epoch": 0.004912572855953372,
+      "grad_norm": 0.47878560423851013,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.625,
+      "step": 59
+    },
+    {
+      "epoch": 0.004995836802664446,
+      "grad_norm": 0.6849039793014526,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.7203,
+      "step": 60
+    },
+    {
+      "epoch": 0.00507910074937552,
+      "grad_norm": 0.5728254914283752,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.8075,
+      "step": 61
+    },
+    {
+      "epoch": 0.005162364696086595,
+      "grad_norm": 0.7572735548019409,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.5874,
+      "step": 62
+    },
+    {
+      "epoch": 0.005245628642797669,
+      "grad_norm": 0.6589543223381042,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.5797,
+      "step": 63
+    },
+    {
+      "epoch": 0.005245628642797669,
+      "eval_loss": 0.6163843274116516,
+      "eval_runtime": 1874.0277,
+      "eval_samples_per_second": 5.397,
+      "eval_steps_per_second": 0.675,
+      "step": 63
+    },
+    {
+      "epoch": 0.005328892589508743,
+      "grad_norm": 0.5503858327865601,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6858,
+      "step": 64
+    },
+    {
+      "epoch": 0.005412156536219817,
+      "grad_norm": 0.4466218948364258,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.7072,
+      "step": 65
+    },
+    {
+      "epoch": 0.005495420482930891,
+      "grad_norm": 0.676203727722168,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.6532,
+      "step": 66
+    },
+    {
+      "epoch": 0.005578684429641965,
+      "grad_norm": 0.5970198512077332,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.4029,
+      "step": 67
+    },
+    {
+      "epoch": 0.005661948376353039,
+      "grad_norm": 0.59070885181427,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.6509,
+      "step": 68
+    },
+    {
+      "epoch": 0.005745212323064113,
+      "grad_norm": 0.5007186532020569,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.7345,
+      "step": 69
+    },
+    {
+      "epoch": 0.005828476269775187,
+      "grad_norm": 0.549541175365448,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.492,
+      "step": 70
+    },
+    {
+      "epoch": 0.005911740216486262,
+      "grad_norm": 0.6607359051704407,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.5709,
+      "step": 71
+    },
+    {
+      "epoch": 0.005995004163197336,
+      "grad_norm": 0.4524803161621094,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.843,
+      "step": 72
+    },
+    {
+      "epoch": 0.005995004163197336,
+      "eval_loss": 0.6111176013946533,
+      "eval_runtime": 1875.3753,
+      "eval_samples_per_second": 5.393,
+      "eval_steps_per_second": 0.675,
+      "step": 72
+    },
+    {
+      "epoch": 0.00607826810990841,
+      "grad_norm": 0.5329728126525879,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.7755,
+      "step": 73
+    },
+    {
+      "epoch": 0.006161532056619483,
+      "grad_norm": 0.5134813189506531,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.5342,
+      "step": 74
+    },
+    {
+      "epoch": 0.0062447960033305576,
+      "grad_norm": 0.47925451397895813,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.9089,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.817628228583424e+16,
+  "total_flos": 8.693387637030912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null