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:a6b37a51d937da6293c08b490dc94388ea37de502ac083b2bf859447e11da34b
+oid sha256:566e707db1ec109b7de18f39db0405edea1872dfe6fe7005423b0d53c3c1001b
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4177cc1260f6b648b5cfc485dac95054c627f46c76ee70115e4c77f82fd47a9
+oid sha256:3d15fc0802be07b7fd1276d666f8f4aef0db03976af597a70871fc2e6bcb618b
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90cdb72911d38e9202f3334751018a6c79ad3b2006b03921a34979cf1abce5c7
+oid sha256:831cb014d734d1a236f43ff0ae6d2fae9843b9526271b8c069d0c080cd61d6bb
 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": 0.2506265664160401,
+  "epoch": 0.37593984962406013,
   "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": 1.4047,
       "step": 50
+    },
+    {
+      "epoch": 0.2556390977443609,
+      "grad_norm": 1.230220079421997,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.2893,
+      "step": 51
+    },
+    {
+      "epoch": 0.2606516290726817,
+      "grad_norm": 2.455333709716797,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.219,
+      "step": 52
+    },
+    {
+      "epoch": 0.2656641604010025,
+      "grad_norm": 1.4559978246688843,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.2945,
+      "step": 53
+    },
+    {
+      "epoch": 0.2706766917293233,
+      "grad_norm": 3.1076526641845703,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.3378,
+      "step": 54
+    },
+    {
+      "epoch": 0.2706766917293233,
+      "eval_loss": 0.7307549715042114,
+      "eval_runtime": 28.6544,
+      "eval_samples_per_second": 5.863,
+      "eval_steps_per_second": 0.733,
+      "step": 54
+    },
+    {
+      "epoch": 0.2756892230576441,
+      "grad_norm": 1.1804949045181274,
+      "learning_rate": 5e-05,
+      "loss": 1.1941,
+      "step": 55
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 3.7159390449523926,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.599,
+      "step": 56
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 1.7314178943634033,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.2022,
+      "step": 57
+    },
+    {
+      "epoch": 0.2907268170426065,
+      "grad_norm": 3.72270131111145,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.6478,
+      "step": 58
+    },
+    {
+      "epoch": 0.2957393483709273,
+      "grad_norm": 2.9939489364624023,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.5453,
+      "step": 59
+    },
+    {
+      "epoch": 0.3007518796992481,
+      "grad_norm": 2.26654314994812,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.3947,
+      "step": 60
+    },
+    {
+      "epoch": 0.3057644110275689,
+      "grad_norm": 2.3148698806762695,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.4923,
+      "step": 61
+    },
+    {
+      "epoch": 0.3107769423558897,
+      "grad_norm": 1.921850323677063,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.4355,
+      "step": 62
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 2.0384600162506104,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.3469,
+      "step": 63
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "eval_loss": 0.6959288716316223,
+      "eval_runtime": 28.6169,
+      "eval_samples_per_second": 5.871,
+      "eval_steps_per_second": 0.734,
+      "step": 63
+    },
+    {
+      "epoch": 0.3208020050125313,
+      "grad_norm": 3.557666301727295,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.4865,
+      "step": 64
+    },
+    {
+      "epoch": 0.3258145363408521,
+      "grad_norm": 1.5931860208511353,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.4297,
+      "step": 65
+    },
+    {
+      "epoch": 0.3308270676691729,
+      "grad_norm": 2.942139148712158,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.4265,
+      "step": 66
+    },
+    {
+      "epoch": 0.3358395989974937,
+      "grad_norm": 1.7241272926330566,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.3485,
+      "step": 67
+    },
+    {
+      "epoch": 0.3408521303258145,
+      "grad_norm": 1.5445481538772583,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.4078,
+      "step": 68
+    },
+    {
+      "epoch": 0.3458646616541353,
+      "grad_norm": 1.5881041288375854,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.3533,
+      "step": 69
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.4929602146148682,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.32,
+      "step": 70
+    },
+    {
+      "epoch": 0.3558897243107769,
+      "grad_norm": 1.622667670249939,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.301,
+      "step": 71
+    },
+    {
+      "epoch": 0.3609022556390977,
+      "grad_norm": 1.4693689346313477,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.4372,
+      "step": 72
+    },
+    {
+      "epoch": 0.3609022556390977,
+      "eval_loss": 0.6896541118621826,
+      "eval_runtime": 28.7246,
+      "eval_samples_per_second": 5.849,
+      "eval_steps_per_second": 0.731,
+      "step": 72
+    },
+    {
+      "epoch": 0.3659147869674185,
+      "grad_norm": 9.016338348388672,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.7571,
+      "step": 73
+    },
+    {
+      "epoch": 0.37092731829573933,
+      "grad_norm": 2.0812020301818848,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.4578,
+      "step": 74
+    },
+    {
+      "epoch": 0.37593984962406013,
+      "grad_norm": 2.0818440914154053,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.4927,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.946469637318246e+16,
+  "total_flos": 8.887031545882214e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null