Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f5c558cd109ecdab8ac6da366fdb75e5d86d07263a247ec16ec5c9d91ebeb
+oid sha256:009a4577ea9f39ac432b86286d492354281723bf3499d281e3142b4d7a01e9b6
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaa9359d97df4c1fcb4e1c0b120c1524db04db6cb306695d6770c1773825f130
+oid sha256:9d119c656e6b5819f5214e6ecbf80c1aeaa8e2cceaf763dcc7d498652468e6f7
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b60062fc375f7f1c4e484b5943687b640607aed4dd62534dae2acdd19d81a447
+oid sha256:68c2a2b6c14c41c8ac1cc853bb5193f411312de8e64dc95fc7f6bdf424a267af
 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": 0.0135464643727987,
+  "epoch": 0.02031969655919805,
   "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": 2.8472,
       "step": 50
+    },
+    {
+      "epoch": 0.013817393660254673,
+      "grad_norm": 1.7614214420318604,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 3.1347,
+      "step": 51
+    },
+    {
+      "epoch": 0.014088322947710648,
+      "grad_norm": 1.6398626565933228,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 3.2098,
+      "step": 52
+    },
+    {
+      "epoch": 0.014359252235166622,
+      "grad_norm": 1.405993938446045,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 2.858,
+      "step": 53
+    },
+    {
+      "epoch": 0.014630181522622595,
+      "grad_norm": 1.9929529428482056,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.2367,
+      "step": 54
+    },
+    {
+      "epoch": 0.014630181522622595,
+      "eval_loss": 1.6083791255950928,
+      "eval_runtime": 234.097,
+      "eval_samples_per_second": 13.277,
+      "eval_steps_per_second": 1.662,
+      "step": 54
+    },
+    {
+      "epoch": 0.014901110810078569,
+      "grad_norm": 1.4126490354537964,
+      "learning_rate": 5e-05,
+      "loss": 3.062,
+      "step": 55
+    },
+    {
+      "epoch": 0.015172040097534544,
+      "grad_norm": 1.6564135551452637,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 3.5186,
+      "step": 56
+    },
+    {
+      "epoch": 0.015442969384990518,
+      "grad_norm": 2.3048603534698486,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 3.425,
+      "step": 57
+    },
+    {
+      "epoch": 0.01571389867244649,
+      "grad_norm": 2.091020107269287,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 3.7023,
+      "step": 58
+    },
+    {
+      "epoch": 0.015984827959902467,
+      "grad_norm": 1.5611733198165894,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 3.481,
+      "step": 59
+    },
+    {
+      "epoch": 0.01625575724735844,
+      "grad_norm": 1.8734015226364136,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.9785,
+      "step": 60
+    },
+    {
+      "epoch": 0.016526686534814414,
+      "grad_norm": 1.6963518857955933,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.8544,
+      "step": 61
+    },
+    {
+      "epoch": 0.01679761582227039,
+      "grad_norm": 1.8010172843933105,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 3.151,
+      "step": 62
+    },
+    {
+      "epoch": 0.01706854510972636,
+      "grad_norm": 1.5065714120864868,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.8421,
+      "step": 63
+    },
+    {
+      "epoch": 0.01706854510972636,
+      "eval_loss": 1.5903106927871704,
+      "eval_runtime": 234.0281,
+      "eval_samples_per_second": 13.28,
+      "eval_steps_per_second": 1.662,
+      "step": 63
+    },
+    {
+      "epoch": 0.017339474397182336,
+      "grad_norm": 1.854354739189148,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.0782,
+      "step": 64
+    },
+    {
+      "epoch": 0.017610403684638308,
+      "grad_norm": 1.5748767852783203,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.017881332972094283,
+      "grad_norm": 2.1482014656066895,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.9115,
+      "step": 66
+    },
+    {
+      "epoch": 0.01815226225955026,
+      "grad_norm": 1.5997191667556763,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 3.0273,
+      "step": 67
+    },
+    {
+      "epoch": 0.01842319154700623,
+      "grad_norm": 1.9772167205810547,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 3.3768,
+      "step": 68
+    },
+    {
+      "epoch": 0.018694120834462206,
+      "grad_norm": 1.9302130937576294,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 3.3976,
+      "step": 69
+    },
+    {
+      "epoch": 0.01896505012191818,
+      "grad_norm": 1.626615047454834,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.3308,
+      "step": 70
+    },
+    {
+      "epoch": 0.019235979409374153,
+      "grad_norm": 2.0286331176757812,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 3.3103,
+      "step": 71
+    },
+    {
+      "epoch": 0.019506908696830128,
+      "grad_norm": 2.0638129711151123,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.4762,
+      "step": 72
+    },
+    {
+      "epoch": 0.019506908696830128,
+      "eval_loss": 1.576021671295166,
+      "eval_runtime": 233.8565,
+      "eval_samples_per_second": 13.29,
+      "eval_steps_per_second": 1.663,
+      "step": 72
+    },
+    {
+      "epoch": 0.0197778379842861,
+      "grad_norm": 1.4248108863830566,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.6845,
+      "step": 73
+    },
+    {
+      "epoch": 0.020048767271742075,
+      "grad_norm": 2.354829788208008,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.6582,
+      "step": 74
+    },
+    {
+      "epoch": 0.02031969655919805,
+      "grad_norm": 1.7262550592422485,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 3.2972,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.474786561589248e+16,
+  "total_flos": 9.83913644163072e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null