Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06d63e1cb1fdb0b6ca5fecb1669687ba0a79fff92708ed2efb572d77f306c1bb
+oid sha256:ba10fcc8359141bdc76749bfe804bf1854c7c35161cb682341218e2174e7389e
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f0ba882b4b5a3d2c9b16f849d82d52936054968a9dfe94e1efc2955ffebc38
+oid sha256:c1b73c40de3df8179743b16e333529d91bc1cbc4d729d0b6a0dbb0a2743c526a
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d8240f8b64502e023794a3da2d8c6aa526ac0f753e37b389fdd87097fabd55
+oid sha256:e0c7f44ec6860003f13de57bd2ad679abc76372e696f0ba64dcb096ad8c2d194
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f117663bca47e6dbbfa0c77eb3eb3ed1ed85a3dd0c9f866227e737a73eb5c422
+oid sha256:bd6efc3cf2283ba2318df09b4fccd81fc2c7c92f336f9b8fbed31252acffe51a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7d87a0b1f18c774b632725605bde69fd2b07215dcf9ac48e19e6caa47a6c61
+oid sha256:8ec5a5fa365a025d7b72e73ba5ae61435c717d5192c0a548efd67efffa7d01f8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3daeca24213bd8e7f686bd89b9bb6ba8b6995471fd68b15febf485beb753100
+oid sha256:4ef8374d5b4a7b565c654f01afc3676c24946d4955ee4d27506c6d5576f109d2
 size 15024

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": 0.273224043715847,
+  "epoch": 0.4098360655737705,
   "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": 10.3745,
       "step": 50
+    },
+    {
+      "epoch": 0.2786885245901639,
+      "grad_norm": 0.04402737319469452,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3748,
+      "step": 51
+    },
+    {
+      "epoch": 0.28415300546448086,
+      "grad_norm": 0.04508426785469055,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3746,
+      "step": 52
+    },
+    {
+      "epoch": 0.2896174863387978,
+      "grad_norm": 0.04800768941640854,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3748,
+      "step": 53
+    },
+    {
+      "epoch": 0.29508196721311475,
+      "grad_norm": 0.04819543659687042,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3755,
+      "step": 54
+    },
+    {
+      "epoch": 0.29508196721311475,
+      "eval_loss": 10.374573707580566,
+      "eval_runtime": 0.8298,
+      "eval_samples_per_second": 742.379,
+      "eval_steps_per_second": 24.103,
+      "step": 54
+    },
+    {
+      "epoch": 0.3005464480874317,
+      "grad_norm": 0.051205698400735855,
+      "learning_rate": 5e-05,
+      "loss": 10.375,
+      "step": 55
+    },
+    {
+      "epoch": 0.30601092896174864,
+      "grad_norm": 0.05164771154522896,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3743,
+      "step": 56
+    },
+    {
+      "epoch": 0.3114754098360656,
+      "grad_norm": 0.05184890702366829,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3746,
+      "step": 57
+    },
+    {
+      "epoch": 0.31693989071038253,
+      "grad_norm": 0.05557376146316528,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3744,
+      "step": 58
+    },
+    {
+      "epoch": 0.3224043715846995,
+      "grad_norm": 0.054270245134830475,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3743,
+      "step": 59
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 0.05667842924594879,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3747,
+      "step": 60
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.059168748557567596,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.3726,
+      "step": 61
+    },
+    {
+      "epoch": 0.33879781420765026,
+      "grad_norm": 0.05808443948626518,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3739,
+      "step": 62
+    },
+    {
+      "epoch": 0.3442622950819672,
+      "grad_norm": 0.05408474802970886,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3742,
+      "step": 63
+    },
+    {
+      "epoch": 0.3442622950819672,
+      "eval_loss": 10.373579025268555,
+      "eval_runtime": 0.836,
+      "eval_samples_per_second": 736.823,
+      "eval_steps_per_second": 23.923,
+      "step": 63
+    },
+    {
+      "epoch": 0.34972677595628415,
+      "grad_norm": 0.05801790952682495,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3738,
+      "step": 64
+    },
+    {
+      "epoch": 0.3551912568306011,
+      "grad_norm": 0.05648942291736603,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3744,
+      "step": 65
+    },
+    {
+      "epoch": 0.36065573770491804,
+      "grad_norm": 0.056558702141046524,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3727,
+      "step": 66
+    },
+    {
+      "epoch": 0.366120218579235,
+      "grad_norm": 0.057507459074258804,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3728,
+      "step": 67
+    },
+    {
+      "epoch": 0.37158469945355194,
+      "grad_norm": 0.06369660794734955,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3734,
+      "step": 68
+    },
+    {
+      "epoch": 0.3770491803278688,
+      "grad_norm": 0.06289859116077423,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.373,
+      "step": 69
+    },
+    {
+      "epoch": 0.3825136612021858,
+      "grad_norm": 0.06389268487691879,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3732,
+      "step": 70
+    },
+    {
+      "epoch": 0.3879781420765027,
+      "grad_norm": 0.06123030185699463,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3719,
+      "step": 71
+    },
+    {
+      "epoch": 0.39344262295081966,
+      "grad_norm": 0.06595779210329056,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.373,
+      "step": 72
+    },
+    {
+      "epoch": 0.39344262295081966,
+      "eval_loss": 10.372864723205566,
+      "eval_runtime": 0.8341,
+      "eval_samples_per_second": 738.515,
+      "eval_steps_per_second": 23.978,
+      "step": 72
+    },
+    {
+      "epoch": 0.3989071038251366,
+      "grad_norm": 0.06698242574930191,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3733,
+      "step": 73
+    },
+    {
+      "epoch": 0.40437158469945356,
+      "grad_norm": 0.06163797155022621,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.373,
+      "step": 74
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "grad_norm": 0.06621850281953812,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3736,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 20920978636800.0,
+  "total_flos": 31381467955200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null