Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4269d82abd9179a7a9024ce06b0ea2a05fb71f53202556a2609142877c205219
+oid sha256:9b3e02e5130c16a502b24d52a2e0dbd62ef0b74949f1907f03ddc3917e021df7
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e48e3a967b10047686c2d3922b6ee9568d73684d1db0da2e9bdaaafa4b43a69c
+oid sha256:cc6ba7c38fd7bdb7a45620895016f085b752a6a6cd34f4b667eeec88d4f06e2a
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33752213e91e5d9daaf41b0e911b3b2623b16a8672150d6b365a88ada68018bd
+oid sha256:f4e42707bff3a01dd441022647b82d0d244a8f2409373d258e9184fc37cc91af
 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": 0.352112676056338,
+  "epoch": 0.528169014084507,
   "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": 10.3554,
       "step": 50
+    },
+    {
+      "epoch": 0.3591549295774648,
+      "grad_norm": 0.34007278084754944,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.35,
+      "step": 51
+    },
+    {
+      "epoch": 0.36619718309859156,
+      "grad_norm": 0.4468972384929657,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3637,
+      "step": 52
+    },
+    {
+      "epoch": 0.3732394366197183,
+      "grad_norm": 0.3781704902648926,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3758,
+      "step": 53
+    },
+    {
+      "epoch": 0.38028169014084506,
+      "grad_norm": 0.44845354557037354,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3479,
+      "step": 54
+    },
+    {
+      "epoch": 0.38028169014084506,
+      "eval_loss": 10.359603881835938,
+      "eval_runtime": 0.504,
+      "eval_samples_per_second": 238.083,
+      "eval_steps_per_second": 29.76,
+      "step": 54
+    },
+    {
+      "epoch": 0.3873239436619718,
+      "grad_norm": 0.38202252984046936,
+      "learning_rate": 5e-05,
+      "loss": 10.3515,
+      "step": 55
+    },
+    {
+      "epoch": 0.39436619718309857,
+      "grad_norm": 0.43705958127975464,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3376,
+      "step": 56
+    },
+    {
+      "epoch": 0.4014084507042254,
+      "grad_norm": 0.4019726812839508,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3409,
+      "step": 57
+    },
+    {
+      "epoch": 0.4084507042253521,
+      "grad_norm": 0.41095566749572754,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3169,
+      "step": 58
+    },
+    {
+      "epoch": 0.4154929577464789,
+      "grad_norm": 0.402935653924942,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3601,
+      "step": 59
+    },
+    {
+      "epoch": 0.4225352112676056,
+      "grad_norm": 0.45852792263031006,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3804,
+      "step": 60
+    },
+    {
+      "epoch": 0.4295774647887324,
+      "grad_norm": 0.4683137536048889,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.373,
+      "step": 61
+    },
+    {
+      "epoch": 0.43661971830985913,
+      "grad_norm": 0.47680333256721497,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3482,
+      "step": 62
+    },
+    {
+      "epoch": 0.44366197183098594,
+      "grad_norm": 0.4151249825954437,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3576,
+      "step": 63
+    },
+    {
+      "epoch": 0.44366197183098594,
+      "eval_loss": 10.351668357849121,
+      "eval_runtime": 0.4911,
+      "eval_samples_per_second": 244.326,
+      "eval_steps_per_second": 30.541,
+      "step": 63
+    },
+    {
+      "epoch": 0.4507042253521127,
+      "grad_norm": 0.3624146580696106,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3636,
+      "step": 64
+    },
+    {
+      "epoch": 0.45774647887323944,
+      "grad_norm": 0.47819146513938904,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3438,
+      "step": 65
+    },
+    {
+      "epoch": 0.4647887323943662,
+      "grad_norm": 0.3400690257549286,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3488,
+      "step": 66
+    },
+    {
+      "epoch": 0.47183098591549294,
+      "grad_norm": 0.4769725799560547,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3423,
+      "step": 67
+    },
+    {
+      "epoch": 0.4788732394366197,
+      "grad_norm": 0.3802928030490875,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3375,
+      "step": 68
+    },
+    {
+      "epoch": 0.4859154929577465,
+      "grad_norm": 0.374841570854187,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3634,
+      "step": 69
+    },
+    {
+      "epoch": 0.49295774647887325,
+      "grad_norm": 0.4511743187904358,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3315,
+      "step": 70
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.42619290947914124,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3358,
+      "step": 71
+    },
+    {
+      "epoch": 0.5070422535211268,
+      "grad_norm": 0.44817185401916504,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3273,
+      "step": 72
+    },
+    {
+      "epoch": 0.5070422535211268,
+      "eval_loss": 10.346145629882812,
+      "eval_runtime": 0.499,
+      "eval_samples_per_second": 240.461,
+      "eval_steps_per_second": 30.058,
+      "step": 72
+    },
+    {
+      "epoch": 0.5140845070422535,
+      "grad_norm": 0.4042167365550995,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3548,
+      "step": 73
+    },
+    {
+      "epoch": 0.5211267605633803,
+      "grad_norm": 0.40181946754455566,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.3526,
+      "step": 74
+    },
+    {
+      "epoch": 0.528169014084507,
+      "grad_norm": 0.45714980363845825,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3526,
+      "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