Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0670a2f4b1af5ccbb7ea6970ee6fd24c2919450deb2d16ef6192e6e623caf31c
+oid sha256:9d34d71f8825932dc4b813ddd8f11a961d3595fddaf89feac2a2a9083ca267c9
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3ba09b828260d0c33d289960c9f4ffd0f3d1d58151ceafe52514f54b60f2f87
+oid sha256:e2e16e3fb8e0b0e83ca85159b5e8e15a0b4a14be37e70ecebd113770f6cfe8c4
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a27a5bb4340a5dea0246d6a323f12ff69757e73a88f4cb2d3f1178c8018026
+oid sha256:67d7d79dbbf87075183d0fdf4878a76a739fb585d2d494d287dd89526ca60516
 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": 0.0021930305489155466,
+  "epoch": 0.0032895458233733197,
   "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": 10.3426,
       "step": 50
+    },
+    {
+      "epoch": 0.0022368911598938572,
+      "grad_norm": 0.2247057557106018,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3506,
+      "step": 51
+    },
+    {
+      "epoch": 0.0022807517708721683,
+      "grad_norm": 0.18720436096191406,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.358,
+      "step": 52
+    },
+    {
+      "epoch": 0.0023246123818504794,
+      "grad_norm": 0.19579781591892242,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3548,
+      "step": 53
+    },
+    {
+      "epoch": 0.00236847299282879,
+      "grad_norm": 0.12509997189044952,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3671,
+      "step": 54
+    },
+    {
+      "epoch": 0.00236847299282879,
+      "eval_loss": 10.352391242980957,
+      "eval_runtime": 286.4387,
+      "eval_samples_per_second": 67.03,
+      "eval_steps_per_second": 8.379,
+      "step": 54
+    },
+    {
+      "epoch": 0.002412333603807101,
+      "grad_norm": 0.14832502603530884,
+      "learning_rate": 5e-05,
+      "loss": 10.3538,
+      "step": 55
+    },
+    {
+      "epoch": 0.0024561942147854118,
+      "grad_norm": 0.1959301084280014,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3498,
+      "step": 56
+    },
+    {
+      "epoch": 0.002500054825763723,
+      "grad_norm": 0.21363425254821777,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.363,
+      "step": 57
+    },
+    {
+      "epoch": 0.002543915436742034,
+      "grad_norm": 0.12494485080242157,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3565,
+      "step": 58
+    },
+    {
+      "epoch": 0.0025877760477203446,
+      "grad_norm": 0.19558563828468323,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3621,
+      "step": 59
+    },
+    {
+      "epoch": 0.0026316366586986556,
+      "grad_norm": 0.185495525598526,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3486,
+      "step": 60
+    },
+    {
+      "epoch": 0.0026754972696769667,
+      "grad_norm": 0.21020500361919403,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.3453,
+      "step": 61
+    },
+    {
+      "epoch": 0.0027193578806552774,
+      "grad_norm": 0.2363358736038208,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3425,
+      "step": 62
+    },
+    {
+      "epoch": 0.0027632184916335885,
+      "grad_norm": 0.270352303981781,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3452,
+      "step": 63
+    },
+    {
+      "epoch": 0.0027632184916335885,
+      "eval_loss": 10.349072456359863,
+      "eval_runtime": 286.3258,
+      "eval_samples_per_second": 67.056,
+      "eval_steps_per_second": 8.382,
+      "step": 63
+    },
+    {
+      "epoch": 0.0028070791026118995,
+      "grad_norm": 0.21777836978435516,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3522,
+      "step": 64
+    },
+    {
+      "epoch": 0.00285093971359021,
+      "grad_norm": 0.29503583908081055,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3568,
+      "step": 65
+    },
+    {
+      "epoch": 0.0028948003245685213,
+      "grad_norm": 0.29024678468704224,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3352,
+      "step": 66
+    },
+    {
+      "epoch": 0.0029386609355468323,
+      "grad_norm": 0.22545352578163147,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3506,
+      "step": 67
+    },
+    {
+      "epoch": 0.002982521546525143,
+      "grad_norm": 0.23708412051200867,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3354,
+      "step": 68
+    },
+    {
+      "epoch": 0.003026382157503454,
+      "grad_norm": 0.22012007236480713,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3486,
+      "step": 69
+    },
+    {
+      "epoch": 0.003070242768481765,
+      "grad_norm": 0.21860839426517487,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3508,
+      "step": 70
+    },
+    {
+      "epoch": 0.003114103379460076,
+      "grad_norm": 0.2507653534412384,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3356,
+      "step": 71
+    },
+    {
+      "epoch": 0.003157963990438387,
+      "grad_norm": 0.26605838537216187,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3328,
+      "step": 72
+    },
+    {
+      "epoch": 0.003157963990438387,
+      "eval_loss": 10.346505165100098,
+      "eval_runtime": 286.401,
+      "eval_samples_per_second": 67.039,
+      "eval_steps_per_second": 8.38,
+      "step": 72
+    },
+    {
+      "epoch": 0.003201824601416698,
+      "grad_norm": 0.19735638797283173,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3472,
+      "step": 73
+    },
+    {
+      "epoch": 0.0032456852123950086,
+      "grad_norm": 0.24469499289989471,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.3426,
+      "step": 74
+    },
+    {
+      "epoch": 0.0032895458233733197,
+      "grad_norm": 0.22693535685539246,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3425,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4785673863168.0,
+  "total_flos": 7139283959808.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null