Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bbcde4cfa01463b2b127e5e23714f2f90debc9e3e722328670f98410cac8364
+oid sha256:0844fd14e4606b7dc1b8ea679b4b7a63d63588748f22d31f748b3b39e9140e0b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a44a38f71ee75703bb570e8101481509bdf3085c448c97d9b3f941b5573bcf7
+oid sha256:66f54b3b38477bb452dc3bbe3278736486e816fbb05b324bb5abd5521e55a30c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
+oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
 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": 0.008443093549476529,
+  "epoch": 0.012664640324214792,
   "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": 0.0626,
       "step": 50
+    },
+    {
+      "epoch": 0.008611955420466059,
+      "grad_norm": 1.935459852218628,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.0458,
+      "step": 51
+    },
+    {
+      "epoch": 0.008780817291455589,
+      "grad_norm": 4.436528205871582,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.2329,
+      "step": 52
+    },
+    {
+      "epoch": 0.00894967916244512,
+      "grad_norm": 5.652027130126953,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.246,
+      "step": 53
+    },
+    {
+      "epoch": 0.00911854103343465,
+      "grad_norm": 2.375805616378784,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0326,
+      "step": 54
+    },
+    {
+      "epoch": 0.00911854103343465,
+      "eval_loss": 0.09233339130878448,
+      "eval_runtime": 549.7539,
+      "eval_samples_per_second": 9.071,
+      "eval_steps_per_second": 1.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.009287402904424182,
+      "grad_norm": 3.6387789249420166,
+      "learning_rate": 5e-05,
+      "loss": 0.2236,
+      "step": 55
+    },
+    {
+      "epoch": 0.009456264775413711,
+      "grad_norm": 2.7353525161743164,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.137,
+      "step": 56
+    },
+    {
+      "epoch": 0.009625126646403243,
+      "grad_norm": 4.310062885284424,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.2697,
+      "step": 57
+    },
+    {
+      "epoch": 0.009793988517392773,
+      "grad_norm": 4.689754486083984,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.1093,
+      "step": 58
+    },
+    {
+      "epoch": 0.009962850388382303,
+      "grad_norm": 0.28570395708084106,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.0058,
+      "step": 59
+    },
+    {
+      "epoch": 0.010131712259371834,
+      "grad_norm": 2.6869800090789795,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1282,
+      "step": 60
+    },
+    {
+      "epoch": 0.010300574130361364,
+      "grad_norm": 3.4605836868286133,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.0432,
+      "step": 61
+    },
+    {
+      "epoch": 0.010469436001350895,
+      "grad_norm": 2.410428047180176,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0395,
+      "step": 62
+    },
+    {
+      "epoch": 0.010638297872340425,
+      "grad_norm": 0.8962574005126953,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.0161,
+      "step": 63
+    },
+    {
+      "epoch": 0.010638297872340425,
+      "eval_loss": 0.08070806413888931,
+      "eval_runtime": 548.9743,
+      "eval_samples_per_second": 9.084,
+      "eval_steps_per_second": 1.137,
+      "step": 63
+    },
+    {
+      "epoch": 0.010807159743329957,
+      "grad_norm": 2.4982762336730957,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1033,
+      "step": 64
+    },
+    {
+      "epoch": 0.010976021614319487,
+      "grad_norm": 2.2008962631225586,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0379,
+      "step": 65
+    },
+    {
+      "epoch": 0.011144883485309016,
+      "grad_norm": 2.7710535526275635,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.056,
+      "step": 66
+    },
+    {
+      "epoch": 0.011313745356298548,
+      "grad_norm": 1.5169901847839355,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.1376,
+      "step": 67
+    },
+    {
+      "epoch": 0.011482607227288078,
+      "grad_norm": 4.770974636077881,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.2865,
+      "step": 68
+    },
+    {
+      "epoch": 0.01165146909827761,
+      "grad_norm": 1.257779836654663,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0276,
+      "step": 69
+    },
+    {
+      "epoch": 0.01182033096926714,
+      "grad_norm": 1.8166325092315674,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0374,
+      "step": 70
+    },
+    {
+      "epoch": 0.01198919284025667,
+      "grad_norm": 2.774444103240967,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.0976,
+      "step": 71
+    },
+    {
+      "epoch": 0.0121580547112462,
+      "grad_norm": 2.698269844055176,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.144,
+      "step": 72
+    },
+    {
+      "epoch": 0.0121580547112462,
+      "eval_loss": 0.0661754235625267,
+      "eval_runtime": 548.8204,
+      "eval_samples_per_second": 9.087,
+      "eval_steps_per_second": 1.137,
+      "step": 72
+    },
+    {
+      "epoch": 0.01232691658223573,
+      "grad_norm": 0.39094191789627075,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0049,
+      "step": 73
+    },
+    {
+      "epoch": 0.012495778453225262,
+      "grad_norm": 1.9535773992538452,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0903,
+      "step": 74
+    },
+    {
+      "epoch": 0.012664640324214792,
+      "grad_norm": 4.114951133728027,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.2374,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.70943641780224e+16,
+  "total_flos": 5.56415462670336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null