Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9864ab2c5780e25adb0494d6c344dd9711eee0cbd335ab83b16d66cd907959e6
+oid sha256:65dd7d9da1c1101013c9cc3c1d65ad58f85a2e7406d04c5e552b3591cc01952d
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0310726acd9f6ef02359b54eae6ba88d5bd46c52cccfa23c1b5d612d4f46a5
+oid sha256:367e6368a618034ed3d27c1e1075095d075ac1453bccbef2e048af279bcbd2b4
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72fe4aa95deebd7e422509cc58431e3d02f7b987fff0e4beaf0cb67e66825c20
+oid sha256:b3d44637ce5e861ad816fd68fdeece15df6bfd52efa4d86d6394515a6a4dcaa3
 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": 0.6622516556291391,
+  "epoch": 0.9933774834437086,
   "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": 0.6905,
       "step": 50
+    },
+    {
+      "epoch": 0.6754966887417219,
+      "grad_norm": 0.907538115978241,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.6916,
+      "step": 51
+    },
+    {
+      "epoch": 0.6887417218543046,
+      "grad_norm": 1.336814284324646,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.7712,
+      "step": 52
+    },
+    {
+      "epoch": 0.7019867549668874,
+      "grad_norm": 1.2433383464813232,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.7603,
+      "step": 53
+    },
+    {
+      "epoch": 0.7152317880794702,
+      "grad_norm": 1.756962537765503,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.8239,
+      "step": 54
+    },
+    {
+      "epoch": 0.7152317880794702,
+      "eval_loss": 0.7315835952758789,
+      "eval_runtime": 6.6393,
+      "eval_samples_per_second": 9.64,
+      "eval_steps_per_second": 1.205,
+      "step": 54
+    },
+    {
+      "epoch": 0.7284768211920529,
+      "grad_norm": 0.9817075729370117,
+      "learning_rate": 5e-05,
+      "loss": 0.73,
+      "step": 55
+    },
+    {
+      "epoch": 0.7417218543046358,
+      "grad_norm": 2.438516616821289,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.8745,
+      "step": 56
+    },
+    {
+      "epoch": 0.7549668874172185,
+      "grad_norm": 1.679138422012329,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.7307,
+      "step": 57
+    },
+    {
+      "epoch": 0.7682119205298014,
+      "grad_norm": 1.0264722108840942,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.7304,
+      "step": 58
+    },
+    {
+      "epoch": 0.7814569536423841,
+      "grad_norm": 1.0093244314193726,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.6724,
+      "step": 59
+    },
+    {
+      "epoch": 0.7947019867549668,
+      "grad_norm": 1.3939509391784668,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.7248,
+      "step": 60
+    },
+    {
+      "epoch": 0.8079470198675497,
+      "grad_norm": 0.9721545577049255,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.7113,
+      "step": 61
+    },
+    {
+      "epoch": 0.8211920529801324,
+      "grad_norm": 1.4262372255325317,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.7401,
+      "step": 62
+    },
+    {
+      "epoch": 0.8344370860927153,
+      "grad_norm": 1.2473621368408203,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.7057,
+      "step": 63
+    },
+    {
+      "epoch": 0.8344370860927153,
+      "eval_loss": 0.7136833071708679,
+      "eval_runtime": 6.6384,
+      "eval_samples_per_second": 9.641,
+      "eval_steps_per_second": 1.205,
+      "step": 63
+    },
+    {
+      "epoch": 0.847682119205298,
+      "grad_norm": 1.1054190397262573,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.7594,
+      "step": 64
+    },
+    {
+      "epoch": 0.8609271523178808,
+      "grad_norm": 0.7941734790802002,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.7026,
+      "step": 65
+    },
+    {
+      "epoch": 0.8741721854304636,
+      "grad_norm": 0.9560126066207886,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.8565,
+      "step": 66
+    },
+    {
+      "epoch": 0.8874172185430463,
+      "grad_norm": 0.5420722961425781,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.7,
+      "step": 67
+    },
+    {
+      "epoch": 0.9006622516556292,
+      "grad_norm": 0.9435858726501465,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.6881,
+      "step": 68
+    },
+    {
+      "epoch": 0.9139072847682119,
+      "grad_norm": 1.6616233587265015,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.7059,
+      "step": 69
+    },
+    {
+      "epoch": 0.9271523178807947,
+      "grad_norm": 0.9454774856567383,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6937,
+      "step": 70
+    },
+    {
+      "epoch": 0.9403973509933775,
+      "grad_norm": 0.6445388197898865,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.6944,
+      "step": 71
+    },
+    {
+      "epoch": 0.9536423841059603,
+      "grad_norm": 0.8330978155136108,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.7133,
+      "step": 72
+    },
+    {
+      "epoch": 0.9536423841059603,
+      "eval_loss": 0.6958786845207214,
+      "eval_runtime": 6.6461,
+      "eval_samples_per_second": 9.63,
+      "eval_steps_per_second": 1.204,
+      "step": 72
+    },
+    {
+      "epoch": 0.9668874172185431,
+      "grad_norm": 0.5194578766822815,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.7037,
+      "step": 73
+    },
+    {
+      "epoch": 0.9801324503311258,
+      "grad_norm": 1.3144248723983765,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.7114,
+      "step": 74
+    },
+    {
+      "epoch": 0.9933774834437086,
+      "grad_norm": 1.1942020654678345,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.6967,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6463460040704e+16,
+  "total_flos": 2.4695190061056e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null