Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f751ad6160e762c4b006f79963a7b53c810e69ab71b876b88a876648e91997
+oid sha256:f9160af0804bec34475815f42631e27b800fd19c04242c2ce15c1095a6d9ec56
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac37eddc8bd48eca02de03f4b9c253ef9cbb0cf3b50605d169105d1881a1e652
+oid sha256:6bade7744e6e97a7b031f341c33d2a22efb3f987ca31119f9677db3af1ca5d1a
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:120fcf9c3a75bd5c2156ac7d096d72915b4ccc5583b3dbb62241c1dcc237a5bc
+oid sha256:7cc53caa9ee29aa5549541f2de9dd6caf73aa7da168afdee6aa75fb8a93119dd
 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": 0.07942811755361398,
+  "epoch": 0.11914217633042097,
   "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": 0.8163,
       "step": 50
+    },
+    {
+      "epoch": 0.08101667990468626,
+      "grad_norm": 2.8380324840545654,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.8139,
+      "step": 51
+    },
+    {
+      "epoch": 0.08260524225575853,
+      "grad_norm": 0.9675163626670837,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.3775,
+      "step": 52
+    },
+    {
+      "epoch": 0.08419380460683082,
+      "grad_norm": 2.7258806228637695,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.2049,
+      "step": 53
+    },
+    {
+      "epoch": 0.0857823669579031,
+      "grad_norm": 1.352913737297058,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.7722,
+      "step": 54
+    },
+    {
+      "epoch": 0.0857823669579031,
+      "eval_loss": 0.7361476421356201,
+      "eval_runtime": 25.0673,
+      "eval_samples_per_second": 21.143,
+      "eval_steps_per_second": 2.673,
+      "step": 54
+    },
+    {
+      "epoch": 0.08737092930897537,
+      "grad_norm": 2.3246042728424072,
+      "learning_rate": 5e-05,
+      "loss": 0.7954,
+      "step": 55
+    },
+    {
+      "epoch": 0.08895949166004766,
+      "grad_norm": 1.1780191659927368,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.0354,
+      "step": 56
+    },
+    {
+      "epoch": 0.09054805401111994,
+      "grad_norm": 2.115222930908203,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.6829,
+      "step": 57
+    },
+    {
+      "epoch": 0.09213661636219221,
+      "grad_norm": 1.4351661205291748,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.5475,
+      "step": 58
+    },
+    {
+      "epoch": 0.0937251787132645,
+      "grad_norm": 3.4773356914520264,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.6846,
+      "step": 59
+    },
+    {
+      "epoch": 0.09531374106433678,
+      "grad_norm": 1.848775029182434,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.5564,
+      "step": 60
+    },
+    {
+      "epoch": 0.09690230341540905,
+      "grad_norm": 3.542532444000244,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.605,
+      "step": 61
+    },
+    {
+      "epoch": 0.09849086576648133,
+      "grad_norm": 1.1068249940872192,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.5019,
+      "step": 62
+    },
+    {
+      "epoch": 0.10007942811755362,
+      "grad_norm": 1.011226773262024,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.6327,
+      "step": 63
+    },
+    {
+      "epoch": 0.10007942811755362,
+      "eval_loss": 0.6306856870651245,
+      "eval_runtime": 24.7366,
+      "eval_samples_per_second": 21.426,
+      "eval_steps_per_second": 2.709,
+      "step": 63
+    },
+    {
+      "epoch": 0.10166799046862589,
+      "grad_norm": 0.9041082262992859,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2446,
+      "step": 64
+    },
+    {
+      "epoch": 0.10325655281969817,
+      "grad_norm": 1.7981657981872559,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.3239,
+      "step": 65
+    },
+    {
+      "epoch": 0.10484511517077046,
+      "grad_norm": 1.7157872915267944,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.5888,
+      "step": 66
+    },
+    {
+      "epoch": 0.10643367752184273,
+      "grad_norm": 1.5570635795593262,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.9827,
+      "step": 67
+    },
+    {
+      "epoch": 0.10802223987291501,
+      "grad_norm": 1.05362868309021,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.6535,
+      "step": 68
+    },
+    {
+      "epoch": 0.1096108022239873,
+      "grad_norm": 1.386989951133728,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.8059,
+      "step": 69
+    },
+    {
+      "epoch": 0.11119936457505956,
+      "grad_norm": 1.5930371284484863,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8848,
+      "step": 70
+    },
+    {
+      "epoch": 0.11278792692613185,
+      "grad_norm": 0.6902157664299011,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.1778,
+      "step": 71
+    },
+    {
+      "epoch": 0.11437648927720413,
+      "grad_norm": 1.5689494609832764,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.6893,
+      "step": 72
+    },
+    {
+      "epoch": 0.11437648927720413,
+      "eval_loss": 0.571943998336792,
+      "eval_runtime": 25.0278,
+      "eval_samples_per_second": 21.176,
+      "eval_steps_per_second": 2.677,
+      "step": 72
+    },
+    {
+      "epoch": 0.11596505162827642,
+      "grad_norm": 1.9662429094314575,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.8679,
+      "step": 73
+    },
+    {
+      "epoch": 0.11755361397934869,
+      "grad_norm": 0.8315130472183228,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.3787,
+      "step": 74
+    },
+    {
+      "epoch": 0.11914217633042097,
+      "grad_norm": 1.5936318635940552,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.8645,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6822444115427328.0,
+  "total_flos": 1.0306245365858304e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null