Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c2df089393595e1c13cce41d64a5100271db96a5ff4df0da5ba90e3d60524a
+oid sha256:f80f31c66cfcd979223772a01c415ed3429014477ba1eda834586f3faaff1fda
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34f059b07f2f9fa415e046447202262f8639c93508831f205a1d46bfdb5e1537
+oid sha256:040d965d53986f166048d2421e1f5dd743a1fdf0c7dabde55d380ddb2e39c887
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afbbeff9c2106aa6747a9a6b6d1f2974325978cb30b288d183425c5cf2062c3
+oid sha256:997b37e8e4d4313266e5aafe8f4d418b086633a9c94b4c13db86ae839aa09b15
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8eccac390378b22aeb148c260b00bec01d948946d8363d5282899af673e0e86
+oid sha256:beb167787cdd9594eed637547cf4a56f4a4d8ea359757a120c76bb5d91190782
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025396825396825397,
+  "epoch": 0.0380952380952381,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 4.022,
       "eval_steps_per_second": 2.013,
       "step": 50
+    },
+    {
+      "epoch": 0.025904761904761906,
+      "grad_norm": 0.33596453070640564,
+      "learning_rate": 0.00011391731009600654,
+      "loss": 1.5421,
+      "step": 51
+    },
+    {
+      "epoch": 0.026412698412698412,
+      "grad_norm": 0.2696133852005005,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.3148,
+      "step": 52
+    },
+    {
+      "epoch": 0.02692063492063492,
+      "grad_norm": 0.5372976660728455,
+      "learning_rate": 0.00010697564737441252,
+      "loss": 1.64,
+      "step": 53
+    },
+    {
+      "epoch": 0.027428571428571427,
+      "grad_norm": 0.6545993089675903,
+      "learning_rate": 0.00010348994967025012,
+      "loss": 1.2776,
+      "step": 54
+    },
+    {
+      "epoch": 0.027936507936507936,
+      "grad_norm": 0.2829376757144928,
+      "learning_rate": 0.0001,
+      "loss": 1.2245,
+      "step": 55
+    },
+    {
+      "epoch": 0.028444444444444446,
+      "grad_norm": 0.3656099736690521,
+      "learning_rate": 9.651005032974994e-05,
+      "loss": 1.4617,
+      "step": 56
+    },
+    {
+      "epoch": 0.02895238095238095,
+      "grad_norm": 0.3836618959903717,
+      "learning_rate": 9.302435262558747e-05,
+      "loss": 1.2219,
+      "step": 57
+    },
+    {
+      "epoch": 0.02946031746031746,
+      "grad_norm": 0.30446094274520874,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.5095,
+      "step": 58
+    },
+    {
+      "epoch": 0.029968253968253967,
+      "grad_norm": 0.4856981635093689,
+      "learning_rate": 8.608268990399349e-05,
+      "loss": 1.5771,
+      "step": 59
+    },
+    {
+      "epoch": 0.030476190476190476,
+      "grad_norm": 0.45834746956825256,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 1.3313,
+      "step": 60
+    },
+    {
+      "epoch": 0.030984126984126985,
+      "grad_norm": 0.3143262267112732,
+      "learning_rate": 7.920883091822408e-05,
+      "loss": 1.1435,
+      "step": 61
+    },
+    {
+      "epoch": 0.031492063492063495,
+      "grad_norm": 0.40068405866622925,
+      "learning_rate": 7.580781044003324e-05,
+      "loss": 1.6526,
+      "step": 62
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.2322355955839157,
+      "learning_rate": 7.243626441830009e-05,
+      "loss": 1.2496,
+      "step": 63
+    },
+    {
+      "epoch": 0.032507936507936507,
+      "grad_norm": 0.44400423765182495,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.3121,
+      "step": 64
+    },
+    {
+      "epoch": 0.03301587301587302,
+      "grad_norm": 0.46300458908081055,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 1.5739,
+      "step": 65
+    },
+    {
+      "epoch": 0.033523809523809525,
+      "grad_norm": 0.27108630537986755,
+      "learning_rate": 6.25393406584088e-05,
+      "loss": 0.9874,
+      "step": 66
+    },
+    {
+      "epoch": 0.03403174603174603,
+      "grad_norm": 0.23532073199748993,
+      "learning_rate": 5.9326335692419995e-05,
+      "loss": 1.2079,
+      "step": 67
+    },
+    {
+      "epoch": 0.03453968253968254,
+      "grad_norm": 0.4134567379951477,
+      "learning_rate": 5.616288532109225e-05,
+      "loss": 1.5086,
+      "step": 68
+    },
+    {
+      "epoch": 0.03504761904761905,
+      "grad_norm": 0.3667893707752228,
+      "learning_rate": 5.305284372141095e-05,
+      "loss": 1.5459,
+      "step": 69
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 0.5127963423728943,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.4526,
+      "step": 70
+    },
+    {
+      "epoch": 0.03606349206349206,
+      "grad_norm": 0.23248711228370667,
+      "learning_rate": 4.700807357667952e-05,
+      "loss": 1.7219,
+      "step": 71
+    },
+    {
+      "epoch": 0.036571428571428574,
+      "grad_norm": 0.36493247747421265,
+      "learning_rate": 4.4080709652925336e-05,
+      "loss": 1.2866,
+      "step": 72
+    },
+    {
+      "epoch": 0.03707936507936508,
+      "grad_norm": 0.3120146691799164,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.7468,
+      "step": 73
+    },
+    {
+      "epoch": 0.037587301587301586,
+      "grad_norm": 0.2617102265357971,
+      "learning_rate": 3.843385246743417e-05,
+      "loss": 1.3033,
+      "step": 74
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "grad_norm": 0.37346601486206055,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 1.3576,
+      "step": 75
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "eval_loss": 1.4916026592254639,
+      "eval_runtime": 206.1501,
+      "eval_samples_per_second": 4.021,
+      "eval_steps_per_second": 2.013,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -400,7 +583,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.59230637948928e+16,
+  "total_flos": 9.88845956923392e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null