Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c236d4577e427ec899e06bc9afc96e33c0dad13994fd3140fe7e43bc9c09f1a
+oid sha256:7a0287780036ff9ba1500e3469f7e3213a5790b1427cfe033fb02d9af5ed2e34
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9955a4b10741311b5bbfbd399e7df892038bad9da690d7ac87b1003ffaf1cd7f
+oid sha256:8b7b1049b0f41d5dc0f435a7e07795c11fa877304a71632b6fd26b2c0b78ff4c
 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": 0.002772771384999307,
+  "epoch": 0.0041591570774989605,
   "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": 0.0,
       "step": 50
+    },
+    {
+      "epoch": 0.002828226812699293,
+      "grad_norm": NaN,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.002883682240399279,
+      "grad_norm": NaN,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.0029391376680992652,
+      "grad_norm": NaN,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.002994593095799251,
+      "grad_norm": NaN,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.002994593095799251,
+      "eval_loss": NaN,
+      "eval_runtime": 1519.3079,
+      "eval_samples_per_second": 9.995,
+      "eval_steps_per_second": 1.25,
+      "step": 54
+    },
+    {
+      "epoch": 0.0030500485234992375,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.0031055039511992235,
+      "grad_norm": NaN,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.00316095937889921,
+      "grad_norm": NaN,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.0032164148065991958,
+      "grad_norm": NaN,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.003271870234299182,
+      "grad_norm": NaN,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.003327325661999168,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.0033827810896991544,
+      "grad_norm": NaN,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.0034382365173991404,
+      "grad_norm": NaN,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.0034936919450991267,
+      "grad_norm": NaN,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.0034936919450991267,
+      "eval_loss": NaN,
+      "eval_runtime": 1519.4842,
+      "eval_samples_per_second": 9.994,
+      "eval_steps_per_second": 1.25,
+      "step": 63
+    },
+    {
+      "epoch": 0.0035491473727991127,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.003604602800499099,
+      "grad_norm": NaN,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.003660058228199085,
+      "grad_norm": NaN,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.0037155136558990713,
+      "grad_norm": NaN,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.0037709690835990572,
+      "grad_norm": NaN,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.003826424511299043,
+      "grad_norm": NaN,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.0038818799389990295,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.003937335366699016,
+      "grad_norm": NaN,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.003992790794399002,
+      "grad_norm": NaN,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.003992790794399002,
+      "eval_loss": NaN,
+      "eval_runtime": 1519.4145,
+      "eval_samples_per_second": 9.994,
+      "eval_steps_per_second": 1.25,
+      "step": 72
+    },
+    {
+      "epoch": 0.004048246222098988,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.004103701649798974,
+      "grad_norm": NaN,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.0041591570774989605,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.27049537889239e+16,
+  "total_flos": 1.083155433998254e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null