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 sha256:309c8dcb721a2263f3cbfb0ac7f4550c8789c7796a21b40389afcc99ea606e89
+oid sha256:e6ee7beb3507cd3f39e5a0a380f648b5286dc4721f07a4ee00b013cf126904aa
 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": 0.002457002457002457,
+  "epoch": 0.0036855036855036856,
   "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": 0.002506142506142506,
+      "grad_norm": NaN,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.0025552825552825555,
+      "grad_norm": NaN,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.0026044226044226043,
+      "grad_norm": NaN,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.0026535626535626536,
+      "grad_norm": NaN,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.0026535626535626536,
+      "eval_loss": NaN,
+      "eval_runtime": 1978.4738,
+      "eval_samples_per_second": 8.662,
+      "eval_steps_per_second": 1.083,
+      "step": 54
+    },
+    {
+      "epoch": 0.002702702702702703,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.0027518427518427517,
+      "grad_norm": NaN,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.002800982800982801,
+      "grad_norm": NaN,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.0028501228501228502,
+      "grad_norm": NaN,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.002899262899262899,
+      "grad_norm": NaN,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.0029484029484029483,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.0029975429975429976,
+      "grad_norm": NaN,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.003046683046683047,
+      "grad_norm": NaN,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.0030958230958230957,
+      "grad_norm": NaN,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.0030958230958230957,
+      "eval_loss": NaN,
+      "eval_runtime": 1979.7487,
+      "eval_samples_per_second": 8.656,
+      "eval_steps_per_second": 1.082,
+      "step": 63
+    },
+    {
+      "epoch": 0.003144963144963145,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.0031941031941031942,
+      "grad_norm": NaN,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.003243243243243243,
+      "grad_norm": NaN,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.0032923832923832923,
+      "grad_norm": NaN,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.0033415233415233416,
+      "grad_norm": NaN,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.0033906633906633904,
+      "grad_norm": NaN,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.0034398034398034397,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.003488943488943489,
+      "grad_norm": NaN,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.0035380835380835383,
+      "grad_norm": NaN,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.0035380835380835383,
+      "eval_loss": NaN,
+      "eval_runtime": 1978.2298,
+      "eval_samples_per_second": 8.663,
+      "eval_steps_per_second": 1.083,
+      "step": 72
+    },
+    {
+      "epoch": 0.003587223587223587,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.0036363636363636364,
+      "grad_norm": NaN,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.0036855036855036856,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.969096967048397e+16,
+  "total_flos": 5.898003904305562e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null