Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39007a35c09aa20531bb24768dfdecf28a8f3d5e9a441e552ac4f8f6f7f61736
+oid sha256:9d6e3e3f8da5ca34e31e7e1da106d1a2de25558024735de31f395304b7ea671c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c59790f2e3ba0a4714a087914c6124ed7398fe25ca94de6ab9e0301a8e585f
+oid sha256:7f53083d6bf416fa674a4d7654c4dc44772d047f9fd45a1c2d70bd5cf789eb73
 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": 0.29038112522686027,
+  "epoch": 0.4355716878402904,
   "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": 29.949,
       "eval_steps_per_second": 14.975,
       "step": 50
+    },
+    {
+      "epoch": 0.2961887477313975,
+      "grad_norm": NaN,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 5.5278,
+      "step": 51
+    },
+    {
+      "epoch": 0.3019963702359347,
+      "grad_norm": NaN,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2660.9358,
+      "step": 52
+    },
+    {
+      "epoch": 0.3078039927404719,
+      "grad_norm": NaN,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 25.8831,
+      "step": 53
+    },
+    {
+      "epoch": 0.3136116152450091,
+      "grad_norm": NaN,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 108.3971,
+      "step": 54
+    },
+    {
+      "epoch": 0.3194192377495463,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 215.6494,
+      "step": 55
+    },
+    {
+      "epoch": 0.3252268602540835,
+      "grad_norm": NaN,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 3366.7695,
+      "step": 56
+    },
+    {
+      "epoch": 0.3310344827586207,
+      "grad_norm": NaN,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 26.9873,
+      "step": 57
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": NaN,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.3426497277676951,
+      "grad_norm": NaN,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.3484573502722323,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 7.1294,
+      "step": 60
+    },
+    {
+      "epoch": 0.3542649727767695,
+      "grad_norm": NaN,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 666.5757,
+      "step": 61
+    },
+    {
+      "epoch": 0.3600725952813067,
+      "grad_norm": NaN,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.3658802177858439,
+      "grad_norm": NaN,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.3673,
+      "step": 63
+    },
+    {
+      "epoch": 0.3716878402903811,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.37749546279491836,
+      "grad_norm": NaN,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 293.4128,
+      "step": 65
+    },
+    {
+      "epoch": 0.38330308529945556,
+      "grad_norm": NaN,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1924.7764,
+      "step": 66
+    },
+    {
+      "epoch": 0.38911070780399276,
+      "grad_norm": NaN,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.39491833030852996,
+      "grad_norm": NaN,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.40072595281306717,
+      "grad_norm": NaN,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.40653357531760437,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 447.9875,
+      "step": 70
+    },
+    {
+      "epoch": 0.41234119782214157,
+      "grad_norm": NaN,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.1965,
+      "step": 71
+    },
+    {
+      "epoch": 0.41814882032667877,
+      "grad_norm": NaN,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 636.1243,
+      "step": 72
+    },
+    {
+      "epoch": 0.423956442831216,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 58.9024,
+      "step": 73
+    },
+    {
+      "epoch": 0.4297640653357532,
+      "grad_norm": NaN,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1028.7271,
+      "step": 74
+    },
+    {
+      "epoch": 0.4355716878402904,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 109.8508,
+      "step": 75
+    },
+    {
+      "epoch": 0.4355716878402904,
+      "eval_loss": NaN,
+      "eval_runtime": 9.6787,
+      "eval_samples_per_second": 29.963,
+      "eval_steps_per_second": 14.981,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -400,7 +583,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.985367319012966e+16,
+  "total_flos": 8.956142606195098e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null