Training in progress, step 119, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:409506c2e743c0962472a80fbb6dcaf2cbc9c90ce5fb8329688b39a5b3cfa456
+oid sha256:a7a0675b0ccff9d3ee1f89a5d3ec1b7f2360c88f112fca496ed1e53a1f95999b
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609ac74381de893b35193cf51e9a6fce221b22031433fbd3b97539f9bac6436f
+oid sha256:c587490379a5a51115375645f2d5ea52b7a18285f8ceca78cb845b39b459b45e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70670c442607259270e13afbef3aac28e38a58ddad6998414f76ed43ab7f41d4
+oid sha256:d4a2e0d38e4aad78961b54bb99f0a18c11d847ea1d3d3bc12cf223a3f862cf9e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11208021427099787,
+  "epoch": 0.13076024998283084,
   "eval_steps": 50,
-  "global_step": 102,
+  "global_step": 119,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -745,6 +745,125 @@
       "learning_rate": 8.54379825720049e-05,
       "loss": 0.0,
       "step": 102
+    },
+    {
+      "epoch": 0.1131790399011057,
+      "grad_norm": NaN,
+      "learning_rate": 8.414020075538605e-05,
+      "loss": 0.0,
+      "step": 103
+    },
+    {
+      "epoch": 0.11427786553121351,
+      "grad_norm": NaN,
+      "learning_rate": 8.2839634745074e-05,
+      "loss": 0.0,
+      "step": 104
+    },
+    {
+      "epoch": 0.11537669116132133,
+      "grad_norm": NaN,
+      "learning_rate": 8.153668070607437e-05,
+      "loss": 0.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.11647551679142916,
+      "grad_norm": NaN,
+      "learning_rate": 8.023173553080938e-05,
+      "loss": 0.0,
+      "step": 106
+    },
+    {
+      "epoch": 0.11757434242153698,
+      "grad_norm": NaN,
+      "learning_rate": 7.89251967182208e-05,
+      "loss": 0.0,
+      "step": 107
+    },
+    {
+      "epoch": 0.11867316805164481,
+      "grad_norm": NaN,
+      "learning_rate": 7.761746225268758e-05,
+      "loss": 0.0,
+      "step": 108
+    },
+    {
+      "epoch": 0.11977199368175263,
+      "grad_norm": NaN,
+      "learning_rate": 7.630893048279627e-05,
+      "loss": 0.0,
+      "step": 109
+    },
+    {
+      "epoch": 0.12087081931186044,
+      "grad_norm": NaN,
+      "learning_rate": 7.5e-05,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.12196964494196827,
+      "grad_norm": NaN,
+      "learning_rate": 7.369106951720373e-05,
+      "loss": 0.0,
+      "step": 111
+    },
+    {
+      "epoch": 0.1230684705720761,
+      "grad_norm": NaN,
+      "learning_rate": 7.238253774731244e-05,
+      "loss": 0.0,
+      "step": 112
+    },
+    {
+      "epoch": 0.12416729620218392,
+      "grad_norm": NaN,
+      "learning_rate": 7.10748032817792e-05,
+      "loss": 0.0,
+      "step": 113
+    },
+    {
+      "epoch": 0.12526612183229174,
+      "grad_norm": NaN,
+      "learning_rate": 6.976826446919059e-05,
+      "loss": 0.0,
+      "step": 114
+    },
+    {
+      "epoch": 0.12636494746239957,
+      "grad_norm": NaN,
+      "learning_rate": 6.846331929392562e-05,
+      "loss": 0.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.1274637730925074,
+      "grad_norm": NaN,
+      "learning_rate": 6.7160365254926e-05,
+      "loss": 0.0,
+      "step": 116
+    },
+    {
+      "epoch": 0.12856259872261522,
+      "grad_norm": NaN,
+      "learning_rate": 6.585979924461394e-05,
+      "loss": 0.0,
+      "step": 117
+    },
+    {
+      "epoch": 0.12966142435272301,
+      "grad_norm": NaN,
+      "learning_rate": 6.45620174279951e-05,
+      "loss": 0.0,
+      "step": 118
+    },
+    {
+      "epoch": 0.13076024998283084,
+      "grad_norm": NaN,
+      "learning_rate": 6.326741512198266e-05,
+      "loss": 0.0,
+      "step": 119
     }
   ],
   "logging_steps": 1,
@@ -764,7 +883,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.979003336114831e+17,
+  "total_flos": 6.974956063351112e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null