Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ee6a55c4481085f598c76b9b255ba4df80b7e0e63ad325ff67e26940157e9b1
+oid sha256:6d1a8dd3bb56efc8f5d013240ca65922a8ce332d515e5abf941b96f4e177e540
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c4d26c14515bc424ea5b0bbfeae19c1ae269bc58d5ebf3d8f6f07ac2317cc3
+oid sha256:b516262e611e64feed373fc0a19148dd159b868c8d52c53d4e4b202d27f26b1e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8615f1aeccd0f9873fc0cf2c0322fde20ac202421c015654a471730a5fa755
+oid sha256:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.33444816053511706,
+  "epoch": 0.5016722408026756,
   "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": 1.1736481776669307e-05,
       "loss": 0.0,
       "step": 50
+    },
+    {
+      "epoch": 0.3411371237458194,
+      "grad_norm": NaN,
+      "learning_rate": 1.1391731009600655e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": NaN,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.35451505016722407,
+      "grad_norm": NaN,
+      "learning_rate": 1.0697564737441254e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.3612040133779264,
+      "grad_norm": NaN,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.3612040133779264,
+      "eval_loss": NaN,
+      "eval_runtime": 4.194,
+      "eval_samples_per_second": 30.043,
+      "eval_steps_per_second": 3.815,
+      "step": 54
+    },
+    {
+      "epoch": 0.36789297658862874,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.3745819397993311,
+      "grad_norm": NaN,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.38127090301003347,
+      "grad_norm": NaN,
+      "learning_rate": 9.302435262558748e-06,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.3879598662207358,
+      "grad_norm": NaN,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.39464882943143814,
+      "grad_norm": NaN,
+      "learning_rate": 8.60826899039935e-06,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.4013377926421405,
+      "grad_norm": NaN,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.4080267558528428,
+      "grad_norm": NaN,
+      "learning_rate": 7.92088309182241e-06,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.41471571906354515,
+      "grad_norm": NaN,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.4214046822742475,
+      "grad_norm": NaN,
+      "learning_rate": 7.243626441830009e-06,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.4214046822742475,
+      "eval_loss": NaN,
+      "eval_runtime": 4.1734,
+      "eval_samples_per_second": 30.192,
+      "eval_steps_per_second": 3.834,
+      "step": 63
+    },
+    {
+      "epoch": 0.4280936454849498,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": NaN,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.4414715719063545,
+      "grad_norm": NaN,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.44816053511705684,
+      "grad_norm": NaN,
+      "learning_rate": 5.932633569242e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.45484949832775917,
+      "grad_norm": NaN,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": NaN,
+      "learning_rate": 5.305284372141095e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.4682274247491639,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.47491638795986624,
+      "grad_norm": NaN,
+      "learning_rate": 4.700807357667953e-06,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.4816053511705686,
+      "grad_norm": NaN,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.4816053511705686,
+      "eval_loss": NaN,
+      "eval_runtime": 4.1686,
+      "eval_samples_per_second": 30.226,
+      "eval_steps_per_second": 3.838,
+      "step": 72
+    },
+    {
+      "epoch": 0.4882943143812709,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.49498327759197325,
+      "grad_norm": NaN,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.5016722408026756,
+      "grad_norm": NaN,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.0,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5455654491783168.0,
+  "total_flos": 8183481737674752.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null