Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d42efacb6ebae8205c8b5fa635169a9fda0316599b000306d2e790e5ebab7c
+oid sha256:a64c472a69b7ea9c4855a627bc05fccc721b3906a5733869c8a9bfb2b3dc7a5b
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dccd2209ce0a00fd7d294f9f7e44828a38fbb2c754d6bb490a588c320684b5f
+oid sha256:287b2a46ce32469b30fab2fe22be6379db30d24f3ef3decab6ad6d39c95cbcbf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d65e9c686bf7672c60c2e716324e2ec3b9e362aa67293892146275e003a9f911
+oid sha256:3576cca3b6a084e5b9dbc713d787dac1e4381b121fdf3f476ee9adbb805713a7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9230769230769231,
+  "epoch": 2.8846153846153846,
   "eval_steps": 7,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -421,6 +421,205 @@
       "learning_rate": 3.499576824998298e-05,
       "loss": 0.0,
       "step": 50
+    },
+    {
+      "epoch": 1.9615384615384617,
+      "grad_norm": NaN,
+      "learning_rate": 3.277665748578336e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": NaN,
+      "learning_rate": 3.0595407366387504e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 2.0384615384615383,
+      "grad_norm": NaN,
+      "learning_rate": 2.8456812752951485e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 2.076923076923077,
+      "grad_norm": NaN,
+      "learning_rate": 2.636557474057173e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 2.1153846153846154,
+      "grad_norm": NaN,
+      "learning_rate": 2.4326290324257894e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": NaN,
+      "learning_rate": 2.234344229374003e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "eval_loss": NaN,
+      "eval_runtime": 4.8673,
+      "eval_samples_per_second": 4.52,
+      "eval_steps_per_second": 0.616,
+      "step": 56
+    },
+    {
+      "epoch": 2.1923076923076925,
+      "grad_norm": NaN,
+      "learning_rate": 2.042138937932388e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": NaN,
+      "learning_rate": 1.8564356670455767e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 2.269230769230769,
+      "grad_norm": NaN,
+      "learning_rate": 1.677642632805892e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": NaN,
+      "learning_rate": 1.5061528611057918e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 2.3461538461538463,
+      "grad_norm": NaN,
+      "learning_rate": 1.3423433236816563e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 2.3846153846153846,
+      "grad_norm": NaN,
+      "learning_rate": 1.1865741094480909e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 2.423076923076923,
+      "grad_norm": NaN,
+      "learning_rate": 1.0391876329443533e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 2.423076923076923,
+      "eval_loss": NaN,
+      "eval_runtime": 4.8685,
+      "eval_samples_per_second": 4.519,
+      "eval_steps_per_second": 0.616,
+      "step": 63
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": NaN,
+      "learning_rate": 9.005078816328771e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": NaN,
+      "learning_rate": 7.708397037045129e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "grad_norm": NaN,
+      "learning_rate": 6.50468137956049e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 2.5769230769230766,
+      "grad_norm": NaN,
+      "learning_rate": 5.3965778721306755e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": NaN,
+      "learning_rate": 4.386522366755169e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 2.6538461538461537,
+      "grad_norm": NaN,
+      "learning_rate": 3.476735184645674e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": NaN,
+      "learning_rate": 2.6692162354782944e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "eval_loss": NaN,
+      "eval_runtime": 4.868,
+      "eval_samples_per_second": 4.519,
+      "eval_steps_per_second": 0.616,
+      "step": 70
+    },
+    {
+      "epoch": 2.730769230769231,
+      "grad_norm": NaN,
+      "learning_rate": 1.9657406211579966e-06,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": NaN,
+      "learning_rate": 1.3678547337593494e-06,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 2.8076923076923075,
+      "grad_norm": NaN,
+      "learning_rate": 8.768728562211947e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 2.8461538461538463,
+      "grad_norm": NaN,
+      "learning_rate": 4.938742732674529e-07,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 2.8846153846153846,
+      "grad_norm": NaN,
+      "learning_rate": 2.1970089890509527e-07,
+      "loss": 0.0,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -440,7 +639,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.363231289337446e+16,
+  "total_flos": 1.1017026160872653e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null