Training in progress, step 100000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a23c49d487e0019dc985d75287fb7093ae6d9358b291f443ffc6b3d3ac01f60a
-size 885324633
+oid sha256:d3fd9bc9bde7973a7db5880164bb76ce72e2ba06417d0c2f9ea0aee093927520
+size 885325017

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ecccd9eb602c427ec07b2e2e082a8f8a5cac7f4aecb7f1cc99d1c0fc82cd41d
+oid sha256:3c6f318a7e06329159397e2dd2fc7a97d5ea21a88118941680d17eacb1688f6f
 size 442675755

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7570246e1f2378a9fa9a7220e9a0bba4d7a3e246b3cad14f686250de7cd023
+oid sha256:c1f90751f9a8a9c5182df7e068eba4534bb2d768c3dcc0182a3097f19cf00de3
 size 13611

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7570246e1f2378a9fa9a7220e9a0bba4d7a3e246b3cad14f686250de7cd023
+oid sha256:c1f90751f9a8a9c5182df7e068eba4534bb2d768c3dcc0182a3097f19cf00de3
 size 13611

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7570246e1f2378a9fa9a7220e9a0bba4d7a3e246b3cad14f686250de7cd023
+oid sha256:c1f90751f9a8a9c5182df7e068eba4534bb2d768c3dcc0182a3097f19cf00de3
 size 13611

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7570246e1f2378a9fa9a7220e9a0bba4d7a3e246b3cad14f686250de7cd023
+oid sha256:c1f90751f9a8a9c5182df7e068eba4534bb2d768c3dcc0182a3097f19cf00de3
 size 13611

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7570246e1f2378a9fa9a7220e9a0bba4d7a3e246b3cad14f686250de7cd023
+oid sha256:c1f90751f9a8a9c5182df7e068eba4534bb2d768c3dcc0182a3097f19cf00de3
 size 13611

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7570246e1f2378a9fa9a7220e9a0bba4d7a3e246b3cad14f686250de7cd023
+oid sha256:c1f90751f9a8a9c5182df7e068eba4534bb2d768c3dcc0182a3097f19cf00de3
 size 13611

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7570246e1f2378a9fa9a7220e9a0bba4d7a3e246b3cad14f686250de7cd023
+oid sha256:c1f90751f9a8a9c5182df7e068eba4534bb2d768c3dcc0182a3097f19cf00de3
 size 13611

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7570246e1f2378a9fa9a7220e9a0bba4d7a3e246b3cad14f686250de7cd023
+oid sha256:c1f90751f9a8a9c5182df7e068eba4534bb2d768c3dcc0182a3097f19cf00de3
 size 13611

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eda5fed79fbfae57d1a589b135999ab70f7c329a9938c428058fd62dc77c658
+oid sha256:4178362c6bd24374be7907f1b74df811389bf304534a9b4cb11df3bada4d661b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
  "best_metric": null,
  "best_model_checkpoint": null,
- "epoch": 23.00942,
- "global_step": 50000,
+ "epoch": 47.00838,
+ "global_step": 100000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
@@ -314,11 +314,319 @@
  "eval_samples_per_second": 297.912,
  "eval_steps_per_second": 2.383,
  "step": 50000
+ },
+ {
+ "epoch": 24.0,
+ "learning_rate": 8.894386393810563e-05,
+ "loss": 0.9485,
+ "step": 51000
+ },
+ {
+ "epoch": 24.01,
+ "learning_rate": 8.842005554284296e-05,
+ "loss": 0.9995,
+ "step": 52000
+ },
+ {
+ "epoch": 25.0,
+ "learning_rate": 8.788574348801675e-05,
+ "loss": 0.9509,
+ "step": 53000
+ },
+ {
+ "epoch": 25.01,
+ "learning_rate": 8.73410738492077e-05,
+ "loss": 0.9897,
+ "step": 54000
+ },
+ {
+ "epoch": 26.0,
+ "learning_rate": 8.678619553365659e-05,
+ "loss": 0.9599,
+ "step": 55000
+ },
+ {
+ "epoch": 26.01,
+ "learning_rate": 8.622126023955446e-05,
+ "loss": 0.968,
+ "step": 56000
+ },
+ {
+ "epoch": 27.0,
+ "learning_rate": 8.564642241456986e-05,
+ "loss": 0.9889,
+ "step": 57000
+ },
+ {
+ "epoch": 27.01,
+ "learning_rate": 8.506183921362443e-05,
+ "loss": 0.9331,
+ "step": 58000
+ },
+ {
+ "epoch": 28.0,
+ "learning_rate": 8.44676704559283e-05,
+ "loss": 0.9972,
+ "step": 59000
+ },
+ {
+ "epoch": 28.01,
+ "learning_rate": 8.386407858128706e-05,
+ "loss": 0.9208,
+ "step": 60000
+ },
+ {
+ "epoch": 29.0,
+ "learning_rate": 8.32512286056924e-05,
+ "loss": 0.9923,
+ "step": 61000
+ },
+ {
+ "epoch": 29.01,
+ "learning_rate": 8.262928807620843e-05,
+ "loss": 0.9152,
+ "step": 62000
+ },
+ {
+ "epoch": 30.0,
+ "learning_rate": 8.199842702516583e-05,
+ "loss": 0.981,
+ "step": 63000
+ },
+ {
+ "epoch": 30.01,
+ "learning_rate": 8.135881792367686e-05,
+ "loss": 0.9202,
+ "step": 64000
+ },
+ {
+ "epoch": 31.0,
+ "learning_rate": 8.07106356344834e-05,
+ "loss": 0.9697,
+ "step": 65000
+ },
+ {
+ "epoch": 31.01,
+ "learning_rate": 8.005405736415126e-05,
+ "loss": 0.9151,
+ "step": 66000
+ },
+ {
+ "epoch": 32.0,
+ "learning_rate": 7.938926261462366e-05,
+ "loss": 0.9762,
+ "step": 67000
+ },
+ {
+ "epoch": 32.01,
+ "learning_rate": 7.871643313414718e-05,
+ "loss": 0.9036,
+ "step": 68000
+ },
+ {
+ "epoch": 32.01,
+ "learning_rate": 7.803575286758364e-05,
+ "loss": 0.9742,
+ "step": 69000
+ },
+ {
+ "epoch": 33.0,
+ "learning_rate": 7.734740790612136e-05,
+ "loss": 0.9105,
+ "step": 70000
+ },
+ {
+ "epoch": 33.01,
+ "learning_rate": 7.66515864363997e-05,
+ "loss": 0.9611,
+ "step": 71000
+ },
+ {
+ "epoch": 34.0,
+ "learning_rate": 7.594847868906076e-05,
+ "loss": 0.8994,
+ "step": 72000
+ },
+ {
+ "epoch": 34.01,
+ "learning_rate": 7.52382768867422e-05,
+ "loss": 0.9551,
+ "step": 73000
+ },
+ {
+ "epoch": 35.0,
+ "learning_rate": 7.452117519152542e-05,
+ "loss": 0.8943,
+ "step": 74000
+ },
+ {
+ "epoch": 35.01,
+ "learning_rate": 7.379736965185368e-05,
+ "loss": 0.9445,
+ "step": 75000
+ },
+ {
+ "epoch": 36.0,
+ "learning_rate": 7.30670581489344e-05,
+ "loss": 0.896,
+ "step": 76000
+ },
+ {
+ "epoch": 36.01,
+ "learning_rate": 7.233044034264034e-05,
+ "loss": 0.9371,
+ "step": 77000
+ },
+ {
+ "epoch": 37.0,
+ "learning_rate": 7.158771761692464e-05,
+ "loss": 0.911,
+ "step": 78000
+ },
+ {
+ "epoch": 37.01,
+ "learning_rate": 7.083909302476453e-05,
+ "loss": 0.9143,
+ "step": 79000
+ },
+ {
+ "epoch": 38.0,
+ "learning_rate": 7.008477123264848e-05,
+ "loss": 0.9433,
+ "step": 80000
+ },
+ {
+ "epoch": 38.01,
+ "learning_rate": 6.932495846462261e-05,
+ "loss": 0.881,
+ "step": 81000
+ },
+ {
+ "epoch": 39.0,
+ "learning_rate": 6.855986244591104e-05,
+ "loss": 0.9461,
+ "step": 82000
+ },
+ {
+ "epoch": 39.01,
+ "learning_rate": 6.778969234612584e-05,
+ "loss": 0.8759,
+ "step": 83000
+ },
+ {
+ "epoch": 40.0,
+ "learning_rate": 6.701465872208216e-05,
+ "loss": 0.944,
+ "step": 84000
+ },
+ {
+ "epoch": 40.01,
+ "learning_rate": 6.623497346023418e-05,
+ "loss": 0.8766,
+ "step": 85000
+ },
+ {
+ "epoch": 41.0,
+ "learning_rate": 6.545084971874738e-05,
+ "loss": 0.9291,
+ "step": 86000
+ },
+ {
+ "epoch": 41.01,
+ "learning_rate": 6.466250186922325e-05,
+ "loss": 0.8758,
+ "step": 87000
+ },
+ {
+ "epoch": 42.0,
+ "learning_rate": 6.387014543809223e-05,
+ "loss": 0.9281,
+ "step": 88000
+ },
+ {
+ "epoch": 42.01,
+ "learning_rate": 6.307399704769099e-05,
+ "loss": 0.8725,
+ "step": 89000
+ },
+ {
+ "epoch": 43.0,
+ "learning_rate": 6.227427435703997e-05,
+ "loss": 0.9344,
+ "step": 90000
+ },
+ {
+ "epoch": 43.01,
+ "learning_rate": 6.147119600233758e-05,
+ "loss": 0.8645,
+ "step": 91000
+ },
+ {
+ "epoch": 43.01,
+ "learning_rate": 6.066498153718735e-05,
+ "loss": 0.9319,
+ "step": 92000
+ },
+ {
+ "epoch": 44.0,
+ "learning_rate": 5.985585137257401e-05,
+ "loss": 0.8698,
+ "step": 93000
+ },
+ {
+ "epoch": 44.01,
+ "learning_rate": 5.90440267166055e-05,
+ "loss": 0.9219,
+ "step": 94000
+ },
+ {
+ "epoch": 45.0,
+ "learning_rate": 5.8229729514036705e-05,
+ "loss": 0.8574,
+ "step": 95000
+ },
+ {
+ "epoch": 45.01,
+ "learning_rate": 5.74131823855921e-05,
+ "loss": 0.9154,
+ "step": 96000
+ },
+ {
+ "epoch": 46.0,
+ "learning_rate": 5.6594608567103456e-05,
+ "loss": 0.8572,
+ "step": 97000
+ },
+ {
+ "epoch": 46.01,
+ "learning_rate": 5.577423184847932e-05,
+ "loss": 0.9074,
+ "step": 98000
+ },
+ {
+ "epoch": 47.0,
+ "learning_rate": 5.495227651252315e-05,
+ "loss": 0.8593,
+ "step": 99000
+ },
+ {
+ "epoch": 47.01,
+ "learning_rate": 5.4128967273616625e-05,
+ "loss": 0.8993,
+ "step": 100000
+ },
+ {
+ "epoch": 47.01,
+ "eval_loss": 0.6356155276298523,
+ "eval_runtime": 10.4482,
+ "eval_samples_per_second": 478.553,
+ "eval_steps_per_second": 3.828,
+ "step": 100000
  }
  ],
  "max_steps": 200000,
  "num_train_epochs": 9223372036854775807,
- "total_flos": 8.423667913331835e+17,
+ "total_flos": 1.6847377940160184e+18,
  "trial_name": null,
  "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ecccd9eb602c427ec07b2e2e082a8f8a5cac7f4aecb7f1cc99d1c0fc82cd41d
+oid sha256:3c6f318a7e06329159397e2dd2fc7a97d5ea21a88118941680d17eacb1688f6f
 size 442675755

runs/Feb09_18-26-34_t1v-n-07f0074d-w-0/events.out.tfevents.1675967214.t1v-n-07f0074d-w-0.3787133.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d8dfc5f914d6f4454db7bbf721ef32c120f844c877042a4ce2bd0e0b73e420
-size 12023
+oid sha256:16ec68259af58e37532bdd5376c48e71def64bd20c6cf4bb43377cdeb30e9ce6
+size 20299