Training in progress, step 200000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce00af67b32f5031634448ef59d59c554d1e00a55c8b464f822021954d2f458
+oid sha256:1864e8b6d73df803d6169b4a02883f655f8f1f03dba67d279ba50bf4aec8c451
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f449ea92715ca64c5aa73950f43c9ea9816a4a5ad265403dda147f77444d50
+oid sha256:d7193b0396efbae3c97d694737aabe6c7c60bae54e10275e5280d057220eeba1
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45496c46423f623843268f065bb3004f921eb295069e4d4e3f3d7236dcb94f89
+oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45496c46423f623843268f065bb3004f921eb295069e4d4e3f3d7236dcb94f89
+oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45496c46423f623843268f065bb3004f921eb295069e4d4e3f3d7236dcb94f89
+oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45496c46423f623843268f065bb3004f921eb295069e4d4e3f3d7236dcb94f89
+oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45496c46423f623843268f065bb3004f921eb295069e4d4e3f3d7236dcb94f89
+oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45496c46423f623843268f065bb3004f921eb295069e4d4e3f3d7236dcb94f89
+oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45496c46423f623843268f065bb3004f921eb295069e4d4e3f3d7236dcb94f89
+oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45496c46423f623843268f065bb3004f921eb295069e4d4e3f3d7236dcb94f89
+oid sha256:649f99ced15f6aa95053cf61e777a2d14c6173f37ab5b51c676618360f19400a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0439027dd6f55adc764cb1317d963df8ccf36442066dafecce10b3f538efa8e
+oid sha256:6e461416c63c82734faef19b4949af829ad430bff342d30400b1c1da0cafb58f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.842244762730006,
-  "global_step": 190000,
+  "epoch": 5.097099750242112,
+  "global_step": 200000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3806,11 +3806,211 @@
       "eval_samples_per_second": 780.471,
       "eval_steps_per_second": 12.488,
       "step": 190000
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 0.00022146867474920118,
+      "loss": 0.2961,
+      "step": 190500
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 0.00022104215397571484,
+      "loss": 0.2959,
+      "step": 191000
+    },
+    {
+      "epoch": 4.87,
+      "eval_loss": 0.8258107900619507,
+      "eval_runtime": 1.248,
+      "eval_samples_per_second": 801.284,
+      "eval_steps_per_second": 12.821,
+      "step": 191000
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 0.0002206149109758135,
+      "loss": 0.2954,
+      "step": 191500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 0.00022018695042175818,
+      "loss": 0.295,
+      "step": 192000
+    },
+    {
+      "epoch": 4.89,
+      "eval_loss": 0.8216790556907654,
+      "eval_runtime": 1.2627,
+      "eval_samples_per_second": 791.937,
+      "eval_steps_per_second": 12.671,
+      "step": 192000
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 0.00021975827699365693,
+      "loss": 0.2949,
+      "step": 192500
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 0.00021932889537941365,
+      "loss": 0.295,
+      "step": 193000
+    },
+    {
+      "epoch": 4.92,
+      "eval_loss": 0.8129534721374512,
+      "eval_runtime": 1.2745,
+      "eval_samples_per_second": 784.628,
+      "eval_steps_per_second": 12.554,
+      "step": 193000
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 0.0002188988102746769,
+      "loss": 0.2949,
+      "step": 193500
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 0.0002184680263827885,
+      "loss": 0.2968,
+      "step": 194000
+    },
+    {
+      "epoch": 4.94,
+      "eval_loss": 0.8097214698791504,
+      "eval_runtime": 1.2465,
+      "eval_samples_per_second": 802.226,
+      "eval_steps_per_second": 12.836,
+      "step": 194000
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 0.00021803654841473204,
+      "loss": 0.2953,
+      "step": 194500
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 0.00021760438108908142,
+      "loss": 0.2947,
+      "step": 195000
+    },
+    {
+      "epoch": 4.97,
+      "eval_loss": 0.806962788105011,
+      "eval_runtime": 1.2893,
+      "eval_samples_per_second": 775.619,
+      "eval_steps_per_second": 12.41,
+      "step": 195000
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 0.0002171715291319494,
+      "loss": 0.2944,
+      "step": 195500
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0002167379972769355,
+      "loss": 0.2941,
+      "step": 196000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.8226540684700012,
+      "eval_runtime": 1.2611,
+      "eval_samples_per_second": 792.99,
+      "eval_steps_per_second": 12.688,
+      "step": 196000
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0002163037902650747,
+      "loss": 0.2948,
+      "step": 196500
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.0002158689128447853,
+      "loss": 0.294,
+      "step": 197000
+    },
+    {
+      "epoch": 5.02,
+      "eval_loss": 0.813295841217041,
+      "eval_runtime": 1.2515,
+      "eval_samples_per_second": 799.026,
+      "eval_steps_per_second": 12.784,
+      "step": 197000
+    },
+    {
+      "epoch": 5.03,
+      "learning_rate": 0.00021543336977181704,
+      "loss": 0.2948,
+      "step": 197500
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 0.00021499716580919933,
+      "loss": 0.2947,
+      "step": 198000
+    },
+    {
+      "epoch": 5.05,
+      "eval_loss": 0.8141849637031555,
+      "eval_runtime": 1.3465,
+      "eval_samples_per_second": 742.661,
+      "eval_steps_per_second": 11.883,
+      "step": 198000
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 0.00021456030572718866,
+      "loss": 0.2944,
+      "step": 198500
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 0.000214122794303217,
+      "loss": 0.2941,
+      "step": 199000
+    },
+    {
+      "epoch": 5.07,
+      "eval_loss": 0.8159200549125671,
+      "eval_runtime": 1.3775,
+      "eval_samples_per_second": 725.952,
+      "eval_steps_per_second": 11.615,
+      "step": 199000
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 0.00021368463632183912,
+      "loss": 0.2948,
+      "step": 199500
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 0.00021324583657468055,
+      "loss": 0.294,
+      "step": 200000
+    },
+    {
+      "epoch": 5.1,
+      "eval_loss": 0.827436625957489,
+      "eval_runtime": 1.3211,
+      "eval_samples_per_second": 756.949,
+      "eval_steps_per_second": 12.111,
+      "step": 200000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 6.07020172106332e+21,
+  "total_flos": 6.389675380924775e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f449ea92715ca64c5aa73950f43c9ea9816a4a5ad265403dda147f77444d50
+oid sha256:d7193b0396efbae3c97d694737aabe6c7c60bae54e10275e5280d057220eeba1
 size 102501541