Training in progress, step 290000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8ad2cb8ff3175b9f7848007e562d12603a8c18323c57ee3a36077f04ace11d
+oid sha256:f66cb466fc715e72c4ec81e60ba44dcf7a28e75138eb49dc636ee2010b29cf2d
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a667bd305925526eed71d832e21eaecb45af259ca2eb092c78d12e83a2aae49b
+oid sha256:c5cd5f151c22a36aa02e644aa26cc06f8e87218fd6115b2ca7b3a1e141911eae
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
+oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
+oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
+oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
+oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
+oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
+oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
+oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
+oid sha256:47154c3a981c14b1d0cedd6ba126beed80c62fc2e1c96712050a23feb40f3503
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80db35d9a6af0da10cd7cebe3bf01f3932293e48fc6a8607555efe3b5591e844
+oid sha256:39bc196d8aea9810b9698ff8cd04e2aeef8774f706fbd61ae0f0055bbacd0eaf
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.135939650338957,
-  "global_step": 280000,
+  "epoch": 7.390794637851062,
+  "global_step": 290000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5606,11 +5606,211 @@
       "eval_samples_per_second": 788.963,
       "eval_steps_per_second": 12.623,
       "step": 280000
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 0.00013777852207079235,
+      "loss": 0.2848,
+      "step": 280500
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 0.00013730250483349825,
+      "loss": 0.2836,
+      "step": 281000
+    },
+    {
+      "epoch": 7.16,
+      "eval_loss": 0.8174564242362976,
+      "eval_runtime": 1.3231,
+      "eval_samples_per_second": 755.81,
+      "eval_steps_per_second": 12.093,
+      "step": 281000
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 0.00013682668113317584,
+      "loss": 0.2841,
+      "step": 281500
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 0.00013635105617335703,
+      "loss": 0.2839,
+      "step": 282000
+    },
+    {
+      "epoch": 7.19,
+      "eval_loss": 0.8130354881286621,
+      "eval_runtime": 1.2454,
+      "eval_samples_per_second": 802.941,
+      "eval_steps_per_second": 12.847,
+      "step": 282000
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 0.00013587563515539996,
+      "loss": 0.284,
+      "step": 282500
+    },
+    {
+      "epoch": 7.21,
+      "learning_rate": 0.00013540042327843296,
+      "loss": 0.284,
+      "step": 283000
+    },
+    {
+      "epoch": 7.21,
+      "eval_loss": 0.8058344721794128,
+      "eval_runtime": 1.2695,
+      "eval_samples_per_second": 787.692,
+      "eval_steps_per_second": 12.603,
+      "step": 283000
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 0.00013492542573929678,
+      "loss": 0.284,
+      "step": 283500
+    },
+    {
+      "epoch": 7.24,
+      "learning_rate": 0.00013445064773248846,
+      "loss": 0.2839,
+      "step": 284000
+    },
+    {
+      "epoch": 7.24,
+      "eval_loss": 0.8160645961761475,
+      "eval_runtime": 1.2481,
+      "eval_samples_per_second": 801.208,
+      "eval_steps_per_second": 12.819,
+      "step": 284000
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 0.00013397609445010432,
+      "loss": 0.2843,
+      "step": 284500
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 0.00013350177108178288,
+      "loss": 0.2842,
+      "step": 285000
+    },
+    {
+      "epoch": 7.26,
+      "eval_loss": 0.8231968879699707,
+      "eval_runtime": 1.3325,
+      "eval_samples_per_second": 750.455,
+      "eval_steps_per_second": 12.007,
+      "step": 285000
+    },
+    {
+      "epoch": 7.28,
+      "learning_rate": 0.00013302768281464863,
+      "loss": 0.2839,
+      "step": 285500
+    },
+    {
+      "epoch": 7.29,
+      "learning_rate": 0.0001325538348332548,
+      "loss": 0.2835,
+      "step": 286000
+    },
+    {
+      "epoch": 7.29,
+      "eval_loss": 0.8185608386993408,
+      "eval_runtime": 1.2436,
+      "eval_samples_per_second": 804.112,
+      "eval_steps_per_second": 12.866,
+      "step": 286000
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 0.00013208023231952706,
+      "loss": 0.2839,
+      "step": 286500
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 0.0001316068804527066,
+      "loss": 0.2837,
+      "step": 287000
+    },
+    {
+      "epoch": 7.31,
+      "eval_loss": 0.8180215954780579,
+      "eval_runtime": 1.2676,
+      "eval_samples_per_second": 788.901,
+      "eval_steps_per_second": 12.622,
+      "step": 287000
+    },
+    {
+      "epoch": 7.33,
+      "learning_rate": 0.00013113378440929353,
+      "loss": 0.2841,
+      "step": 287500
+    },
+    {
+      "epoch": 7.34,
+      "learning_rate": 0.00013066094936299056,
+      "loss": 0.2835,
+      "step": 288000
+    },
+    {
+      "epoch": 7.34,
+      "eval_loss": 0.8164823651313782,
+      "eval_runtime": 1.3849,
+      "eval_samples_per_second": 722.072,
+      "eval_steps_per_second": 11.553,
+      "step": 288000
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 0.00013018838048464582,
+      "loss": 0.2834,
+      "step": 288500
+    },
+    {
+      "epoch": 7.37,
+      "learning_rate": 0.00012971608294219702,
+      "loss": 0.2835,
+      "step": 289000
+    },
+    {
+      "epoch": 7.37,
+      "eval_loss": 0.8121501207351685,
+      "eval_runtime": 1.2558,
+      "eval_samples_per_second": 796.286,
+      "eval_steps_per_second": 12.741,
+      "step": 289000
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 0.00012924406190061423,
+      "loss": 0.2835,
+      "step": 289500
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 0.0001287723225218441,
+      "loss": 0.2832,
+      "step": 290000
+    },
+    {
+      "epoch": 7.39,
+      "eval_loss": 0.8192352056503296,
+      "eval_runtime": 1.3002,
+      "eval_samples_per_second": 769.098,
+      "eval_steps_per_second": 12.306,
+      "step": 290000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 8.945545533294685e+21,
+  "total_flos": 9.265032672069185e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a667bd305925526eed71d832e21eaecb45af259ca2eb092c78d12e83a2aae49b
+oid sha256:c5cd5f151c22a36aa02e644aa26cc06f8e87218fd6115b2ca7b3a1e141911eae
 size 102501541