Upload folder using huggingface_hub

checkpoint-400/global_step400/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b443973cf22380c2fc16584c972c310902059fa4c63e51a119e69b6f308eb800
+oid sha256:ef0c10789bcb3eda527750b2f1fc97a2ad5ed9cd117ea557ea5876e3b4b44b50
 size 134451731

checkpoint-400/global_step400/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6787553b3e8478fbb464ffe2a2853d9a134d05d7c06b9c73bf27b4dc40c1ca8
+oid sha256:12c9ba6d05015fe5405a9da936ed3e2f5ff9f7661e6429ecaf2e460a28390e0f
 size 4163799934

checkpoint-400/global_step400/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a733b98fead9026a9e9b3c991b94d5afe9362cd870a68a5d993bba3b2884b8
+oid sha256:fde5b7d09fef56b9d25a86dcfc89fc47c3d11782b9142ae1375e0b2f6da98cf2
 size 134451731

checkpoint-400/global_step400/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4fdb00150d6cbd23d63d06437f63d607eff593e434a040578b03a0a3e0636e
+oid sha256:d06a601056b5affbe24fa4a0a318918685d84c434bc0801a6118b8cc7cb8b868
 size 4163799934

checkpoint-400/global_step400/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f771a4631a295abb6667f1eef70ff6fbefff786402fbbfef2217d86f4026171
+oid sha256:f2015eb61ead1392e69766d89a0db16792e13811733af10d425ece514b3be05c
 size 134451731

checkpoint-400/global_step400/zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fea132091a15f7daa55d3a4d43726501974454e3ccad0a103d52a1f6a7d8b3a
+oid sha256:be6cba9a80a6b026a6e338c39e5b992d1866119a6048cb6e6948586ef4f9bcab
 size 4163799934

checkpoint-400/global_step400/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ecb932c3f382d6a7f6c688ef26c4e32534ca433b33d56ba4b70df8438a6fe4b
+oid sha256:c72cb5735a2083a90cecb19bac5d9560f458ccacb59b050bef801b7f9eba8c19
 size 134451731

checkpoint-400/global_step400/zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205e45caf0a44e886ee36cac4a4d40ea787f1841723963ff8194c319a7e3481f
+oid sha256:979be6fa6ba16d52e471436be61d798561b86e39a66b245978498d3735530f42
 size 4163799934

checkpoint-400/global_step400/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10720f1a234f7b2ab376a623d5218887e48cfdcacad17725993844b0eda0763e
+oid sha256:fb749e1d8758b3454505a3c583bd27630b93b41c714987a246c17e86b6e3cf9f
 size 134451731

checkpoint-400/global_step400/zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:548bf66ce543d3ed57485cbda186fc8db9bab6381c0b3c7eb9634d572662cadd
+oid sha256:89973fee08655591a7ed78b4e0fd8dc5fe0c107b072262f490a446e7393b5a16
 size 4163799934

checkpoint-400/global_step400/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:210b90a137e881d53e17439d919c913a9dd8ead2859a89f55a8e65260b9b8c0a
+oid sha256:9db75fcb1f612036494b3ad7f3f9893f60ba84ac4f0921ad84194c9af37492c6
 size 134451731

checkpoint-400/global_step400/zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4677ce5e7b8ec18a66928493450dba598e12c191a207cd683580248876befc4c
+oid sha256:4631100a870e917734cf6d6120894642f41aef69bbf857a49363712a8419df7b
 size 4163799934

checkpoint-400/global_step400/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12494b56eedd538b14b95fd268aabdf9b41a1a5c6cd79d74588ee9ec4d27c09a
+oid sha256:f6166a921ec43052d4a68a1c89f6eac86c97f6992a468d880a1746e02389a32b
 size 134451731

checkpoint-400/global_step400/zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d948a9c3f5efc1f767cbd9376871f7feb26885d218b80a623c62544f46e4432
+oid sha256:be2f16ff9afc318399b12b0373e1a435fb2f62cd9640ecb8b22068e0e32d6c9b
 size 4163799934

checkpoint-400/global_step400/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc870118a24cd9aa6a6d4b6ec8233b37421cdea47cd9bc43821f1c4d36cdcd5
+oid sha256:ae86cf4d7adb3ca6934324b24c2cd1f3b078c6e9d1c245147b7587e81a2e9b79
 size 134451731

checkpoint-400/global_step400/zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f098bcef0aaad73b511323689dde104708e88d4b20052557cee754ac1e3bb800
+oid sha256:debed0eca41e789b85121bc469404216f166208725234b6af79b78cf885c58d9
 size 4163799934

checkpoint-400/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2baf929fc95bef2cf669334d46693c0d8619f1a1448c9212da17cd1e763d0078
+oid sha256:12d7ad2052b524441df7eb0291f23bd6f573dd8161c99830c26ce2a38a2f113b
 size 5686106713

checkpoint-400/trainer_state.json

@@ -10,91 +10,91 @@
     {
       "epoch": 6.67,
       "learning_rate": 1.5357481488588927e-05,
-      "loss": 1.9835,
+      "loss": 1.9677,
       "step": 10
     },
     {
       "epoch": 13.33,
       "learning_rate": 2e-05,
-      "loss": 1.0763,
+      "loss": 1.0371,
       "step": 20
     },
     {
       "epoch": 20.0,
       "learning_rate": 2e-05,
-      "loss": 0.2284,
+      "loss": 0.2217,
       "step": 30
     },
     {
       "epoch": 26.67,
       "learning_rate": 2e-05,
-      "loss": 0.0691,
+      "loss": 0.0689,
       "step": 40
     },
     {
       "epoch": 33.33,
       "learning_rate": 2e-05,
-      "loss": 0.0442,
+      "loss": 0.0456,
       "step": 50
     },
     {
       "epoch": 40.0,
       "learning_rate": 2e-05,
-      "loss": 0.0319,
+      "loss": 0.0316,
       "step": 60
     },
     {
       "epoch": 46.67,
       "learning_rate": 2e-05,
-      "loss": 0.0243,
+      "loss": 0.0248,
       "step": 70
     },
     {
       "epoch": 53.33,
       "learning_rate": 2e-05,
-      "loss": 0.0186,
+      "loss": 0.0189,
       "step": 80
     },
     {
       "epoch": 60.0,
       "learning_rate": 2e-05,
-      "loss": 0.0149,
+      "loss": 0.0144,
       "step": 90
     },
     {
       "epoch": 66.67,
       "learning_rate": 2e-05,
-      "loss": 0.0119,
+      "loss": 0.0113,
       "step": 100
     },
     {
       "epoch": 73.33,
       "learning_rate": 2e-05,
-      "loss": 0.0103,
+      "loss": 0.0098,
       "step": 110
     },
     {
       "epoch": 80.0,
       "learning_rate": 2e-05,
-      "loss": 0.0091,
+      "loss": 0.009,
       "step": 120
     },
     {
       "epoch": 86.67,
       "learning_rate": 2e-05,
-      "loss": 0.0081,
+      "loss": 0.0076,
       "step": 130
     },
     {
       "epoch": 93.33,
       "learning_rate": 2e-05,
-      "loss": 0.0073,
+      "loss": 0.0075,
       "step": 140
     },
     {
       "epoch": 100.0,
       "learning_rate": 2e-05,
-      "loss": 0.0064,
+      "loss": 0.0065,
       "step": 150
     },
     {
@@ -106,61 +106,61 @@
     {
       "epoch": 113.33,
       "learning_rate": 2e-05,
-      "loss": 0.0059,
+      "loss": 0.0057,
       "step": 170
     },
     {
       "epoch": 120.0,
       "learning_rate": 2e-05,
-      "loss": 0.0057,
+      "loss": 0.0054,
       "step": 180
     },
     {
       "epoch": 126.67,
       "learning_rate": 2e-05,
-      "loss": 0.0054,
+      "loss": 0.0079,
       "step": 190
     },
     {
       "epoch": 133.33,
       "learning_rate": 2e-05,
-      "loss": 0.0052,
+      "loss": 0.0063,
       "step": 200
     },
     {
       "epoch": 140.0,
       "learning_rate": 2e-05,
-      "loss": 0.0049,
+      "loss": 0.0058,
       "step": 210
     },
     {
       "epoch": 146.67,
       "learning_rate": 2e-05,
-      "loss": 0.0046,
+      "loss": 0.005,
       "step": 220
     },
     {
       "epoch": 153.33,
       "learning_rate": 2e-05,
-      "loss": 0.0045,
+      "loss": 0.005,
       "step": 230
     },
     {
       "epoch": 160.0,
       "learning_rate": 2e-05,
-      "loss": 0.0044,
+      "loss": 0.0047,
       "step": 240
     },
     {
       "epoch": 166.67,
       "learning_rate": 2e-05,
-      "loss": 0.0043,
+      "loss": 0.0046,
       "step": 250
     },
     {
       "epoch": 173.33,
       "learning_rate": 2e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 260
     },
     {
@@ -172,13 +172,13 @@
     {
       "epoch": 186.67,
       "learning_rate": 2e-05,
-      "loss": 0.0044,
+      "loss": 0.0042,
       "step": 280
     },
     {
       "epoch": 193.33,
       "learning_rate": 2e-05,
-      "loss": 0.0041,
+      "loss": 0.0043,
       "step": 290
     },
     {
@@ -190,13 +190,13 @@
     {
       "epoch": 206.67,
       "learning_rate": 2e-05,
-      "loss": 0.0043,
+      "loss": 0.0038,
       "step": 310
     },
     {
       "epoch": 213.33,
       "learning_rate": 2e-05,
-      "loss": 0.004,
+      "loss": 0.0039,
       "step": 320
     },
     {
@@ -208,19 +208,19 @@
     {
       "epoch": 226.67,
       "learning_rate": 2e-05,
-      "loss": 0.0041,
+      "loss": 0.0038,
       "step": 340
     },
     {
       "epoch": 233.33,
       "learning_rate": 2e-05,
-      "loss": 0.0039,
+      "loss": 0.0034,
       "step": 350
     },
     {
       "epoch": 240.0,
       "learning_rate": 2e-05,
-      "loss": 0.0039,
+      "loss": 0.0037,
       "step": 360
     },
     {
@@ -232,19 +232,19 @@
     {
       "epoch": 253.33,
       "learning_rate": 2e-05,
-      "loss": 0.0039,
+      "loss": 0.0037,
       "step": 380
     },
     {
       "epoch": 260.0,
       "learning_rate": 2e-05,
-      "loss": 0.0039,
+      "loss": 0.0037,
       "step": 390
     },
     {
       "epoch": 266.67,
       "learning_rate": 2e-05,
-      "loss": 0.0038,
+      "loss": 0.0036,
       "step": 400
     }
   ],

checkpoint-400/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2188a20782c485df4937a49e7b018f87feb047b94549b3e8907cdc9eff5c9801
+oid sha256:d27383b338ae82946f100d10bfcecddd777acad3c5731d207d2c433e024bc936
 size 5563

flyte_training_config.json

@@ -1 +1 @@
-{"base_model": "togethercomputer/RedPajama-INCITE-Base-3B-v1", "data_path": "wikipedia", "data_name": "20220301.simple", "num_epochs": 1, "max_steps": 600, "learning_rate": 2e-05, "weight_decay": 0.02, "warmup_ratio": 0.03, "lr_scheduler_type": "cosine", "batch_size": 16, "micro_batch_size": 1, "val_set_size": 0, "group_by_length": false, "instruction_key": "instruction", "input_key": "input", "output_key": "output", "device_map": "auto", "cache_dir": null, "optim": "adamw_torch", "model_max_length": 512, "debug_mode": false, "debug_train_data_size": 1024, "wandb_project": ""}
+{"base_model": "togethercomputer/RedPajama-INCITE-Base-3B-v1", "data_path": "wikipedia", "data_name": "20220301.simple", "num_epochs": 1, "max_steps": 500, "learning_rate": 2e-05, "weight_decay": 0.02, "warmup_ratio": 0.03, "lr_scheduler_type": "cosine", "batch_size": 16, "micro_batch_size": 1, "val_set_size": 0, "group_by_length": false, "instruction_key": "instruction", "input_key": "input", "output_key": "output", "device_map": "auto", "cache_dir": null, "optim": "adamw_torch", "model_max_length": 512, "debug_mode": false, "debug_train_data_size": 1024, "wandb_project": ""}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef169a3afa7399d0902467f5eee63dbdc13551b74cca448925e7531d1b88c5e6
+oid sha256:1c78fce58791364df7963a13abee4f3dbeed8e23b68478b2387491d1158a55cb
 size 5686106713

trainer_state.json

@@ -1,136 +1,136 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 400.0,
-  "global_step": 600,
+  "epoch": 333.3333333333333,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 6.67,
-      "learning_rate": 1.4388747994087888e-05,
-      "loss": 1.9989,
+      "learning_rate": 1.5357481488588927e-05,
+      "loss": 1.9677,
       "step": 10
     },
     {
       "epoch": 13.33,
       "learning_rate": 2e-05,
-      "loss": 1.1205,
+      "loss": 1.0371,
       "step": 20
     },
     {
       "epoch": 20.0,
       "learning_rate": 2e-05,
-      "loss": 0.2458,
+      "loss": 0.2217,
       "step": 30
     },
     {
       "epoch": 26.67,
       "learning_rate": 2e-05,
-      "loss": 0.0727,
+      "loss": 0.0689,
       "step": 40
     },
     {
       "epoch": 33.33,
       "learning_rate": 2e-05,
-      "loss": 0.0478,
+      "loss": 0.0456,
       "step": 50
     },
     {
       "epoch": 40.0,
       "learning_rate": 2e-05,
-      "loss": 0.0351,
+      "loss": 0.0316,
       "step": 60
     },
     {
       "epoch": 46.67,
       "learning_rate": 2e-05,
-      "loss": 0.0258,
+      "loss": 0.0248,
       "step": 70
     },
     {
       "epoch": 53.33,
       "learning_rate": 2e-05,
-      "loss": 0.0196,
+      "loss": 0.0189,
       "step": 80
     },
     {
       "epoch": 60.0,
       "learning_rate": 2e-05,
-      "loss": 0.0158,
+      "loss": 0.0144,
       "step": 90
     },
     {
       "epoch": 66.67,
       "learning_rate": 2e-05,
-      "loss": 0.0132,
+      "loss": 0.0113,
       "step": 100
     },
     {
       "epoch": 73.33,
       "learning_rate": 2e-05,
-      "loss": 0.0112,
+      "loss": 0.0098,
       "step": 110
     },
     {
       "epoch": 80.0,
       "learning_rate": 2e-05,
-      "loss": 0.0099,
+      "loss": 0.009,
       "step": 120
     },
     {
       "epoch": 86.67,
       "learning_rate": 2e-05,
-      "loss": 0.009,
+      "loss": 0.0076,
       "step": 130
     },
     {
       "epoch": 93.33,
       "learning_rate": 2e-05,
-      "loss": 0.0077,
+      "loss": 0.0075,
       "step": 140
     },
     {
       "epoch": 100.0,
       "learning_rate": 2e-05,
-      "loss": 0.0073,
+      "loss": 0.0065,
       "step": 150
     },
     {
       "epoch": 106.67,
       "learning_rate": 2e-05,
-      "loss": 0.0068,
+      "loss": 0.0064,
       "step": 160
     },
     {
       "epoch": 113.33,
       "learning_rate": 2e-05,
-      "loss": 0.0064,
+      "loss": 0.0057,
       "step": 170
     },
     {
       "epoch": 120.0,
       "learning_rate": 2e-05,
-      "loss": 0.0062,
+      "loss": 0.0054,
       "step": 180
     },
     {
       "epoch": 126.67,
       "learning_rate": 2e-05,
-      "loss": 0.0057,
+      "loss": 0.0079,
       "step": 190
     },
     {
       "epoch": 133.33,
       "learning_rate": 2e-05,
-      "loss": 0.0056,
+      "loss": 0.0063,
       "step": 200
     },
     {
       "epoch": 140.0,
       "learning_rate": 2e-05,
-      "loss": 0.0054,
+      "loss": 0.0058,
       "step": 210
     },
     {
@@ -154,19 +154,19 @@
     {
       "epoch": 166.67,
       "learning_rate": 2e-05,
-      "loss": 0.0045,
+      "loss": 0.0046,
       "step": 250
     },
     {
       "epoch": 173.33,
       "learning_rate": 2e-05,
-      "loss": 0.0046,
+      "loss": 0.0043,
       "step": 260
     },
     {
       "epoch": 180.0,
       "learning_rate": 2e-05,
-      "loss": 0.0044,
+      "loss": 0.0043,
       "step": 270
     },
     {
@@ -184,37 +184,37 @@
     {
       "epoch": 200.0,
       "learning_rate": 2e-05,
-      "loss": 0.0043,
+      "loss": 0.0042,
       "step": 300
     },
     {
       "epoch": 206.67,
       "learning_rate": 2e-05,
-      "loss": 0.0041,
+      "loss": 0.0038,
       "step": 310
     },
     {
       "epoch": 213.33,
       "learning_rate": 2e-05,
-      "loss": 0.0042,
+      "loss": 0.0039,
       "step": 320
     },
     {
       "epoch": 220.0,
       "learning_rate": 2e-05,
-      "loss": 0.0041,
+      "loss": 0.004,
       "step": 330
     },
     {
       "epoch": 226.67,
       "learning_rate": 2e-05,
-      "loss": 0.0042,
+      "loss": 0.0038,
       "step": 340
     },
     {
       "epoch": 233.33,
       "learning_rate": 2e-05,
-      "loss": 0.004,
+      "loss": 0.0034,
       "step": 350
     },
     {
@@ -226,31 +226,31 @@
     {
       "epoch": 246.67,
       "learning_rate": 2e-05,
-      "loss": 0.004,
+      "loss": 0.0038,
       "step": 370
     },
     {
       "epoch": 253.33,
       "learning_rate": 2e-05,
-      "loss": 0.0039,
+      "loss": 0.0037,
       "step": 380
     },
     {
       "epoch": 260.0,
       "learning_rate": 2e-05,
-      "loss": 0.0041,
+      "loss": 0.0037,
       "step": 390
     },
     {
       "epoch": 266.67,
       "learning_rate": 2e-05,
-      "loss": 0.004,
+      "loss": 0.0036,
       "step": 400
     },
     {
       "epoch": 273.33,
       "learning_rate": 2e-05,
-      "loss": 0.0039,
+      "loss": 0.0037,
       "step": 410
     },
     {
@@ -262,31 +262,31 @@
     {
       "epoch": 286.67,
       "learning_rate": 2e-05,
-      "loss": 0.0037,
+      "loss": 0.0038,
       "step": 430
     },
     {
       "epoch": 293.33,
       "learning_rate": 2e-05,
-      "loss": 0.0038,
+      "loss": 0.0036,
       "step": 440
     },
     {
       "epoch": 300.0,
       "learning_rate": 2e-05,
-      "loss": 0.0039,
+      "loss": 0.0035,
       "step": 450
     },
     {
       "epoch": 306.67,
       "learning_rate": 2e-05,
-      "loss": 0.0038,
+      "loss": 0.0037,
       "step": 460
     },
     {
       "epoch": 313.33,
       "learning_rate": 2e-05,
-      "loss": 0.0042,
+      "loss": 0.0038,
       "step": 470
     },
     {
@@ -298,88 +298,28 @@
     {
       "epoch": 326.67,
       "learning_rate": 2e-05,
-      "loss": 0.0039,
+      "loss": 0.0036,
       "step": 490
     },
     {
       "epoch": 333.33,
       "learning_rate": 2e-05,
-      "loss": 0.0037,
+      "loss": 0.0036,
       "step": 500
     },
     {
-      "epoch": 340.0,
-      "learning_rate": 2e-05,
-      "loss": 0.0039,
-      "step": 510
-    },
-    {
-      "epoch": 346.67,
-      "learning_rate": 2e-05,
-      "loss": 0.0038,
-      "step": 520
-    },
-    {
-      "epoch": 353.33,
-      "learning_rate": 2e-05,
-      "loss": 0.0039,
-      "step": 530
-    },
-    {
-      "epoch": 360.0,
-      "learning_rate": 2e-05,
-      "loss": 0.004,
-      "step": 540
-    },
-    {
-      "epoch": 366.67,
-      "learning_rate": 2e-05,
-      "loss": 0.0041,
-      "step": 550
-    },
-    {
-      "epoch": 373.33,
-      "learning_rate": 2e-05,
-      "loss": 0.004,
-      "step": 560
-    },
-    {
-      "epoch": 380.0,
-      "learning_rate": 2e-05,
-      "loss": 0.0038,
-      "step": 570
-    },
-    {
-      "epoch": 386.67,
-      "learning_rate": 2e-05,
-      "loss": 0.0043,
-      "step": 580
-    },
-    {
-      "epoch": 393.33,
-      "learning_rate": 2e-05,
-      "loss": 0.0044,
-      "step": 590
-    },
-    {
-      "epoch": 400.0,
-      "learning_rate": 2e-05,
-      "loss": 0.0045,
-      "step": 600
-    },
-    {
-      "epoch": 400.0,
-      "step": 600,
-      "total_flos": 252437248081920.0,
-      "train_loss": 0.06393463966126244,
-      "train_runtime": 25615.4629,
-      "train_samples_per_second": 2.998,
+      "epoch": 333.33,
+      "step": 500,
+      "total_flos": 210359990353920.0,
+      "train_loss": 0.07269182289391755,
+      "train_runtime": 21326.3915,
+      "train_samples_per_second": 3.001,
       "train_steps_per_second": 0.023
     }
   ],
-  "max_steps": 600,
-  "num_train_epochs": 600,
-  "total_flos": 252437248081920.0,
+  "max_steps": 500,
+  "num_train_epochs": 500,
+  "total_flos": 210359990353920.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca119656b0c065b976f0609f35399b6dc7949ec169648835cc1620bd5d7ea119
+oid sha256:d27383b338ae82946f100d10bfcecddd777acad3c5731d207d2c433e024bc936
 size 5563