Muennighoff commited on
Commit
f1bc96e
·
1 Parent(s): 871d789
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +5 -0
  2. 2b855b50c4py/transformers/config.json +1 -0
  3. 2b855b50c4py/transformers/pytorch_model.bin +3 -0
  4. 2b855b60c4py/transformers/config.json +1 -0
  5. 2b855b60c4py/transformers/pytorch_model.bin +3 -0
  6. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  7. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +3 -0
  8. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +3 -0
  9. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +3 -0
  10. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +3 -0
  11. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +3 -0
  12. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +3 -0
  13. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +3 -0
  14. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +3 -0
  15. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +3 -0
  16. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +3 -0
  17. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
  18. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +3 -0
  19. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +3 -0
  20. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +3 -0
  21. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +3 -0
  22. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +3 -0
  23. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +3 -0
  24. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +3 -0
  25. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +3 -0
  26. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +3 -0
  27. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +3 -0
  28. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
  29. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +3 -0
  30. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +3 -0
  31. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +3 -0
  32. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +3 -0
  33. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +3 -0
  34. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +3 -0
  35. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +3 -0
  36. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +3 -0
  37. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +3 -0
  38. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +3 -0
  39. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
  40. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +3 -0
  41. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +3 -0
  42. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +3 -0
  43. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +3 -0
  44. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +3 -0
  45. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +3 -0
  46. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +3 -0
  47. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +3 -0
  48. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +3 -0
  49. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +3 -0
  50. 2b855b70c4py/global_step52452/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
.gitattributes CHANGED
@@ -32,3 +32,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ evaluation/2b855b50c4py/examples.limited=3000.model=2b855b50c4py.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2022-12-28T13:17:10.jsonl filter=lfs diff=lfs merge=lfs -text
36
+ evaluation/2b855b60c4py/examples.limited=3000.model=2b855b60c4py.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2022-12-28T13:17:23.jsonl filter=lfs diff=lfs merge=lfs -text
37
+ evaluation/2b855b70c4py/examples.limited=3000.model=2b855b70c4py.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2022-12-28T13:17:33.jsonl filter=lfs diff=lfs merge=lfs -text
38
+ evaluation/2b855b80c4py/examples.limited=3000.model=2b855b80c4py.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2022-12-28T13:24:27.jsonl filter=lfs diff=lfs merge=lfs -text
39
+ evaluation/2b855b90c4py/examples.limited=3000.model=2b855b90c4py.task=GEM-wiki_lingua_en.templates=tldr_en.fewshot=1.batchsize=16.seed=1234.timestamp=2022-12-28T13:25:53.jsonl filter=lfs diff=lfs merge=lfs -text
2b855b50c4py/transformers/config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 50304, "n_positions": 2048, "n_embd": 2560, "n_layer": 34, "n_head": 20, "n_inner": 10240, "activation_function": "gelu", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["GPT2LMHeadModel"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.25.0.dev0", "n_ctx": 1024, "gradient_checkpointing": false, "model_type": "gpt2"}
2b855b50c4py/transformers/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e057c1767d3e349447cb3635e979e0b30346792d1a1753caa0c8a58c92f7962d
3
+ size 5903417421
2b855b60c4py/transformers/config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 50304, "n_positions": 2048, "n_embd": 2560, "n_layer": 34, "n_head": 20, "n_inner": 10240, "activation_function": "gelu", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["GPT2LMHeadModel"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.25.0.dev0", "n_ctx": 1024, "gradient_checkpointing": false, "model_type": "gpt2"}
2b855b60c4py/transformers/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad05ab84dc56e975fa3975a1934b79d4255d3f919b8d7fb8c5c81cdf11fed1d6
3
+ size 5903417421
2b855b70c4py/global_step52452/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00537f31fbb3806ee0312c9a67d4f5a5ade0c48c6fc57ffb7ac49de4dad2a744
3
+ size 131677719
2b855b70c4py/global_step52452/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2acbcc4f7021c8ea7b08ca768d3f2b9e78b335bd9a90caa96684187a1a0b3f5f
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deac8492dcebb04428b85de8f8e67fd7e8c4cb98c653c8c1ea3067defad9a0ad
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8012d4a87146ad38c9239b9e06dc61f19e6f0cb454ef81f60438774b12423c9
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9609530eb423ee123165d61cde6404bd4363d1d1985d0a4820a733cdaeab556b
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:450285108f15b492ff1528cf744e5a54414ae89fa9e5793e9b61e4640023557b
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a2a283a7a1ebe72acf420760fc3fe67928cd0bee35af07af6b8ec35798bb8bc
3
+ size 131677677
2b855b70c4py/global_step52452/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8ecb25a96a57bc0bb294ddaa2bdc952f931ed67e980c9e4bbba5801c9b38b4
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd8728950b414f872b0bb040d2c5a223f8dc0777a2986fd7987e4473994092a
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a14a1fc9f118021448373a9380d42fe662a89903e483b9f708b337a70202044
3
+ size 131677869
2b855b70c4py/global_step52452/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48fea8b61f279342e9cd1c6c93a0ac794cb50cea02ae7aa8353d4cda76d776d3
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac24b3ec72c5feffd8269aaced9912b718c421843338051447c0aa2ad2083577
3
+ size 131677794
2b855b70c4py/global_step52452/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81a94f33917490be15c6635c91db29c67542f2815af582293780e94fd96c08be
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce47ecd1a7d9da8a7f9c695e634b1ea097850301a872209b79b762b455750f4a
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0840755b0a3489fddd19bf28719806b4870a549cd229de4acf834f22b106cf02
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdd697c58044fb15e716429048359c5ccc2ffd7530950f51212247722746b723
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a69a277a948d3c87b2d342623da478abd4ef3115f3d79d69827c78af5dcf52
3
+ size 131677677
2b855b70c4py/global_step52452/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17bab5bea4ea4e998b24f727b2711a619eb8c3716d6f39d361847e7654561986
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36079ae0437f928ee7396e7f6dc6d7658d69344334a21676ec0f210c35a6406f
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f3e1b79d45e07106499267895938d98a9da403cf20ece7b4eef3b0c412be438
3
+ size 131677677
2b855b70c4py/global_step52452/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55822f5fa42fb7f971595d3d029dc10a0fc2fe568aaa90387542bc6ba000f984
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bb67322a0b2fb73b6d41d00d929f073e45f63d6bfb6a2577d8dcbd792079908
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f21183912e0be11e5f0e0fe95ec546fca33e03c52647e3deda5ded88970652
3
+ size 131677730
2b855b70c4py/global_step52452/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06722e3fa2dd0c1db83091d155c9a8c9eb0978fc84b1c3f64bcf171090796b7
3
+ size 131677677
2b855b70c4py/global_step52452/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54d355ed9bcf371f368ff883929eb838fde7c9f9e6fb1f7926df0dea7ad89418
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea8ca07e12cfe974a2e3c9e4e30b6d9d2b4bbff0dade81533081c93c09bb46
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee99f357cd85d88daf7bfea9224fbc9e93a7b88bb062669f95b6e91ab97753ed
3
+ size 131677869
2b855b70c4py/global_step52452/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498725dce04d6cf6c6c38c412890176d29730ea1b3e5526215dd74d09c6b3b64
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:557229bbf18389d68414370f9d784a1e246b037ef12281f942710112fc7a2103
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f0c9009bdbc53696c3451cdd0ede93a87fbe69a6416e0fd30c00746494e842
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed4512736554568ee69f19b7fe229f9a7d5cbf93edcdc5921e61f035ae4d9e91
3
+ size 131677677
2b855b70c4py/global_step52452/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c64287ab0555267e987a0357589569a33ec2ddaa3259c520fd4129ef74f6971
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4598625e28446fa815ce2674a5afe89386b3019a04786063fb56d166f0d0ba13
3
+ size 131677677
2b855b70c4py/global_step52452/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8be09ca56417b1bf627fa1eb841eeeb56e8b2f4e2f623fb590fcc54d44629e6
3
+ size 131677730
2b855b70c4py/global_step52452/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6a7e1876d25a554f3a3ecee5016a466d457202c40a2648ce1fe05820fb7f8b7
3
+ size 131677869
2b855b70c4py/global_step52452/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7efd0dd1b102be6f55d517291edfe6eedf0b83294d779de653032d0b5f9171ac
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42a76ee1d382f9a563e0d9a240b78f6ef82228293980b4a4a8f850101ec87a2
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f974fd3dcf7bf9117a60c4aac6ba350f07341fd6dcf6b35840d64ae4f3c65682
3
+ size 131677677
2b855b70c4py/global_step52452/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3609e447c0cd5e5d1a0485a0fe54173170123f0499ee1aba8a20ffcb6a8fe738
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae25b4f356009bd90636bd1d0fb7cfd7bf87642fe7025d37fe5f991b6cd1536
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1b76e49aaa3cd05d0bdbba9d331e92f9459559b1c31245224e16d53a0b042a
3
+ size 131677741
2b855b70c4py/global_step52452/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ef11c6eda26a3c046d35aeb2309555363173cb96686f39e1f6cb9fc7b579bb7
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3fa0378e0032c32883595b16fb6654cc07e83dcee518a0ac2fe910fa6951972
3
+ size 131677869
2b855b70c4py/global_step52452/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5463e34356027c3041658f8c17f8cfb80aebc437c7848c5c2111db254e361d81
3
+ size 131677805
2b855b70c4py/global_step52452/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f561cff01a657f552db2c02ffc9b40fb813f188d5a4311985152c82e7c9a1a8
3
+ size 131677666