Upload folder using huggingface_hub

.gitattributes

@@ -86,3 +86,12 @@ flytet2ycrlv6/local_flytekit/faa0c0e4bee4bd512a5fe448c325d4ac/flyte-n_5ajos6/san
 flytet2ycrlv6/local_flytekit/faa0c0e4bee4bd512a5fe448c325d4ac/flyte-nfrsb6tj/sandbox/local_flytekit/ac8e394f8d5951aa902d8954089f2ee7/00000 filter=lfs diff=lfs merge=lfs -text
 flytet2ycrlv6/local_flytekit/faa0c0e4bee4bd512a5fe448c325d4ac/flyte-yfnwy3oa/sandbox/local_flytekit/92cdb3caaae47f47d0ec3ea5ea850d37/00000 filter=lfs diff=lfs merge=lfs -text
 flytet2ycrlv6/local_flytekit/faa0c0e4bee4bd512a5fe448c325d4ac/models--togethercomputer--RedPajama-INCITE-Base-3B-v1/blobs/844708c42241de49775b872663ad58422a35b8e5a7d50b1f808408db8c1fb84b filter=lfs diff=lfs merge=lfs -text
+flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-4cfkymcd/sandbox/local_flytekit/ac62304dcd93efb7f70889060117e3fe/00000 filter=lfs diff=lfs merge=lfs -text
+flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-4q2w_rwy/sandbox/local_flytekit/dbd2ca746875e688d31715058d2c6053/00000 filter=lfs diff=lfs merge=lfs -text
+flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-82nqk4w0/sandbox/local_flytekit/49514a1872a4bad4a98a17419b9144b1/00000 filter=lfs diff=lfs merge=lfs -text
+flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-ekw5z4k8/sandbox/local_flytekit/6c65d7cd91fd6e22f9363cf6f418c644/00000 filter=lfs diff=lfs merge=lfs -text
+flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-hazc2d7f/sandbox/local_flytekit/034ef16fc317187112251f7824655542/00000 filter=lfs diff=lfs merge=lfs -text
+flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-le2pt09a/sandbox/local_flytekit/1cc32a933cca0e6c5306e62a23a36936/00000 filter=lfs diff=lfs merge=lfs -text
+flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-tz8lbfds/sandbox/local_flytekit/202b258b898f9254dc79ceac1de43c88/00000 filter=lfs diff=lfs merge=lfs -text
+flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-uar2souv/sandbox/local_flytekit/cc50b53b143467dd7cd9fc1ef31d8024/00000 filter=lfs diff=lfs merge=lfs -text
+flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/models--togethercomputer--RedPajama-INCITE-Base-3B-v1/blobs/844708c42241de49775b872663ad58422a35b8e5a7d50b1f808408db8c1fb84b filter=lfs diff=lfs merge=lfs -text

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": 100, "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": 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": ""}

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "togethercomputer/RedPajama-INCITE-Base-3B-v1",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 50432
+}

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.29.2"
+}

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8b8bc0ffe6d5ddb8c9a708c551cb0a7c431408b464036a0d327abcab4ee1fe
+size 134451731

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea8f9372751f5b892635e46ad5663fa496d4c64ed1812950776ef8370ec99ad5
+size 4163799934

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0037cff251b91281af741e6d594c5d0faf01852a89de1082c6241cf6a7e7e3ce
+size 134451731

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:537f9ec9fe121cedb0fa51712c5c312a7b64c9afe84757c18d1912dae304b7bc
+size 4163799934

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b9dffefd8affda097a4a50348bffc3e304b22ec43148ec91cd27e8f1602e06
+size 134451731

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62dda00b5c9c549ce154ae2eb2163e237a0c64fe61de09dd107eab3d76598e77
+size 4163799934

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279e97699a2b117d41aa025ed11a71537d820abbd021d95edfafd473ac08c925
+size 134451731

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d7709dd5c8f15f93bf93aa7c84e973680a733c1262ac32e35486afc53f58e1e
+size 4163799934

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f88b0f89feeb546be51a38b2f9634048adecf48e76fe3bfd0d062d25a8a7ca1
+size 134451731

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2801d5e6333cb9bd6c54a94f10cce16dd6160b1bcd683e0affac574ce512806
+size 4163799934

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce8e85b2ea564f3ec4a25b0792a2be886ec032995f5ddce5fc0411afec8f26f
+size 134451731

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d18f17134066d982c7b50a9f9fe474082f82a8cc880f2bfe66f504a3e6d7740
+size 4163799934

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b427c9ab40845cd9d7343eba227cfc9cfbe05940c689688fdcdcdff14de7ce2
+size 134451731

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51114f5d47ca8063ae31c4ea5a166f2a8cdb66ff62bdcb0244a222c7af9f8ec8
+size 4163799934

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4593166ebab0e00ec035eb718df5fc90ede816c339e117d507761f5a6996425
+size 134451731

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/global_step600/zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e8d721a5805ac6288a8b10d2b4664aab327a6f047d30bb4f08332df7393cef0
+size 4163799934

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/latest

@@ -0,0 +1 @@
+global_step600

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef169a3afa7399d0902467f5eee63dbdc13551b74cca448925e7531d1b88c5e6
+size 5686106713

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f951d60f8a1d9e9164b202423f407b73a0694c7dc86515b50179cbc406e74e8b
+size 21687

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d8c9492c4a0528ff4cb5fe427af80fa86fa170ca65304287f2e743e3f28ee2
+size 21687

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c061a15dc81ab8a0ec638615f0b5293e680066b9ea61809b829b2c61d865ecf
+size 21687

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71767783ad4f0b58328625cde99082571b10f144ecc010a25e0cdad33ed2893
+size 21687

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614d4e66bccc234afe1ad456b4cd903190e30c1cc6f93a75b7c3199b1e79cb84
+size 21687

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad784f6867bcd0671063e3489a9f9483932ef45ed0b1a948dbe06b29030a790
+size 21687

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa935e4bb3088c91f5f5d63c9d7f6a89577ee6ae9b05647e0e98911b4db9cb7f
+size 21687

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629122cf75578db60fd3210f61c496b8e2c9f07c4a1879036faf64dac1e86587
+size 21687

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "unk_token": "<|endoftext|>"
+}

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/trainer_state.json

@@ -0,0 +1,376 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 400.0,
+  "global_step": 600,
+  "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,
+      "step": 10
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 2e-05,
+      "loss": 1.1205,
+      "step": 20
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2e-05,
+      "loss": 0.2458,
+      "step": 30
+    },
+    {
+      "epoch": 26.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0727,
+      "step": 40
+    },
+    {
+      "epoch": 33.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0478,
+      "step": 50
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0351,
+      "step": 60
+    },
+    {
+      "epoch": 46.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0258,
+      "step": 70
+    },
+    {
+      "epoch": 53.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0196,
+      "step": 80
+    },
+    {
+      "epoch": 60.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0158,
+      "step": 90
+    },
+    {
+      "epoch": 66.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0132,
+      "step": 100
+    },
+    {
+      "epoch": 73.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0112,
+      "step": 110
+    },
+    {
+      "epoch": 80.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0099,
+      "step": 120
+    },
+    {
+      "epoch": 86.67,
+      "learning_rate": 2e-05,
+      "loss": 0.009,
+      "step": 130
+    },
+    {
+      "epoch": 93.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0077,
+      "step": 140
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0073,
+      "step": 150
+    },
+    {
+      "epoch": 106.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0068,
+      "step": 160
+    },
+    {
+      "epoch": 113.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0064,
+      "step": 170
+    },
+    {
+      "epoch": 120.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0062,
+      "step": 180
+    },
+    {
+      "epoch": 126.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0057,
+      "step": 190
+    },
+    {
+      "epoch": 133.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0056,
+      "step": 200
+    },
+    {
+      "epoch": 140.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0054,
+      "step": 210
+    },
+    {
+      "epoch": 146.67,
+      "learning_rate": 2e-05,
+      "loss": 0.005,
+      "step": 220
+    },
+    {
+      "epoch": 153.33,
+      "learning_rate": 2e-05,
+      "loss": 0.005,
+      "step": 230
+    },
+    {
+      "epoch": 160.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0047,
+      "step": 240
+    },
+    {
+      "epoch": 166.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0045,
+      "step": 250
+    },
+    {
+      "epoch": 173.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0046,
+      "step": 260
+    },
+    {
+      "epoch": 180.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0044,
+      "step": 270
+    },
+    {
+      "epoch": 186.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0042,
+      "step": 280
+    },
+    {
+      "epoch": 193.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0043,
+      "step": 290
+    },
+    {
+      "epoch": 200.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0043,
+      "step": 300
+    },
+    {
+      "epoch": 206.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0041,
+      "step": 310
+    },
+    {
+      "epoch": 213.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0042,
+      "step": 320
+    },
+    {
+      "epoch": 220.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0041,
+      "step": 330
+    },
+    {
+      "epoch": 226.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0042,
+      "step": 340
+    },
+    {
+      "epoch": 233.33,
+      "learning_rate": 2e-05,
+      "loss": 0.004,
+      "step": 350
+    },
+    {
+      "epoch": 240.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0037,
+      "step": 360
+    },
+    {
+      "epoch": 246.67,
+      "learning_rate": 2e-05,
+      "loss": 0.004,
+      "step": 370
+    },
+    {
+      "epoch": 253.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0039,
+      "step": 380
+    },
+    {
+      "epoch": 260.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0041,
+      "step": 390
+    },
+    {
+      "epoch": 266.67,
+      "learning_rate": 2e-05,
+      "loss": 0.004,
+      "step": 400
+    },
+    {
+      "epoch": 273.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0039,
+      "step": 410
+    },
+    {
+      "epoch": 280.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0038,
+      "step": 420
+    },
+    {
+      "epoch": 286.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0037,
+      "step": 430
+    },
+    {
+      "epoch": 293.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0038,
+      "step": 440
+    },
+    {
+      "epoch": 300.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0039,
+      "step": 450
+    },
+    {
+      "epoch": 306.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0038,
+      "step": 460
+    },
+    {
+      "epoch": 313.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0042,
+      "step": 470
+    },
+    {
+      "epoch": 320.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0037,
+      "step": 480
+    },
+    {
+      "epoch": 326.67,
+      "learning_rate": 2e-05,
+      "loss": 0.0039,
+      "step": 490
+    },
+    {
+      "epoch": 333.33,
+      "learning_rate": 2e-05,
+      "loss": 0.0037,
+      "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
+    }
+  ],
+  "max_steps": 600,
+  "num_train_epochs": 600,
+  "total_flos": 252437248081920.0,
+  "trial_name": null,
+  "trial_params": null
+}

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca119656b0c065b976f0609f35399b6dc7949ec169648835cc1620bd5d7ea119
+size 5563

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/checkpoint-600/zero_to_fp32.py

@@ -0,0 +1,483 @@
+#!/usr/bin/env python
+'''Copyright The Microsoft DeepSpeed Team'''
+
+# This script extracts fp32 consolidated weights from a zero 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION,
+                                            OPTIMIZER_STATE_DICT,
+                                            SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS,
+                                            ZERO_STAGE,
+                                            PARTITION_COUNT,
+                                            PARAM_SHAPES,
+                                            BUFFER_NAMES)
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage == 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_optim_files(checkpoint_dir):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    optim_files = sorted(glob.glob(os.path.join(checkpoint_dir,
+                                                "*_optim_states.pt")),
+                         key=natural_keys)
+
+    if len(optim_files) == 0:
+        raise FileNotFoundError(
+            f"can't find '*_optim_states.pt' files in directory '{checkpoint_dir}'")
+
+    return optim_files
+
+
+def parse_model_state(file):
+    state_dict = torch.load(file, map_location=device)
+
+    if BUFFER_NAMES not in state_dict:
+        raise ValueError(f"{file} is not a model state checkpoint")
+    buffer_names = state_dict[BUFFER_NAMES]
+    if debug:
+        print("Found buffers:", buffer_names)
+
+    # recover just the buffers while restoring them to fp32 if they were saved in fp16
+    buffers = {
+        k: v.float()
+        for k,
+        v in state_dict["module"].items() if k in buffer_names
+    }
+    param_shapes = state_dict[PARAM_SHAPES]
+
+    ds_version = state_dict.get(DS_VERSION, None)
+
+    return buffers, param_shapes, ds_version
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dicts.append(torch.load(f, map_location=device))
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage == 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage == 2:
+        fp32_flat_groups = [
+            state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key]
+            for i in range(len(state_dicts))
+        ]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key],
+                      0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(
+        f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_file = get_model_state_file(ds_checkpoint_dir, zero_stage)
+    buffers, param_shapes, ds_version = parse_model_state(model_file)
+    print(f'Parsing checkpoint created by deepspeed=={ds_version}')
+
+    if zero_stage == 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size,
+                                                          param_shapes,
+                                                          fp32_flat_groups,
+                                                          buffers)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size,
+                                                          param_shapes,
+                                                          fp32_flat_groups,
+                                                          buffers)
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size,
+                                               param_shapes,
+                                               fp32_flat_groups,
+                                               buffers):
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(
+                    f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum([
+        full_single_fp32_vector.numel()
+        for full_single_fp32_vector in merged_single_partition_of_fp32_groups
+    ])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum(
+            [sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    state_dict = OrderedDict()
+
+    # buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(
+                    f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} "
+                )
+            state_dict[name] = full_single_fp32_vector.narrow(
+                0,
+                offset,
+                unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(
+                f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(
+        f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements"
+    )
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size,
+                                               param_shapes,
+                                               fp32_flat_groups,
+                                               buffers):
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    state_dict = OrderedDict()
+
+    # buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"{total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0,
+                                             offset,
+                                             partitioned_numel)
+                  for i in range(world_size)),
+            0).narrow(0,
+                      0,
+                      unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(
+            f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(
+        f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements"
+    )
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "checkpoint_dir",
+        type=str,
+        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help=
+        "path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)"
+    )
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file)

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "togethercomputer/RedPajama-INCITE-Base-3B-v1",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 50432
+}

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-4cfkymcd/sandbox/local_flytekit/ac62304dcd93efb7f70889060117e3fe/00000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067772915d011157436dc1ea88cb38756555e25be2d07616d1ee97dfac6e6535
+size 133886409

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-4q2w_rwy/sandbox/local_flytekit/dbd2ca746875e688d31715058d2c6053/00000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067772915d011157436dc1ea88cb38756555e25be2d07616d1ee97dfac6e6535
+size 133886409

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-82nqk4w0/sandbox/local_flytekit/49514a1872a4bad4a98a17419b9144b1/00000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067772915d011157436dc1ea88cb38756555e25be2d07616d1ee97dfac6e6535
+size 133886409

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-ekw5z4k8/sandbox/local_flytekit/6c65d7cd91fd6e22f9363cf6f418c644/00000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067772915d011157436dc1ea88cb38756555e25be2d07616d1ee97dfac6e6535
+size 133886409

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-hazc2d7f/sandbox/local_flytekit/034ef16fc317187112251f7824655542/00000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067772915d011157436dc1ea88cb38756555e25be2d07616d1ee97dfac6e6535
+size 133886409

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-le2pt09a/sandbox/local_flytekit/1cc32a933cca0e6c5306e62a23a36936/00000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067772915d011157436dc1ea88cb38756555e25be2d07616d1ee97dfac6e6535
+size 133886409

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-nony34p2/sandbox/local_flytekit/inputs.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a8cff16d96a34c1446a07a556b1b5547323c7d14551dc26106ea2752acdb6a7
+size 1839

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-tz8lbfds/sandbox/local_flytekit/202b258b898f9254dc79ceac1de43c88/00000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067772915d011157436dc1ea88cb38756555e25be2d07616d1ee97dfac6e6535
+size 133886409

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte-uar2souv/sandbox/local_flytekit/cc50b53b143467dd7cd9fc1ef31d8024/00000

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067772915d011157436dc1ea88cb38756555e25be2d07616d1ee97dfac6e6535
+size 133886409

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/flyte_training_config.json

@@ -0,0 +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": ""}

flytei5n1f0xr/local_flytekit/12359fa3e845f047743a0b5c420028f3/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.29.2"
+}