Upload folder using huggingface_hub

113_128_e3_3e-5/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

113_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106cd260c39edbdaf0941c1b1dcebac82e7fb6794e41d2dc459ad4a9470508b0
+size 791751704

113_128_e3_3e-5/latest

@@ -0,0 +1 @@
+global_step339

113_128_e3_3e-5/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6f07b327c28b0c12b08300763b57ac30b508ca2daf17d51f32bff755a4e552
+size 16389

113_128_e3_3e-5/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f2c5ca1a49d73f1ac157d30f26fb111367f0d2d32093ab6963f48d2bd43c1b
+size 16389

113_128_e3_3e-5/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44e39c8ecad1f6c1d6823e889fe96883d04bcd1655429b168618d2ea4628b65
+size 16389

113_128_e3_3e-5/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee930c9cd8deff5c3aa486bcd81b92366a1eb0337ad4233fbe7a11ae907be45
+size 16389

113_128_e3_3e-5/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e18f1c48a859c2b08000fca3d72917d91800a0fa043822957701ba0563d18267
+size 16389

113_128_e3_3e-5/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6e1edaefc946d0db6b7dc19d4f3a6103bed852da397fa03262320ef317e22e
+size 16389

113_128_e3_3e-5/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3763441d016b1b92b67f6ec8f2f31437942da0659bdaf03c99735d4cc46bfbb0
+size 16389

113_128_e3_3e-5/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d036d0b96983c7af3c0edf7d70c1c18728d3aab75484a4bd5f34dba648a25cff
+size 16389

113_128_e3_3e-5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e9a84e8bc46693c66d33d58c3c847d3418cc8cb5f3a48c8352a5babd72a221
+size 1401

113_128_e3_3e-5/special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<reponame>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

113_128_e3_3e-5/tokenizer_config.json

@@ -0,0 +1,188 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<reponame>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

113_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,503 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 339,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.9870209097862244,
+      "learning_rate": 7.058823529411765e-06,
+      "loss": 1.4205,
+      "step": 5
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.6665951013565063,
+      "learning_rate": 1.5882352941176473e-05,
+      "loss": 1.3557,
+      "step": 10
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.5841373205184937,
+      "learning_rate": 2.4705882352941174e-05,
+      "loss": 1.2928,
+      "step": 15
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.615104079246521,
+      "learning_rate": 2.9997144412471088e-05,
+      "loss": 1.2613,
+      "step": 20
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.5761383175849915,
+      "learning_rate": 2.9965031537858088e-05,
+      "loss": 1.1522,
+      "step": 25
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.5668302178382874,
+      "learning_rate": 2.9897312963925566e-05,
+      "loss": 1.1196,
+      "step": 30
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.560051441192627,
+      "learning_rate": 2.9794149810760422e-05,
+      "loss": 1.0904,
+      "step": 35
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.6102662086486816,
+      "learning_rate": 2.9655787530315307e-05,
+      "loss": 1.0337,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.6607431769371033,
+      "learning_rate": 2.948255532241464e-05,
+      "loss": 0.9462,
+      "step": 45
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.6369997262954712,
+      "learning_rate": 2.927486535150267e-05,
+      "loss": 0.8745,
+      "step": 50
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.754904568195343,
+      "learning_rate": 2.9033211765997144e-05,
+      "loss": 0.8789,
+      "step": 55
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.6922693252563477,
+      "learning_rate": 2.8758169522581795e-05,
+      "loss": 0.817,
+      "step": 60
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.8895229697227478,
+      "learning_rate": 2.8450393018234975e-05,
+      "loss": 0.7534,
+      "step": 65
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.7855993509292603,
+      "learning_rate": 2.8110614533249145e-05,
+      "loss": 0.6895,
+      "step": 70
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.1190693378448486,
+      "learning_rate": 2.773964248894578e-05,
+      "loss": 0.6758,
+      "step": 75
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.000949501991272,
+      "learning_rate": 2.7338359524230917e-05,
+      "loss": 0.6647,
+      "step": 80
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.9869967103004456,
+      "learning_rate": 2.690772039556782e-05,
+      "loss": 0.6306,
+      "step": 85
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.9438302516937256,
+      "learning_rate": 2.6448749705363208e-05,
+      "loss": 0.5918,
+      "step": 90
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.9366146922111511,
+      "learning_rate": 2.5962539464171864e-05,
+      "loss": 0.5571,
+      "step": 95
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.078191876411438,
+      "learning_rate": 2.54502464925197e-05,
+      "loss": 0.5491,
+      "step": 100
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 1.0569181442260742,
+      "learning_rate": 2.4913089668527073e-05,
+      "loss": 0.4279,
+      "step": 105
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.3981460332870483,
+      "learning_rate": 2.4352347027881003e-05,
+      "loss": 0.4635,
+      "step": 110
+    },
+    {
+      "epoch": 1.0177777777777777,
+      "grad_norm": 1.1050782203674316,
+      "learning_rate": 2.376935272305607e-05,
+      "loss": 0.4038,
+      "step": 115
+    },
+    {
+      "epoch": 1.0622222222222222,
+      "grad_norm": 1.0900036096572876,
+      "learning_rate": 2.3165493849018966e-05,
+      "loss": 0.3738,
+      "step": 120
+    },
+    {
+      "epoch": 1.1066666666666667,
+      "grad_norm": 1.0031921863555908,
+      "learning_rate": 2.2542207142969077e-05,
+      "loss": 0.3053,
+      "step": 125
+    },
+    {
+      "epoch": 1.1511111111111112,
+      "grad_norm": 1.2216390371322632,
+      "learning_rate": 2.1900975565967284e-05,
+      "loss": 0.3187,
+      "step": 130
+    },
+    {
+      "epoch": 1.1955555555555555,
+      "grad_norm": 1.1459314823150635,
+      "learning_rate": 2.124332477458618e-05,
+      "loss": 0.2862,
+      "step": 135
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.3857018947601318,
+      "learning_rate": 2.0570819490976602e-05,
+      "loss": 0.2825,
+      "step": 140
+    },
+    {
+      "epoch": 1.2844444444444445,
+      "grad_norm": 1.3354018926620483,
+      "learning_rate": 1.988505977998695e-05,
+      "loss": 0.2771,
+      "step": 145
+    },
+    {
+      "epoch": 1.3288888888888888,
+      "grad_norm": 1.1405192613601685,
+      "learning_rate": 1.918767724219309e-05,
+      "loss": 0.2677,
+      "step": 150
+    },
+    {
+      "epoch": 1.3733333333333333,
+      "grad_norm": 0.9553251266479492,
+      "learning_rate": 1.848033113189652e-05,
+      "loss": 0.2529,
+      "step": 155
+    },
+    {
+      "epoch": 1.4177777777777778,
+      "grad_norm": 1.4199899435043335,
+      "learning_rate": 1.776470440932719e-05,
+      "loss": 0.2536,
+      "step": 160
+    },
+    {
+      "epoch": 1.462222222222222,
+      "grad_norm": 1.2820732593536377,
+      "learning_rate": 1.70424997364437e-05,
+      "loss": 0.241,
+      "step": 165
+    },
+    {
+      "epoch": 1.5066666666666668,
+      "grad_norm": 1.140531063079834,
+      "learning_rate": 1.6315435425858007e-05,
+      "loss": 0.2016,
+      "step": 170
+    },
+    {
+      "epoch": 1.551111111111111,
+      "grad_norm": 1.2134946584701538,
+      "learning_rate": 1.558524135252315e-05,
+      "loss": 0.1976,
+      "step": 175
+    },
+    {
+      "epoch": 1.5955555555555554,
+      "grad_norm": 0.9495282769203186,
+      "learning_rate": 1.485365483791113e-05,
+      "loss": 0.1918,
+      "step": 180
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 1.1606873273849487,
+      "learning_rate": 1.4122416516473645e-05,
+      "loss": 0.204,
+      "step": 185
+    },
+    {
+      "epoch": 1.6844444444444444,
+      "grad_norm": 0.9224468469619751,
+      "learning_rate": 1.339326619422034e-05,
+      "loss": 0.176,
+      "step": 190
+    },
+    {
+      "epoch": 1.728888888888889,
+      "grad_norm": 1.2094045877456665,
+      "learning_rate": 1.2667938709268134e-05,
+      "loss": 0.1827,
+      "step": 195
+    },
+    {
+      "epoch": 1.7733333333333334,
+      "grad_norm": 0.9437515139579773,
+      "learning_rate": 1.1948159804210497e-05,
+      "loss": 0.1683,
+      "step": 200
+    },
+    {
+      "epoch": 1.8177777777777777,
+      "grad_norm": 1.0713050365447998,
+      "learning_rate": 1.123564202012728e-05,
+      "loss": 0.17,
+      "step": 205
+    },
+    {
+      "epoch": 1.8622222222222222,
+      "grad_norm": 1.2000973224639893,
+      "learning_rate": 1.0532080622004453e-05,
+      "loss": 0.161,
+      "step": 210
+    },
+    {
+      "epoch": 1.9066666666666667,
+      "grad_norm": 1.119629144668579,
+      "learning_rate": 9.839149565258074e-06,
+      "loss": 0.1638,
+      "step": 215
+    },
+    {
+      "epoch": 1.951111111111111,
+      "grad_norm": 1.2566231489181519,
+      "learning_rate": 9.158497512959335e-06,
+      "loss": 0.1274,
+      "step": 220
+    },
+    {
+      "epoch": 1.9955555555555555,
+      "grad_norm": 1.0539401769638062,
+      "learning_rate": 8.491743913236629e-06,
+      "loss": 0.1374,
+      "step": 225
+    },
+    {
+      "epoch": 2.0355555555555553,
+      "grad_norm": 0.9025583863258362,
+      "learning_rate": 7.840475146187582e-06,
+      "loss": 0.1092,
+      "step": 230
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.9942991137504578,
+      "learning_rate": 7.2062407494685e-06,
+      "loss": 0.101,
+      "step": 235
+    },
+    {
+      "epoch": 2.1244444444444444,
+      "grad_norm": 0.854168713092804,
+      "learning_rate": 6.590549731541573e-06,
+      "loss": 0.1029,
+      "step": 240
+    },
+    {
+      "epoch": 2.168888888888889,
+      "grad_norm": 0.8503538370132446,
+      "learning_rate": 5.99486698135159e-06,
+      "loss": 0.0935,
+      "step": 245
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 1.0321223735809326,
+      "learning_rate": 5.4206097829743856e-06,
+      "loss": 0.1061,
+      "step": 250
+    },
+    {
+      "epoch": 2.2577777777777777,
+      "grad_norm": 1.0085475444793701,
+      "learning_rate": 4.869144443529709e-06,
+      "loss": 0.0912,
+      "step": 255
+    },
+    {
+      "epoch": 2.3022222222222224,
+      "grad_norm": 0.7533451318740845,
+      "learning_rate": 4.341783042381501e-06,
+      "loss": 0.0839,
+      "step": 260
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 0.8863906860351562,
+      "learning_rate": 3.839780309360061e-06,
+      "loss": 0.0774,
+      "step": 265
+    },
+    {
+      "epoch": 2.391111111111111,
+      "grad_norm": 0.8447932600975037,
+      "learning_rate": 3.3643306394337016e-06,
+      "loss": 0.0935,
+      "step": 270
+    },
+    {
+      "epoch": 2.4355555555555557,
+      "grad_norm": 0.8222954869270325,
+      "learning_rate": 2.9165652509327206e-06,
+      "loss": 0.0867,
+      "step": 275
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.8490050435066223,
+      "learning_rate": 2.4975494940869687e-06,
+      "loss": 0.0913,
+      "step": 280
+    },
+    {
+      "epoch": 2.5244444444444447,
+      "grad_norm": 0.7602738738059998,
+      "learning_rate": 2.1082803162807986e-06,
+      "loss": 0.086,
+      "step": 285
+    },
+    {
+      "epoch": 2.568888888888889,
+      "grad_norm": 0.7665712237358093,
+      "learning_rate": 1.7496838900561229e-06,
+      "loss": 0.0836,
+      "step": 290
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 0.7276795506477356,
+      "learning_rate": 1.4226134095072586e-06,
+      "loss": 0.0857,
+      "step": 295
+    },
+    {
+      "epoch": 2.6577777777777776,
+      "grad_norm": 0.809053897857666,
+      "learning_rate": 1.127847060310403e-06,
+      "loss": 0.0877,
+      "step": 300
+    },
+    {
+      "epoch": 2.7022222222222223,
+      "grad_norm": 0.6767805814743042,
+      "learning_rate": 8.66086168217694e-07,
+      "loss": 0.0837,
+      "step": 305
+    },
+    {
+      "epoch": 2.7466666666666666,
+      "grad_norm": 0.6591976881027222,
+      "learning_rate": 6.3795353042096e-07,
+      "loss": 0.0848,
+      "step": 310
+    },
+    {
+      "epoch": 2.7911111111111113,
+      "grad_norm": 0.7077962756156921,
+      "learning_rate": 4.4399193375535885e-07,
+      "loss": 0.0798,
+      "step": 315
+    },
+    {
+      "epoch": 2.8355555555555556,
+      "grad_norm": 0.6267828345298767,
+      "learning_rate": 2.8466286326840676e-07,
+      "loss": 0.073,
+      "step": 320
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.6956906318664551,
+      "learning_rate": 1.603454042271324e-07,
+      "loss": 0.0665,
+      "step": 325
+    },
+    {
+      "epoch": 2.924444444444444,
+      "grad_norm": 0.8111679553985596,
+      "learning_rate": 7.133534017569998e-08,
+      "loss": 0.0848,
+      "step": 330
+    },
+    {
+      "epoch": 2.968888888888889,
+      "grad_norm": 0.6904391050338745,
+      "learning_rate": 1.7844449189487466e-08,
+      "loss": 0.0788,
+      "step": 335
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 339,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.424035460217569e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

113_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47eefdbddda40f399c9cb1b35116553e49b33d7825868b80e55a1f2b528691a
+size 8209

113_128_e3_3e-5/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 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
+from dataclasses import dataclass
+
+# 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,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+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_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        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]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    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, exclude_frozen_parameters):
+    """
+    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_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # 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.")
+
+    # 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() if _has_callable(shape, 'numel') else math.prod(shape)
+            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")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    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 _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # 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
+
+    # 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
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # 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"Trainable params: {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 Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    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, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    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("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    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,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)