Upload folder using huggingface_hub

122_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": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

122_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3385d6a060da607ff235de35e9588247c9fb583cacfa36f646c6d721deec323
+size 791751704

122_128_e3_3e-5/latest

@@ -0,0 +1 @@
+global_step357

122_128_e3_3e-5/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b1de4e319e13122564e608b3128952cb98eae0cb9dd40e18601836c28ff820
+size 16389

122_128_e3_3e-5/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5026a8dc3f1f7b3d09e157032c137a683381c2b9dfb98817ffaf10fe96a5e28e
+size 16389

122_128_e3_3e-5/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41bbcf0c1be39385d401d4b0a46d10f3f4600919a2aa6d347b773fc527e0e77f
+size 16389

122_128_e3_3e-5/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f0db48ffa6340715032c0dcdacda182416171311c9577c5674ec72d48aeb26
+size 16389

122_128_e3_3e-5/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5825de59757de8625fbe9205d83984c1cbbfed95c87e7638dccd55a9a345cbb7
+size 16389

122_128_e3_3e-5/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900b08dde96dab4eca88d6191539f432ddcd921b60444c2f5ed2e3699d849826
+size 16389

122_128_e3_3e-5/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1341f2d7c2fc3f513ef2b0bcb02013575a7cd8702af7e1176a14f274a4e845db
+size 16389

122_128_e3_3e-5/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c25bb968e003a7779a054987fc0d280a9aa1830765ff8caac60fa64029b11068
+size 16389

122_128_e3_3e-5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb293785f935a25d5a405238369f2517c19e35a07373dddaaf9e4fb4133693c
+size 1401

122_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
+  }
+}

122_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
+}

122_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,531 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 357,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04201680672268908,
+      "grad_norm": 0.9933851361274719,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.3411,
+      "step": 5
+    },
+    {
+      "epoch": 0.08403361344537816,
+      "grad_norm": 0.8307157754898071,
+      "learning_rate": 1.5e-05,
+      "loss": 1.3388,
+      "step": 10
+    },
+    {
+      "epoch": 0.12605042016806722,
+      "grad_norm": 0.6347477436065674,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 1.2455,
+      "step": 15
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "grad_norm": 0.5502736568450928,
+      "learning_rate": 2.9999355892280363e-05,
+      "loss": 1.2357,
+      "step": 20
+    },
+    {
+      "epoch": 0.21008403361344538,
+      "grad_norm": 0.8497635722160339,
+      "learning_rate": 2.9976817929807542e-05,
+      "loss": 1.1235,
+      "step": 25
+    },
+    {
+      "epoch": 0.25210084033613445,
+      "grad_norm": 0.6049529314041138,
+      "learning_rate": 2.9922129876636385e-05,
+      "loss": 1.1497,
+      "step": 30
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.6350284814834595,
+      "learning_rate": 2.9835409129257777e-05,
+      "loss": 1.0699,
+      "step": 35
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 0.6193023324012756,
+      "learning_rate": 2.9716841847369106e-05,
+      "loss": 1.0079,
+      "step": 40
+    },
+    {
+      "epoch": 0.37815126050420167,
+      "grad_norm": 0.5986446142196655,
+      "learning_rate": 2.956668255425325e-05,
+      "loss": 0.9518,
+      "step": 45
+    },
+    {
+      "epoch": 0.42016806722689076,
+      "grad_norm": 0.6701114773750305,
+      "learning_rate": 2.9385253590404403e-05,
+      "loss": 0.8495,
+      "step": 50
+    },
+    {
+      "epoch": 0.46218487394957986,
+      "grad_norm": 0.6679443717002869,
+      "learning_rate": 2.9172944421573587e-05,
+      "loss": 0.8682,
+      "step": 55
+    },
+    {
+      "epoch": 0.5042016806722689,
+      "grad_norm": 0.8251531720161438,
+      "learning_rate": 2.8930210802719297e-05,
+      "loss": 0.7745,
+      "step": 60
+    },
+    {
+      "epoch": 0.5462184873949579,
+      "grad_norm": 0.8040196299552917,
+      "learning_rate": 2.8657573799657945e-05,
+      "loss": 0.7815,
+      "step": 65
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.860281229019165,
+      "learning_rate": 2.835561867051426e-05,
+      "loss": 0.6993,
+      "step": 70
+    },
+    {
+      "epoch": 0.6302521008403361,
+      "grad_norm": 0.8152778744697571,
+      "learning_rate": 2.8024993609372878e-05,
+      "loss": 0.6996,
+      "step": 75
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 0.905694842338562,
+      "learning_rate": 2.7666408354827985e-05,
+      "loss": 0.6614,
+      "step": 80
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.9018568992614746,
+      "learning_rate": 2.7280632666418013e-05,
+      "loss": 0.596,
+      "step": 85
+    },
+    {
+      "epoch": 0.7563025210084033,
+      "grad_norm": 1.0211740732192993,
+      "learning_rate": 2.6868494672215927e-05,
+      "loss": 0.6054,
+      "step": 90
+    },
+    {
+      "epoch": 0.7983193277310925,
+      "grad_norm": 0.9811335802078247,
+      "learning_rate": 2.643087909112238e-05,
+      "loss": 0.5757,
+      "step": 95
+    },
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 0.9313960075378418,
+      "learning_rate": 2.5968725333677628e-05,
+      "loss": 0.486,
+      "step": 100
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 1.0459967851638794,
+      "learning_rate": 2.5483025485469437e-05,
+      "loss": 0.5013,
+      "step": 105
+    },
+    {
+      "epoch": 0.9243697478991597,
+      "grad_norm": 1.0594935417175293,
+      "learning_rate": 2.4974822177465556e-05,
+      "loss": 0.4798,
+      "step": 110
+    },
+    {
+      "epoch": 0.9663865546218487,
+      "grad_norm": 1.130965232849121,
+      "learning_rate": 2.4445206347842714e-05,
+      "loss": 0.4217,
+      "step": 115
+    },
+    {
+      "epoch": 1.0084033613445378,
+      "grad_norm": 1.2540010213851929,
+      "learning_rate": 2.3895314900116553e-05,
+      "loss": 0.4044,
+      "step": 120
+    },
+    {
+      "epoch": 1.050420168067227,
+      "grad_norm": 1.2571556568145752,
+      "learning_rate": 2.3326328262599784e-05,
+      "loss": 0.3648,
+      "step": 125
+    },
+    {
+      "epoch": 1.092436974789916,
+      "grad_norm": 1.0288017988204956,
+      "learning_rate": 2.2739467854427512e-05,
+      "loss": 0.3434,
+      "step": 130
+    },
+    {
+      "epoch": 1.134453781512605,
+      "grad_norm": 1.0461671352386475,
+      "learning_rate": 2.2135993463589308e-05,
+      "loss": 0.3131,
+      "step": 135
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 1.2845399379730225,
+      "learning_rate": 2.151720054259654e-05,
+      "loss": 0.29,
+      "step": 140
+    },
+    {
+      "epoch": 1.2184873949579833,
+      "grad_norm": 1.1760258674621582,
+      "learning_rate": 2.0884417427590217e-05,
+      "loss": 0.2664,
+      "step": 145
+    },
+    {
+      "epoch": 1.2605042016806722,
+      "grad_norm": 0.9658586382865906,
+      "learning_rate": 2.023900248685892e-05,
+      "loss": 0.2607,
+      "step": 150
+    },
+    {
+      "epoch": 1.3025210084033614,
+      "grad_norm": 1.231645941734314,
+      "learning_rate": 1.9582341204888077e-05,
+      "loss": 0.2561,
+      "step": 155
+    },
+    {
+      "epoch": 1.3445378151260505,
+      "grad_norm": 1.0359504222869873,
+      "learning_rate": 1.8915843208199967e-05,
+      "loss": 0.2388,
+      "step": 160
+    },
+    {
+      "epoch": 1.3865546218487395,
+      "grad_norm": 1.1632640361785889,
+      "learning_rate": 1.824093923936917e-05,
+      "loss": 0.2375,
+      "step": 165
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.8923390507698059,
+      "learning_rate": 1.7559078085709e-05,
+      "loss": 0.2229,
+      "step": 170
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 1.265421986579895,
+      "learning_rate": 1.687172346922213e-05,
+      "loss": 0.2048,
+      "step": 175
+    },
+    {
+      "epoch": 1.5126050420168067,
+      "grad_norm": 0.9728976488113403,
+      "learning_rate": 1.6180350904491537e-05,
+      "loss": 0.2081,
+      "step": 180
+    },
+    {
+      "epoch": 1.5546218487394958,
+      "grad_norm": 1.1996934413909912,
+      "learning_rate": 1.5486444531256813e-05,
+      "loss": 0.1879,
+      "step": 185
+    },
+    {
+      "epoch": 1.596638655462185,
+      "grad_norm": 0.965488612651825,
+      "learning_rate": 1.4791493928475275e-05,
+      "loss": 0.1914,
+      "step": 190
+    },
+    {
+      "epoch": 1.638655462184874,
+      "grad_norm": 1.346483588218689,
+      "learning_rate": 1.4096990916706865e-05,
+      "loss": 0.1785,
+      "step": 195
+    },
+    {
+      "epoch": 1.680672268907563,
+      "grad_norm": 1.236024022102356,
+      "learning_rate": 1.3404426355687167e-05,
+      "loss": 0.1575,
+      "step": 200
+    },
+    {
+      "epoch": 1.7226890756302522,
+      "grad_norm": 0.9271143674850464,
+      "learning_rate": 1.2715286943962925e-05,
+      "loss": 0.1727,
+      "step": 205
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.9287970662117004,
+      "learning_rate": 1.2031052027460272e-05,
+      "loss": 0.15,
+      "step": 210
+    },
+    {
+      "epoch": 1.8067226890756303,
+      "grad_norm": 0.9872588515281677,
+      "learning_rate": 1.1353190423836431e-05,
+      "loss": 0.1531,
+      "step": 215
+    },
+    {
+      "epoch": 1.8487394957983194,
+      "grad_norm": 1.0399729013442993,
+      "learning_rate": 1.0683157269432097e-05,
+      "loss": 0.1474,
+      "step": 220
+    },
+    {
+      "epoch": 1.8907563025210083,
+      "grad_norm": 1.0511770248413086,
+      "learning_rate": 1.0022390895592813e-05,
+      "loss": 0.1504,
+      "step": 225
+    },
+    {
+      "epoch": 1.9327731092436975,
+      "grad_norm": 0.9378284811973572,
+      "learning_rate": 9.37230974106497e-06,
+      "loss": 0.1207,
+      "step": 230
+    },
+    {
+      "epoch": 1.9747899159663866,
+      "grad_norm": 0.980301558971405,
+      "learning_rate": 8.734309307094382e-06,
+      "loss": 0.1294,
+      "step": 235
+    },
+    {
+      "epoch": 2.0168067226890756,
+      "grad_norm": 0.8719095587730408,
+      "learning_rate": 8.109759161763797e-06,
+      "loss": 0.1161,
+      "step": 240
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.877722978591919,
+      "learning_rate": 7.500000000000004e-06,
+      "loss": 0.1026,
+      "step": 245
+    },
+    {
+      "epoch": 2.100840336134454,
+      "grad_norm": 0.813258945941925,
+      "learning_rate": 6.906340765561734e-06,
+      "loss": 0.0796,
+      "step": 250
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.7355106472969055,
+      "learning_rate": 6.330055841186401e-06,
+      "loss": 0.0983,
+      "step": 255
+    },
+    {
+      "epoch": 2.184873949579832,
+      "grad_norm": 1.0861235857009888,
+      "learning_rate": 5.7723823129275e-06,
+      "loss": 0.0918,
+      "step": 260
+    },
+    {
+      "epoch": 2.226890756302521,
+      "grad_norm": 0.93150794506073,
+      "learning_rate": 5.234517314555213e-06,
+      "loss": 0.087,
+      "step": 265
+    },
+    {
+      "epoch": 2.26890756302521,
+      "grad_norm": 0.8490555882453918,
+      "learning_rate": 4.717615457720836e-06,
+      "loss": 0.0908,
+      "step": 270
+    },
+    {
+      "epoch": 2.310924369747899,
+      "grad_norm": 0.828468382358551,
+      "learning_rate": 4.2227863534016355e-06,
+      "loss": 0.0847,
+      "step": 275
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.8411772847175598,
+      "learning_rate": 3.7510922299466818e-06,
+      "loss": 0.0776,
+      "step": 280
+    },
+    {
+      "epoch": 2.3949579831932772,
+      "grad_norm": 0.8613879680633545,
+      "learning_rate": 3.3035456528369785e-06,
+      "loss": 0.0775,
+      "step": 285
+    },
+    {
+      "epoch": 2.4369747899159666,
+      "grad_norm": 0.7724470496177673,
+      "learning_rate": 2.881107351054695e-06,
+      "loss": 0.0879,
+      "step": 290
+    },
+    {
+      "epoch": 2.4789915966386555,
+      "grad_norm": 0.6795789003372192,
+      "learning_rate": 2.4846841547275916e-06,
+      "loss": 0.0808,
+      "step": 295
+    },
+    {
+      "epoch": 2.5210084033613445,
+      "grad_norm": 0.6780486702919006,
+      "learning_rate": 2.1151270484758052e-06,
+      "loss": 0.0855,
+      "step": 300
+    },
+    {
+      "epoch": 2.5630252100840334,
+      "grad_norm": 0.6190922260284424,
+      "learning_rate": 1.7732293446397724e-06,
+      "loss": 0.0664,
+      "step": 305
+    },
+    {
+      "epoch": 2.6050420168067228,
+      "grad_norm": 0.6506485939025879,
+      "learning_rate": 1.459724980310767e-06,
+      "loss": 0.0821,
+      "step": 310
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.7087223529815674,
+      "learning_rate": 1.1752869418197055e-06,
+      "loss": 0.0721,
+      "step": 315
+    },
+    {
+      "epoch": 2.689075630252101,
+      "grad_norm": 0.6863821744918823,
+      "learning_rate": 9.205258200663685e-07,
+      "loss": 0.0734,
+      "step": 320
+    },
+    {
+      "epoch": 2.73109243697479,
+      "grad_norm": 0.6743139624595642,
+      "learning_rate": 6.959884997901705e-07,
+      "loss": 0.0749,
+      "step": 325
+    },
+    {
+      "epoch": 2.773109243697479,
+      "grad_norm": 0.6538113355636597,
+      "learning_rate": 5.021569855962188e-07,
+      "loss": 0.0757,
+      "step": 330
+    },
+    {
+      "epoch": 2.815126050420168,
+      "grad_norm": 0.630624532699585,
+      "learning_rate": 3.394473672567655e-07,
+      "loss": 0.0684,
+      "step": 335
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.6647582650184631,
+      "learning_rate": 2.0820892650920686e-07,
+      "loss": 0.0763,
+      "step": 340
+    },
+    {
+      "epoch": 2.899159663865546,
+      "grad_norm": 0.635470449924469,
+      "learning_rate": 1.0872338726798826e-07,
+      "loss": 0.0697,
+      "step": 345
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.6120880246162415,
+      "learning_rate": 4.120431086000409e-08,
+      "loss": 0.0654,
+      "step": 350
+    },
+    {
+      "epoch": 2.9831932773109244,
+      "grad_norm": 0.8066940307617188,
+      "learning_rate": 5.796637581689246e-09,
+      "loss": 0.0805,
+      "step": 355
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 357,
+  "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": 4.833024612184883e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

122_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03845061412500c4727d9a4d37e6a45ad1ed8fe5625f7cf167ee1a76b3ab563
+size 8209

122_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)