Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-19/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: other
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: reasoning-multilingual-R1-Llama-70B-train
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# reasoning-multilingual-R1-Llama-70B-train
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on the reasoning-multilingual-R1-Llama-70B-train dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5690
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.6972        | 0.1053 | 2    | 0.5688          |
+| 0.6915        | 0.2105 | 4    | 0.5684          |
+| 0.7911        | 0.3158 | 6    | 0.5687          |
+| 0.7261        | 0.4211 | 8    | 0.5700          |
+| 0.86          | 0.5263 | 10   | 0.5687          |
+| 0.6903        | 0.6316 | 12   | 0.5691          |
+| 0.5994        | 0.7368 | 14   | 0.5684          |
+| 0.7792        | 0.8421 | 16   | 0.5696          |
+| 0.7023        | 0.9474 | 18   | 0.5689          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0.dev20241113+rocm6.2
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.5690025091171265,
+    "eval_runtime": 0.2986,
+    "eval_samples_per_second": 6.697,
+    "eval_steps_per_second": 3.349,
+    "total_flos": 6341035089199104.0,
+    "train_loss": 0.7060548631768477,
+    "train_runtime": 53.6484,
+    "train_samples_per_second": 2.759,
+    "train_steps_per_second": 0.354
+}

checkpoint-19/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-19/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.46.1"
+}

checkpoint-19/global_step19/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29445bdc364a5997a0a26d1a205320006f0ca40d31a0dd7fb6f59f11fff4ab48
+size 2665637808

checkpoint-19/global_step19/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:790404feebce213825abb1dd5f8bda8fbff5d6fda95a5c0a3b49ffc93005a30c
+size 2665641008

checkpoint-19/global_step19/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:355561e653a80a6f6761bc1d11ed8fc21bae6ff1f13edf70ef09fa78946d1361
+size 2665641072

checkpoint-19/global_step19/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0ebf7a727fd2dc713bc87bdc1b19130172768a4d3059772fcf12a305148f1a
+size 2665641008

checkpoint-19/global_step19/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f530c19c1642c9cffd24b650c221fd79dd9da7bfb496d71cc96ced37ab111fdd
+size 2665640944

checkpoint-19/global_step19/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fef97611dd4ecdf1617f29d2324913f416aed97246a944025582665ecf5113
+size 2665641264

checkpoint-19/global_step19/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9b14d2bcea6264476c79e016b51936f1f813a1d070f85eca1851ce5b4a18bf
+size 2665640816

checkpoint-19/global_step19/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb4b2defe968f0e9db211643d9fe8a24c32b3032470d26373b7039e2d5477a82
+size 2665637936

checkpoint-19/global_step19/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f46360aef548288443c4e361dbf1ef18f039bd56b0d0786136850c55362f264
+size 3554269304

checkpoint-19/latest

@@ -0,0 +1 @@
+global_step19

checkpoint-19/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ec08307e50d95b42fd6402ddccf7fdfa4156c9363a19e6312efd09cebc52b8
+size 3554214752

checkpoint-19/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1165242405b17b3d6a8186ae61b13dcb1faa5a54320bebd74ef8d71b964bf7
+size 15984

checkpoint-19/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562c262916c9997ec644c42fed9655ab28706b74fca20290ca921c4761d6a4b0
+size 15984

checkpoint-19/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d40f8118f513299624ded0a9bcf09778b961635615090409394d4f96f928f6
+size 15984

checkpoint-19/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4391f924238a4cb855c4cbdc6d1a14954f785431c75997d05c7a4ee6615dae7
+size 15984

checkpoint-19/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7b19bb9543a16bf9f4cd96466ac581436f63070f5815f3a7ba57980608994f
+size 15984

checkpoint-19/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97da4a1ede0a3e0f96411cacd5bfdf84d9355198f7aadc9bcb8be41122043f63
+size 15984

checkpoint-19/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544cb6421b975bd5d2b2360a4e666003794e6197ae654d2ad963cd6572a86ede
+size 15984

checkpoint-19/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d6eb32a23f3bef6262bbcb2eda724b2fd6f5e579969aa27c71a5971331722b
+size 15984

checkpoint-19/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8019dcc30845879688d343ea0e3e2f6e1ed3d0f26585ba32e8c8519cee8a0837
+size 1064

checkpoint-19/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-19/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02643f00207dfc5ed248992486bde04314c21dca556bf65ce520690962b8db63
+size 11422965

checkpoint-19/tokenizer_config.json

@@ -0,0 +1,204 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-19/trainer_state.json

@@ -0,0 +1,238 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 2,
+  "global_step": 19,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 11935214993408.0,
+      "learning_rate": 1e-05,
+      "loss": 0.7163,
+      "step": 1
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2096675946496.0,
+      "learning_rate": 9.924038765061042e-06,
+      "loss": 0.6972,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "eval_loss": 0.5687638521194458,
+      "eval_runtime": 0.2981,
+      "eval_samples_per_second": 6.709,
+      "eval_steps_per_second": 3.354,
+      "step": 2
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 7390838128640.0,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.7795,
+      "step": 3
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 3194177454080.0,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.6915,
+      "step": 4
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 0.5684303045272827,
+      "eval_runtime": 0.2966,
+      "eval_samples_per_second": 6.743,
+      "eval_steps_per_second": 3.371,
+      "step": 4
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 131253493760.0,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.6744,
+      "step": 5
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 491539005440.0,
+      "learning_rate": 8.213938048432697e-06,
+      "loss": 0.7911,
+      "step": 6
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "eval_loss": 0.5686608552932739,
+      "eval_runtime": 0.2967,
+      "eval_samples_per_second": 6.742,
+      "eval_steps_per_second": 3.371,
+      "step": 6
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 235763302400.0,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.5594,
+      "step": 7
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 279532568576.0,
+      "learning_rate": 6.710100716628345e-06,
+      "loss": 0.7261,
+      "step": 8
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": 0.5699889063835144,
+      "eval_runtime": 0.2966,
+      "eval_samples_per_second": 6.744,
+      "eval_steps_per_second": 3.372,
+      "step": 8
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 175990996992.0,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.6122,
+      "step": 9
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 10130321047552.0,
+      "learning_rate": 5e-06,
+      "loss": 0.86,
+      "step": 10
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "eval_loss": 0.568690836429596,
+      "eval_runtime": 0.2978,
+      "eval_samples_per_second": 6.715,
+      "eval_steps_per_second": 3.358,
+      "step": 10
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 3898177486848.0,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.7364,
+      "step": 11
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 1318930219008.0,
+      "learning_rate": 3.289899283371657e-06,
+      "loss": 0.6903,
+      "step": 12
+    },
+    {
+      "epoch": 0.631578947368421,
+      "eval_loss": 0.5691469311714172,
+      "eval_runtime": 0.2973,
+      "eval_samples_per_second": 6.728,
+      "eval_steps_per_second": 3.364,
+      "step": 12
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 137136914432.0,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.663,
+      "step": 13
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 1604217339904.0,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 0.5994,
+      "step": 14
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "eval_loss": 0.5684089064598083,
+      "eval_runtime": 0.2979,
+      "eval_samples_per_second": 6.714,
+      "eval_steps_per_second": 3.357,
+      "step": 14
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 73108439040.0,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.7457,
+      "step": 15
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 361255075840.0,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.7792,
+      "step": 16
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 0.5695986747741699,
+      "eval_runtime": 0.2976,
+      "eval_samples_per_second": 6.72,
+      "eval_steps_per_second": 3.36,
+      "step": 16
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 222161354752.0,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.6121,
+      "step": 17
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 4849853267968.0,
+      "learning_rate": 7.59612349389599e-08,
+      "loss": 0.7023,
+      "step": 18
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "eval_loss": 0.5688631534576416,
+      "eval_runtime": 0.298,
+      "eval_samples_per_second": 6.711,
+      "eval_steps_per_second": 3.355,
+      "step": 18
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 994095661056.0,
+      "learning_rate": 0.0,
+      "loss": 0.7789,
+      "step": 19
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 19,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 19,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6341035089199104.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-19/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d85de0559cf61ca94211b430a49a67f680bb75ce8ddeebe275a4f5596c3c43
+size 7160

checkpoint-19/zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+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 tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        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_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.5690025091171265,
+    "eval_runtime": 0.2986,
+    "eval_samples_per_second": 6.697,
+    "eval_steps_per_second": 3.349
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.46.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ec08307e50d95b42fd6402ddccf7fdfa4156c9363a19e6312efd09cebc52b8
+size 3554214752

runs/Feb06_18-31-53_amd-G262-ZO0-00/events.out.tfevents.1738866822.amd-G262-ZO0-00.61747.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fddd4702f5caba5a7931e0e008b7b2db28662512eff9d5fe8e0a909b8a32eb8
+size 12225

runs/Feb06_18-31-53_amd-G262-ZO0-00/events.out.tfevents.1738866881.amd-G262-ZO0-00.61747.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be90771fb0eb93ff8cf8a197c03c3bfed949a8d8b2b37e5bd41c7697d64045d7
+size 354

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02643f00207dfc5ed248992486bde04314c21dca556bf65ce520690962b8db63
+size 11422965

tokenizer_config.json

@@ -0,0 +1,204 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 6341035089199104.0,
+    "train_loss": 0.7060548631768477,
+    "train_runtime": 53.6484,
+    "train_samples_per_second": 2.759,
+    "train_steps_per_second": 0.354
+}

trainer_log.jsonl

@@ -0,0 +1,29 @@
+{"current_steps": 1, "total_steps": 19, "loss": 0.7163, "lr": 1e-05, "epoch": 0.05263157894736842, "percentage": 5.26, "elapsed_time": "0:00:06", "remaining_time": "0:01:53"}
+{"current_steps": 2, "total_steps": 19, "loss": 0.6972, "lr": 9.924038765061042e-06, "epoch": 0.10526315789473684, "percentage": 10.53, "elapsed_time": "0:00:07", "remaining_time": "0:01:05"}
+{"current_steps": 2, "total_steps": 19, "eval_loss": 0.5687638521194458, "epoch": 0.10526315789473684, "percentage": 10.53, "elapsed_time": "0:00:08", "remaining_time": "0:01:08"}
+{"current_steps": 3, "total_steps": 19, "loss": 0.7795, "lr": 9.698463103929542e-06, "epoch": 0.15789473684210525, "percentage": 15.79, "elapsed_time": "0:00:09", "remaining_time": "0:00:50"}
+{"current_steps": 4, "total_steps": 19, "loss": 0.6915, "lr": 9.330127018922195e-06, "epoch": 0.21052631578947367, "percentage": 21.05, "elapsed_time": "0:00:10", "remaining_time": "0:00:41"}
+{"current_steps": 4, "total_steps": 19, "eval_loss": 0.5684303045272827, "epoch": 0.21052631578947367, "percentage": 21.05, "elapsed_time": "0:00:11", "remaining_time": "0:00:42"}
+{"current_steps": 5, "total_steps": 19, "loss": 0.6744, "lr": 8.83022221559489e-06, "epoch": 0.2631578947368421, "percentage": 26.32, "elapsed_time": "0:00:12", "remaining_time": "0:00:35"}
+{"current_steps": 6, "total_steps": 19, "loss": 0.7911, "lr": 8.213938048432697e-06, "epoch": 0.3157894736842105, "percentage": 31.58, "elapsed_time": "0:00:14", "remaining_time": "0:00:30"}
+{"current_steps": 6, "total_steps": 19, "eval_loss": 0.5686608552932739, "epoch": 0.3157894736842105, "percentage": 31.58, "elapsed_time": "0:00:14", "remaining_time": "0:00:31"}
+{"current_steps": 7, "total_steps": 19, "loss": 0.5594, "lr": 7.500000000000001e-06, "epoch": 0.3684210526315789, "percentage": 36.84, "elapsed_time": "0:00:15", "remaining_time": "0:00:27"}
+{"current_steps": 8, "total_steps": 19, "loss": 0.7261, "lr": 6.710100716628345e-06, "epoch": 0.42105263157894735, "percentage": 42.11, "elapsed_time": "0:00:17", "remaining_time": "0:00:23"}
+{"current_steps": 8, "total_steps": 19, "eval_loss": 0.5699889063835144, "epoch": 0.42105263157894735, "percentage": 42.11, "elapsed_time": "0:00:17", "remaining_time": "0:00:24"}
+{"current_steps": 9, "total_steps": 19, "loss": 0.6122, "lr": 5.8682408883346535e-06, "epoch": 0.47368421052631576, "percentage": 47.37, "elapsed_time": "0:00:19", "remaining_time": "0:00:21"}
+{"current_steps": 10, "total_steps": 19, "loss": 0.86, "lr": 5e-06, "epoch": 0.5263157894736842, "percentage": 52.63, "elapsed_time": "0:00:20", "remaining_time": "0:00:18"}
+{"current_steps": 10, "total_steps": 19, "eval_loss": 0.568690836429596, "epoch": 0.5263157894736842, "percentage": 52.63, "elapsed_time": "0:00:20", "remaining_time": "0:00:18"}
+{"current_steps": 11, "total_steps": 19, "loss": 0.7364, "lr": 4.131759111665349e-06, "epoch": 0.5789473684210527, "percentage": 57.89, "elapsed_time": "0:00:22", "remaining_time": "0:00:16"}
+{"current_steps": 12, "total_steps": 19, "loss": 0.6903, "lr": 3.289899283371657e-06, "epoch": 0.631578947368421, "percentage": 63.16, "elapsed_time": "0:00:23", "remaining_time": "0:00:13"}
+{"current_steps": 12, "total_steps": 19, "eval_loss": 0.5691469311714172, "epoch": 0.631578947368421, "percentage": 63.16, "elapsed_time": "0:00:24", "remaining_time": "0:00:14"}
+{"current_steps": 13, "total_steps": 19, "loss": 0.663, "lr": 2.5000000000000015e-06, "epoch": 0.6842105263157895, "percentage": 68.42, "elapsed_time": "0:00:25", "remaining_time": "0:00:11"}
+{"current_steps": 14, "total_steps": 19, "loss": 0.5994, "lr": 1.7860619515673034e-06, "epoch": 0.7368421052631579, "percentage": 73.68, "elapsed_time": "0:00:27", "remaining_time": "0:00:09"}
+{"current_steps": 14, "total_steps": 19, "eval_loss": 0.5684089064598083, "epoch": 0.7368421052631579, "percentage": 73.68, "elapsed_time": "0:00:27", "remaining_time": "0:00:09"}
+{"current_steps": 15, "total_steps": 19, "loss": 0.7457, "lr": 1.1697777844051105e-06, "epoch": 0.7894736842105263, "percentage": 78.95, "elapsed_time": "0:00:28", "remaining_time": "0:00:07"}
+{"current_steps": 16, "total_steps": 19, "loss": 0.7792, "lr": 6.698729810778065e-07, "epoch": 0.8421052631578947, "percentage": 84.21, "elapsed_time": "0:00:30", "remaining_time": "0:00:05"}
+{"current_steps": 16, "total_steps": 19, "eval_loss": 0.5695986747741699, "epoch": 0.8421052631578947, "percentage": 84.21, "elapsed_time": "0:00:30", "remaining_time": "0:00:05"}
+{"current_steps": 17, "total_steps": 19, "loss": 0.6121, "lr": 3.015368960704584e-07, "epoch": 0.8947368421052632, "percentage": 89.47, "elapsed_time": "0:00:31", "remaining_time": "0:00:03"}
+{"current_steps": 18, "total_steps": 19, "loss": 0.7023, "lr": 7.59612349389599e-08, "epoch": 0.9473684210526315, "percentage": 94.74, "elapsed_time": "0:00:33", "remaining_time": "0:00:01"}
+{"current_steps": 18, "total_steps": 19, "eval_loss": 0.5688631534576416, "epoch": 0.9473684210526315, "percentage": 94.74, "elapsed_time": "0:00:33", "remaining_time": "0:00:01"}
+{"current_steps": 19, "total_steps": 19, "loss": 0.7789, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:35", "remaining_time": "0:00:00"}
+{"current_steps": 19, "total_steps": 19, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:51", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,247 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 2,
+  "global_step": 19,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 11935214993408.0,
+      "learning_rate": 1e-05,
+      "loss": 0.7163,
+      "step": 1
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2096675946496.0,
+      "learning_rate": 9.924038765061042e-06,
+      "loss": 0.6972,
+      "step": 2
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "eval_loss": 0.5687638521194458,
+      "eval_runtime": 0.2981,
+      "eval_samples_per_second": 6.709,
+      "eval_steps_per_second": 3.354,
+      "step": 2
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 7390838128640.0,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.7795,
+      "step": 3
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 3194177454080.0,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.6915,
+      "step": 4
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 0.5684303045272827,
+      "eval_runtime": 0.2966,
+      "eval_samples_per_second": 6.743,
+      "eval_steps_per_second": 3.371,
+      "step": 4
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 131253493760.0,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.6744,
+      "step": 5
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 491539005440.0,
+      "learning_rate": 8.213938048432697e-06,
+      "loss": 0.7911,
+      "step": 6
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "eval_loss": 0.5686608552932739,
+      "eval_runtime": 0.2967,
+      "eval_samples_per_second": 6.742,
+      "eval_steps_per_second": 3.371,
+      "step": 6
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 235763302400.0,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.5594,
+      "step": 7
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 279532568576.0,
+      "learning_rate": 6.710100716628345e-06,
+      "loss": 0.7261,
+      "step": 8
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": 0.5699889063835144,
+      "eval_runtime": 0.2966,
+      "eval_samples_per_second": 6.744,
+      "eval_steps_per_second": 3.372,
+      "step": 8
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 175990996992.0,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.6122,
+      "step": 9
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 10130321047552.0,
+      "learning_rate": 5e-06,
+      "loss": 0.86,
+      "step": 10
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "eval_loss": 0.568690836429596,
+      "eval_runtime": 0.2978,
+      "eval_samples_per_second": 6.715,
+      "eval_steps_per_second": 3.358,
+      "step": 10
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 3898177486848.0,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.7364,
+      "step": 11
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 1318930219008.0,
+      "learning_rate": 3.289899283371657e-06,
+      "loss": 0.6903,
+      "step": 12
+    },
+    {
+      "epoch": 0.631578947368421,
+      "eval_loss": 0.5691469311714172,
+      "eval_runtime": 0.2973,
+      "eval_samples_per_second": 6.728,
+      "eval_steps_per_second": 3.364,
+      "step": 12
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 137136914432.0,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.663,
+      "step": 13
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 1604217339904.0,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 0.5994,
+      "step": 14
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "eval_loss": 0.5684089064598083,
+      "eval_runtime": 0.2979,
+      "eval_samples_per_second": 6.714,
+      "eval_steps_per_second": 3.357,
+      "step": 14
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 73108439040.0,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.7457,
+      "step": 15
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 361255075840.0,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.7792,
+      "step": 16
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 0.5695986747741699,
+      "eval_runtime": 0.2976,
+      "eval_samples_per_second": 6.72,
+      "eval_steps_per_second": 3.36,
+      "step": 16
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 222161354752.0,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.6121,
+      "step": 17
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 4849853267968.0,
+      "learning_rate": 7.59612349389599e-08,
+      "loss": 0.7023,
+      "step": 18
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "eval_loss": 0.5688631534576416,
+      "eval_runtime": 0.298,
+      "eval_samples_per_second": 6.711,
+      "eval_steps_per_second": 3.355,
+      "step": 18
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 994095661056.0,
+      "learning_rate": 0.0,
+      "loss": 0.7789,
+      "step": 19
+    },
+    {
+      "epoch": 1.0,
+      "step": 19,
+      "total_flos": 6341035089199104.0,
+      "train_loss": 0.7060548631768477,
+      "train_runtime": 53.6484,
+      "train_samples_per_second": 2.759,
+      "train_steps_per_second": 0.354
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 19,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 19,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6341035089199104.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d85de0559cf61ca94211b430a49a67f680bb75ce8ddeebe275a4f5596c3c43
+size 7160