初始化项目，由ModelHub XC社区提供模型

Model: mremila/Llama-3.1-8B-knowledge
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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-411/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: meta-llama/Meta-Llama-3.1-8B
+library_name: transformers
+model_name: Llama-3.1-8B-knowledge
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for Llama-3.1-8B-knowledge
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.29.0+computecanada
+- Transformers: 5.3.0+computecanada
+- Pytorch: 2.10.0+computecanada
+- Datasets: 4.7.0+computecanada
+- Tokenizers: 0.22.2+computecanada
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

chat_template.jinja

@@ -0,0 +1,109 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "26 Jul 2024" %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

checkpoint-411/chat_template.jinja

@@ -0,0 +1,109 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "26 Jul 2024" %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

checkpoint-411/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float32",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-411/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128009,
+    128001
+  ],
+  "pad_token_id": 128009,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.3.0"
+}

checkpoint-411/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15222e81efe711c42e45d6f2f59a270e7c9c416d53102c947231a57a41ecf97e
+size 32121079032

checkpoint-411/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649a26bf24794ce2234efcf319417f473dae311efae1c76c92c687ddbd9ffd16
+size 64242369179

checkpoint-411/pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e3f27c8b1fc26f52b1b617ee993057233c985bb06068c9cc855319473b2ec3
+size 32121192148

checkpoint-411/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659b1cdee2219458dd84ce6a632a595465680b8080e5c44bd600ff97eca8d752
+size 15429

checkpoint-411/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86accf27064cdd503053e90476a6bd10de333d4ff0594535ad55ea13a473c91d
+size 15429

checkpoint-411/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ca8d714ef40be035404c1957b5a4dee84e1f43980408393f8aa710552ee6f6
+size 15429

checkpoint-411/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfdebe99e40accc9c9d8f09c63136a14abda997d9b501969ec8e16e9d183179
+size 15429

checkpoint-411/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1ac65bebf3c1e7e7b379f797abb6738d1fc86d2dd3a9f903cf338d5cbc5406
+size 1465

checkpoint-411/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoint-411/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "TokenizersBackend"
+}

checkpoint-411/trainer_state.json

@@ -0,0 +1,444 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 411,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.396573783457279,
+      "epoch": 0.024384668139907032,
+      "grad_norm": 9.35292911529541,
+      "learning_rate": 3.4615384615384617e-06,
+      "loss": 2.2944561004638673,
+      "mean_token_accuracy": 0.5621824176982045,
+      "num_tokens": 1138906.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.8874999050050973,
+      "epoch": 0.048769336279814064,
+      "grad_norm": 0.24744118750095367,
+      "learning_rate": 4.92462311557789e-06,
+      "loss": 1.7899208068847656,
+      "mean_token_accuracy": 0.628978100977838,
+      "num_tokens": 2293055.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.7037040002644062,
+      "epoch": 0.0731540044197211,
+      "grad_norm": 0.16765649616718292,
+      "learning_rate": 4.7989949748743725e-06,
+      "loss": 1.619252586364746,
+      "mean_token_accuracy": 0.6523888424038887,
+      "num_tokens": 3409941.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.587071031332016,
+      "epoch": 0.09753867255962813,
+      "grad_norm": 0.36697572469711304,
+      "learning_rate": 4.673366834170855e-06,
+      "loss": 1.5249744415283204,
+      "mean_token_accuracy": 0.6715210393071175,
+      "num_tokens": 4532623.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.5395442467182874,
+      "epoch": 0.12192334069953517,
+      "grad_norm": 0.15763863921165466,
+      "learning_rate": 4.547738693467337e-06,
+      "loss": 1.4616802215576172,
+      "mean_token_accuracy": 0.6869728203862906,
+      "num_tokens": 5700954.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.4842158311977982,
+      "epoch": 0.1463080088394422,
+      "grad_norm": 0.05921294912695885,
+      "learning_rate": 4.42211055276382e-06,
+      "loss": 1.3743048667907716,
+      "mean_token_accuracy": 0.7031451839953661,
+      "num_tokens": 6797204.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.4583968281745912,
+      "epoch": 0.17069267697934923,
+      "grad_norm": 0.15839053690433502,
+      "learning_rate": 4.2964824120603016e-06,
+      "loss": 1.364408302307129,
+      "mean_token_accuracy": 0.7028716931119561,
+      "num_tokens": 7935684.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.3737002125009894,
+      "epoch": 0.19507734511925626,
+      "grad_norm": 0.2055569589138031,
+      "learning_rate": 4.170854271356784e-06,
+      "loss": 1.2981891632080078,
+      "mean_token_accuracy": 0.7154177609831095,
+      "num_tokens": 9100164.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.3365630799904467,
+      "epoch": 0.2194620132591633,
+      "grad_norm": 0.08240273594856262,
+      "learning_rate": 4.045226130653266e-06,
+      "loss": 1.2741600036621095,
+      "mean_token_accuracy": 0.7182379385456443,
+      "num_tokens": 10251679.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.287783969938755,
+      "epoch": 0.24384668139907034,
+      "grad_norm": 0.06663907319307327,
+      "learning_rate": 3.919597989949749e-06,
+      "loss": 1.2690627098083496,
+      "mean_token_accuracy": 0.7233840074390173,
+      "num_tokens": 11356051.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.2535302273929119,
+      "epoch": 0.26823134953897737,
+      "grad_norm": 0.11975441128015518,
+      "learning_rate": 3.7939698492462314e-06,
+      "loss": 1.2374841690063476,
+      "mean_token_accuracy": 0.728168161958456,
+      "num_tokens": 12484208.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.2418669171631336,
+      "epoch": 0.2926160176788844,
+      "grad_norm": 0.09109269082546234,
+      "learning_rate": 3.6683417085427137e-06,
+      "loss": 1.2369081497192382,
+      "mean_token_accuracy": 0.7338437670841813,
+      "num_tokens": 13561759.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.213769260980189,
+      "epoch": 0.31700068581879143,
+      "grad_norm": 0.09609343856573105,
+      "learning_rate": 3.542713567839196e-06,
+      "loss": 1.2193414688110351,
+      "mean_token_accuracy": 0.7347961757332087,
+      "num_tokens": 14727153.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.2099591370671987,
+      "epoch": 0.34138535395869846,
+      "grad_norm": 0.045514918863773346,
+      "learning_rate": 3.4170854271356786e-06,
+      "loss": 1.2130016326904296,
+      "mean_token_accuracy": 0.7383950665593147,
+      "num_tokens": 15840961.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.187617147155106,
+      "epoch": 0.3657700220986055,
+      "grad_norm": 0.13311414420604706,
+      "learning_rate": 3.291457286432161e-06,
+      "loss": 1.2047300338745117,
+      "mean_token_accuracy": 0.7410888081416488,
+      "num_tokens": 16984769.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.172801567055285,
+      "epoch": 0.3901546902385125,
+      "grad_norm": 0.11037907749414444,
+      "learning_rate": 3.165829145728643e-06,
+      "loss": 1.191337490081787,
+      "mean_token_accuracy": 0.7454195737838745,
+      "num_tokens": 18135300.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.1579898716881871,
+      "epoch": 0.41453935837841954,
+      "grad_norm": 0.11947419494390488,
+      "learning_rate": 3.040201005025126e-06,
+      "loss": 1.1634675025939942,
+      "mean_token_accuracy": 0.749046934582293,
+      "num_tokens": 19277169.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.1670682085677981,
+      "epoch": 0.4389240265183266,
+      "grad_norm": 0.04084308072924614,
+      "learning_rate": 2.914572864321608e-06,
+      "loss": 1.1813165664672851,
+      "mean_token_accuracy": 0.7435223584994674,
+      "num_tokens": 20442936.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.1455160442739725,
+      "epoch": 0.46330869465823366,
+      "grad_norm": 0.08265366405248642,
+      "learning_rate": 2.7889447236180903e-06,
+      "loss": 1.1532262802124023,
+      "mean_token_accuracy": 0.7507004836574197,
+      "num_tokens": 21546055.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.1505778279155492,
+      "epoch": 0.4876933627981407,
+      "grad_norm": 0.04568405821919441,
+      "learning_rate": 2.663316582914573e-06,
+      "loss": 1.1755168914794922,
+      "mean_token_accuracy": 0.744980787485838,
+      "num_tokens": 22707770.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.133826574496925,
+      "epoch": 0.5120780309380477,
+      "grad_norm": 0.07941383123397827,
+      "learning_rate": 2.5376884422110553e-06,
+      "loss": 1.1708141326904298,
+      "mean_token_accuracy": 0.7456702718511223,
+      "num_tokens": 23850765.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.1377525204792618,
+      "epoch": 0.5364626990779547,
+      "grad_norm": 0.0786183699965477,
+      "learning_rate": 2.412060301507538e-06,
+      "loss": 1.1719804763793946,
+      "mean_token_accuracy": 0.7453695390373468,
+      "num_tokens": 24969640.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.0979079050943255,
+      "epoch": 0.5608473672178618,
+      "grad_norm": 0.037526968866586685,
+      "learning_rate": 2.28643216080402e-06,
+      "loss": 1.1441015243530273,
+      "mean_token_accuracy": 0.7491984859108924,
+      "num_tokens": 26118771.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.107094001956284,
+      "epoch": 0.5852320353577688,
+      "grad_norm": 0.03871579468250275,
+      "learning_rate": 2.1608040201005025e-06,
+      "loss": 1.1631497383117675,
+      "mean_token_accuracy": 0.7486034173518419,
+      "num_tokens": 27275023.0,
+      "step": 240
+    },
+    {
+      "entropy": 1.0854291021823883,
+      "epoch": 0.6096167034976758,
+      "grad_norm": 0.04375020042061806,
+      "learning_rate": 2.035175879396985e-06,
+      "loss": 1.1235612869262694,
+      "mean_token_accuracy": 0.7546378022059799,
+      "num_tokens": 28333140.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.0757445141673088,
+      "epoch": 0.6340013716375829,
+      "grad_norm": 0.05372092127799988,
+      "learning_rate": 1.9095477386934674e-06,
+      "loss": 1.1169811248779298,
+      "mean_token_accuracy": 0.7564450742676854,
+      "num_tokens": 29418762.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.0732924519106746,
+      "epoch": 0.6583860397774899,
+      "grad_norm": 0.058155521750450134,
+      "learning_rate": 1.7839195979899499e-06,
+      "loss": 1.1255494117736817,
+      "mean_token_accuracy": 0.7540135690942407,
+      "num_tokens": 30506833.0,
+      "step": 270
+    },
+    {
+      "entropy": 1.0920044222846628,
+      "epoch": 0.6827707079173969,
+      "grad_norm": 0.03951919823884964,
+      "learning_rate": 1.6582914572864323e-06,
+      "loss": 1.1335023880004882,
+      "mean_token_accuracy": 0.7506223158910871,
+      "num_tokens": 31612624.0,
+      "step": 280
+    },
+    {
+      "entropy": 1.0659992009401322,
+      "epoch": 0.7071553760573039,
+      "grad_norm": 0.04476330056786537,
+      "learning_rate": 1.5326633165829146e-06,
+      "loss": 1.1336694717407227,
+      "mean_token_accuracy": 0.7525387002155185,
+      "num_tokens": 32760933.0,
+      "step": 290
+    },
+    {
+      "entropy": 1.052399990335107,
+      "epoch": 0.731540044197211,
+      "grad_norm": 0.039937425404787064,
+      "learning_rate": 1.407035175879397e-06,
+      "loss": 1.109424877166748,
+      "mean_token_accuracy": 0.7570657260715962,
+      "num_tokens": 33900534.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.0555859578773379,
+      "epoch": 0.755924712337118,
+      "grad_norm": 0.05961156636476517,
+      "learning_rate": 1.2814070351758795e-06,
+      "loss": 1.1106980323791504,
+      "mean_token_accuracy": 0.7565701389685273,
+      "num_tokens": 35022809.0,
+      "step": 310
+    },
+    {
+      "entropy": 1.0802918665111065,
+      "epoch": 0.780309380477025,
+      "grad_norm": 0.035128556191921234,
+      "learning_rate": 1.155778894472362e-06,
+      "loss": 1.1406271934509278,
+      "mean_token_accuracy": 0.7501922188326716,
+      "num_tokens": 36188396.0,
+      "step": 320
+    },
+    {
+      "entropy": 1.0649904919788242,
+      "epoch": 0.8046940486169321,
+      "grad_norm": 0.0338631235063076,
+      "learning_rate": 1.0301507537688443e-06,
+      "loss": 1.1402740478515625,
+      "mean_token_accuracy": 0.7498057916760444,
+      "num_tokens": 37320320.0,
+      "step": 330
+    },
+    {
+      "entropy": 1.0344580493867397,
+      "epoch": 0.8290787167568391,
+      "grad_norm": 0.05243472009897232,
+      "learning_rate": 9.045226130653267e-07,
+      "loss": 1.0902214050292969,
+      "mean_token_accuracy": 0.7581806099042296,
+      "num_tokens": 38349591.0,
+      "step": 340
+    },
+    {
+      "entropy": 1.045315737091005,
+      "epoch": 0.8534633848967462,
+      "grad_norm": 0.03376954793930054,
+      "learning_rate": 7.788944723618092e-07,
+      "loss": 1.0944804191589355,
+      "mean_token_accuracy": 0.7578815678134561,
+      "num_tokens": 39480077.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.036611631512642,
+      "epoch": 0.8778480530366533,
+      "grad_norm": 0.04112258553504944,
+      "learning_rate": 6.532663316582916e-07,
+      "loss": 1.089322853088379,
+      "mean_token_accuracy": 0.7601783391088247,
+      "num_tokens": 40567760.0,
+      "step": 360
+    },
+    {
+      "entropy": 1.0330295177176594,
+      "epoch": 0.9022327211765603,
+      "grad_norm": 0.076757051050663,
+      "learning_rate": 5.276381909547739e-07,
+      "loss": 1.0854530334472656,
+      "mean_token_accuracy": 0.759020702727139,
+      "num_tokens": 41667104.0,
+      "step": 370
+    },
+    {
+      "entropy": 1.055363328382373,
+      "epoch": 0.9266173893164673,
+      "grad_norm": 0.059090178459882736,
+      "learning_rate": 4.0201005025125634e-07,
+      "loss": 1.124905490875244,
+      "mean_token_accuracy": 0.7546801719814539,
+      "num_tokens": 42823783.0,
+      "step": 380
+    },
+    {
+      "entropy": 1.0368478525429965,
+      "epoch": 0.9510020574563743,
+      "grad_norm": 0.08474253863096237,
+      "learning_rate": 2.7638190954773876e-07,
+      "loss": 1.1043139457702638,
+      "mean_token_accuracy": 0.7581638781353831,
+      "num_tokens": 43905335.0,
+      "step": 390
+    },
+    {
+      "entropy": 1.0361423827707767,
+      "epoch": 0.9753867255962814,
+      "grad_norm": 0.037209831178188324,
+      "learning_rate": 1.5075376884422112e-07,
+      "loss": 1.1020542144775392,
+      "mean_token_accuracy": 0.7570645421743393,
+      "num_tokens": 45063169.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.0295690370723605,
+      "epoch": 0.9997713937361884,
+      "grad_norm": 0.052957672625780106,
+      "learning_rate": 2.512562814070352e-08,
+      "loss": 1.1035842895507812,
+      "mean_token_accuracy": 0.7561511231586338,
+      "num_tokens": 46179529.0,
+      "step": 410
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 411,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.721169677367378e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-411/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:190956920b8c2b722edbc9d824f8cfedf236eaf6f36fabf7d7902bfd41a7b850
+size 6097

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float32",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128009,
+    128001
+  ],
+  "pad_token_id": 128009,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.3.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d25063b5e5117bee25614fea0101a38afad91e59d3a54e25593f0e60e8ee5f4
+size 32121079032

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:190956920b8c2b722edbc9d824f8cfedf236eaf6f36fabf7d7902bfd41a7b850
+size 6097