Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-Next-80B-A3B-Thinking
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen3-Next-80B-A3B-Thinking
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

adapter_config.json

@@ -0,0 +1,47 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-Next-80B-A3B-Thinking",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "shared_expert_gate",
+    "linear_attn.in_proj_qkvz",
+    "shared_expert.gate_proj",
+    "shared_expert.down_proj",
+    "o_proj",
+    "shared_expert.up_proj",
+    "linear_attn.in_proj_ba",
+    "k_proj",
+    "linear_attn.out_proj",
+    "v_proj",
+    "mlp.gate"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a20b6ab68a405fef7856f5b1e2890ce481f8475b508a1134ed13fda97d5dd8ef
+size 106429272

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n<think>\n' }}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddda833950388a06484c359715f38c8ba18f1e29bc495fd81bea18eb7cceb147
+size 55092381

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ad5156cb5ab55f8cd0ece74445bd91b51e4b70f18b043a45705f36ab0130d4
+size 15429

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fec8319af6b2d6a743854f6c5ca2fa58a4eca9142a778df742e377e0ff94303
+size 15429

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:472a0c27c9c4a1ff02f8d7e105c3c3b7448fe82c11d32db353e38ee4846df0ef
+size 15429

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90778dcc377d95e6a4ed8f6f74550df1165f14dbd78b3643a5900648026d353d
+size 15429

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:253623eb1c82cfe00d3e3cb586d78e339aadb91eb510a90f07642ff3a74a6516
+size 1465

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1277 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.972972972972973,
+  "eval_steps": 55,
+  "global_step": 110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 6.015130996704102,
+      "eval_runtime": 175.115,
+      "eval_samples_per_second": 0.571,
+      "eval_steps_per_second": 0.074,
+      "memory/device_reserved (GiB)": 57.3,
+      "memory/max_active (GiB)": 43.52,
+      "memory/max_allocated (GiB)": 43.52,
+      "step": 0
+    },
+    {
+      "epoch": 0.018018018018018018,
+      "grad_norm": 0.601690411567688,
+      "learning_rate": 0.0,
+      "loss": 5.8902,
+      "memory/device_reserved (GiB)": 57.78,
+      "memory/max_active (GiB)": 52.56,
+      "memory/max_allocated (GiB)": 52.56,
+      "step": 1,
+      "tokens_per_second_per_gpu": 177.27
+    },
+    {
+      "epoch": 0.036036036036036036,
+      "grad_norm": 0.5987619161605835,
+      "learning_rate": 1.818181818181818e-06,
+      "loss": 5.9238,
+      "memory/device_reserved (GiB)": 57.83,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 2,
+      "tokens_per_second_per_gpu": 32.34
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 0.6140171885490417,
+      "learning_rate": 3.636363636363636e-06,
+      "loss": 6.108,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 3,
+      "tokens_per_second_per_gpu": 32.29
+    },
+    {
+      "epoch": 0.07207207207207207,
+      "grad_norm": 0.6393939256668091,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 6.0509,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 4,
+      "tokens_per_second_per_gpu": 34.19
+    },
+    {
+      "epoch": 0.09009009009009009,
+      "grad_norm": 0.6186049580574036,
+      "learning_rate": 7.272727272727272e-06,
+      "loss": 6.0799,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 5,
+      "tokens_per_second_per_gpu": 48.39
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 0.6133891344070435,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 6.0418,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 6,
+      "tokens_per_second_per_gpu": 35.74
+    },
+    {
+      "epoch": 0.12612612612612611,
+      "grad_norm": 0.6060707569122314,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 5.9976,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 7,
+      "tokens_per_second_per_gpu": 42.46
+    },
+    {
+      "epoch": 0.14414414414414414,
+      "grad_norm": 0.6184359192848206,
+      "learning_rate": 1.2727272727272727e-05,
+      "loss": 6.0328,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 8,
+      "tokens_per_second_per_gpu": 38.38
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 0.6444172859191895,
+      "learning_rate": 1.4545454545454545e-05,
+      "loss": 5.9618,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 9,
+      "tokens_per_second_per_gpu": 26.99
+    },
+    {
+      "epoch": 0.18018018018018017,
+      "grad_norm": 0.6325266361236572,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 6.1674,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 10,
+      "tokens_per_second_per_gpu": 29.93
+    },
+    {
+      "epoch": 0.1981981981981982,
+      "grad_norm": 0.6881551146507263,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 5.9809,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 11,
+      "tokens_per_second_per_gpu": 33.12
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.6200075745582581,
+      "learning_rate": 2e-05,
+      "loss": 5.9737,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 12,
+      "tokens_per_second_per_gpu": 33.23
+    },
+    {
+      "epoch": 0.23423423423423423,
+      "grad_norm": 0.6758139133453369,
+      "learning_rate": 2.1818181818181818e-05,
+      "loss": 5.9377,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 13,
+      "tokens_per_second_per_gpu": 31.95
+    },
+    {
+      "epoch": 0.25225225225225223,
+      "grad_norm": 0.6687948107719421,
+      "learning_rate": 2.3636363636363637e-05,
+      "loss": 6.0492,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 14,
+      "tokens_per_second_per_gpu": 31.88
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.6872105002403259,
+      "learning_rate": 2.5454545454545454e-05,
+      "loss": 6.1111,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 15,
+      "tokens_per_second_per_gpu": 40.32
+    },
+    {
+      "epoch": 0.2882882882882883,
+      "grad_norm": 0.7107413411140442,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 5.9434,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 16,
+      "tokens_per_second_per_gpu": 31.11
+    },
+    {
+      "epoch": 0.3063063063063063,
+      "grad_norm": 0.7199774384498596,
+      "learning_rate": 2.909090909090909e-05,
+      "loss": 6.0871,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 17,
+      "tokens_per_second_per_gpu": 40.84
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 0.7394067049026489,
+      "learning_rate": 3.090909090909091e-05,
+      "loss": 5.8008,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 18,
+      "tokens_per_second_per_gpu": 52.0
+    },
+    {
+      "epoch": 0.34234234234234234,
+      "grad_norm": 0.7493309378623962,
+      "learning_rate": 3.272727272727273e-05,
+      "loss": 5.8617,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 19,
+      "tokens_per_second_per_gpu": 35.37
+    },
+    {
+      "epoch": 0.36036036036036034,
+      "grad_norm": 0.7457339763641357,
+      "learning_rate": 3.454545454545455e-05,
+      "loss": 5.7479,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 20,
+      "tokens_per_second_per_gpu": 35.34
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 0.7670865058898926,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 5.7939,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 21,
+      "tokens_per_second_per_gpu": 37.74
+    },
+    {
+      "epoch": 0.3963963963963964,
+      "grad_norm": 0.7689312100410461,
+      "learning_rate": 3.818181818181819e-05,
+      "loss": 5.7546,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 22,
+      "tokens_per_second_per_gpu": 34.11
+    },
+    {
+      "epoch": 0.4144144144144144,
+      "grad_norm": 0.7929359674453735,
+      "learning_rate": 4e-05,
+      "loss": 5.8247,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 23,
+      "tokens_per_second_per_gpu": 22.92
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 0.7598868012428284,
+      "learning_rate": 4.181818181818182e-05,
+      "loss": 5.6557,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 24,
+      "tokens_per_second_per_gpu": 29.09
+    },
+    {
+      "epoch": 0.45045045045045046,
+      "grad_norm": 0.7897383570671082,
+      "learning_rate": 4.3636363636363636e-05,
+      "loss": 5.6503,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 25,
+      "tokens_per_second_per_gpu": 43.23
+    },
+    {
+      "epoch": 0.46846846846846846,
+      "grad_norm": 0.8077855706214905,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 5.7059,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 26,
+      "tokens_per_second_per_gpu": 38.97
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 0.7965295910835266,
+      "learning_rate": 4.7272727272727275e-05,
+      "loss": 5.5299,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 27,
+      "tokens_per_second_per_gpu": 29.02
+    },
+    {
+      "epoch": 0.5045045045045045,
+      "grad_norm": 0.7723223567008972,
+      "learning_rate": 4.909090909090909e-05,
+      "loss": 5.442,
+      "memory/device_reserved (GiB)": 57.85,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 28,
+      "tokens_per_second_per_gpu": 25.82
+    },
+    {
+      "epoch": 0.5225225225225225,
+      "grad_norm": 0.7679380178451538,
+      "learning_rate": 5.090909090909091e-05,
+      "loss": 5.3683,
+      "memory/device_reserved (GiB)": 57.86,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 29,
+      "tokens_per_second_per_gpu": 36.19
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.7431294322013855,
+      "learning_rate": 5.272727272727272e-05,
+      "loss": 5.2314,
+      "memory/device_reserved (GiB)": 57.86,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 30,
+      "tokens_per_second_per_gpu": 48.12
+    },
+    {
+      "epoch": 0.5585585585585585,
+      "grad_norm": 0.7318829298019409,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 5.2971,
+      "memory/device_reserved (GiB)": 57.86,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 31,
+      "tokens_per_second_per_gpu": 30.47
+    },
+    {
+      "epoch": 0.5765765765765766,
+      "grad_norm": 0.6973780393600464,
+      "learning_rate": 5.636363636363636e-05,
+      "loss": 5.0413,
+      "memory/device_reserved (GiB)": 57.86,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 32,
+      "tokens_per_second_per_gpu": 39.86
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 0.7133749127388,
+      "learning_rate": 5.818181818181818e-05,
+      "loss": 5.1071,
+      "memory/device_reserved (GiB)": 57.86,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 33,
+      "tokens_per_second_per_gpu": 23.77
+    },
+    {
+      "epoch": 0.6126126126126126,
+      "grad_norm": 0.6688926219940186,
+      "learning_rate": 6e-05,
+      "loss": 4.906,
+      "memory/device_reserved (GiB)": 57.86,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 34,
+      "tokens_per_second_per_gpu": 24.91
+    },
+    {
+      "epoch": 0.6306306306306306,
+      "grad_norm": 0.6534309983253479,
+      "learning_rate": 6.181818181818182e-05,
+      "loss": 4.9764,
+      "memory/device_reserved (GiB)": 57.88,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 35,
+      "tokens_per_second_per_gpu": 33.75
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 0.6284618377685547,
+      "learning_rate": 6.363636363636364e-05,
+      "loss": 4.8235,
+      "memory/device_reserved (GiB)": 57.91,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 36,
+      "tokens_per_second_per_gpu": 32.66
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5952987670898438,
+      "learning_rate": 6.545454545454546e-05,
+      "loss": 4.7779,
+      "memory/device_reserved (GiB)": 57.91,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 37,
+      "tokens_per_second_per_gpu": 28.28
+    },
+    {
+      "epoch": 0.6846846846846847,
+      "grad_norm": 0.6216407418251038,
+      "learning_rate": 6.727272727272727e-05,
+      "loss": 4.7969,
+      "memory/device_reserved (GiB)": 57.94,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 38,
+      "tokens_per_second_per_gpu": 30.94
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 0.5679822564125061,
+      "learning_rate": 6.90909090909091e-05,
+      "loss": 4.7705,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 39,
+      "tokens_per_second_per_gpu": 39.6
+    },
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 0.5590559244155884,
+      "learning_rate": 7.090909090909092e-05,
+      "loss": 4.7452,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 40,
+      "tokens_per_second_per_gpu": 37.24
+    },
+    {
+      "epoch": 0.7387387387387387,
+      "grad_norm": 0.5368968844413757,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 4.7783,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 41,
+      "tokens_per_second_per_gpu": 28.42
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 0.5522942543029785,
+      "learning_rate": 7.454545454545455e-05,
+      "loss": 4.7181,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 42,
+      "tokens_per_second_per_gpu": 32.13
+    },
+    {
+      "epoch": 0.7747747747747747,
+      "grad_norm": 0.4933941066265106,
+      "learning_rate": 7.636363636363637e-05,
+      "loss": 4.8171,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 43,
+      "tokens_per_second_per_gpu": 24.91
+    },
+    {
+      "epoch": 0.7927927927927928,
+      "grad_norm": 0.487724244594574,
+      "learning_rate": 7.818181818181818e-05,
+      "loss": 4.5267,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 44,
+      "tokens_per_second_per_gpu": 38.94
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.484387069940567,
+      "learning_rate": 8e-05,
+      "loss": 4.4651,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 45,
+      "tokens_per_second_per_gpu": 28.12
+    },
+    {
+      "epoch": 0.8288288288288288,
+      "grad_norm": 0.47269508242607117,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 4.4782,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 46,
+      "tokens_per_second_per_gpu": 37.47
+    },
+    {
+      "epoch": 0.8468468468468469,
+      "grad_norm": 0.4501938819885254,
+      "learning_rate": 8.363636363636364e-05,
+      "loss": 4.2217,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 47,
+      "tokens_per_second_per_gpu": 36.52
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.4240598678588867,
+      "learning_rate": 8.545454545454545e-05,
+      "loss": 4.2584,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 48,
+      "tokens_per_second_per_gpu": 25.0
+    },
+    {
+      "epoch": 0.8828828828828829,
+      "grad_norm": 0.4062960743904114,
+      "learning_rate": 8.727272727272727e-05,
+      "loss": 4.3664,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.66,
+      "memory/max_allocated (GiB)": 52.66,
+      "step": 49,
+      "tokens_per_second_per_gpu": 34.05
+    },
+    {
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.4040940999984741,
+      "learning_rate": 8.90909090909091e-05,
+      "loss": 4.31,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 50,
+      "tokens_per_second_per_gpu": 31.81
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 0.38634198904037476,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 4.1829,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 51,
+      "tokens_per_second_per_gpu": 31.96
+    },
+    {
+      "epoch": 0.9369369369369369,
+      "grad_norm": 0.4119090139865875,
+      "learning_rate": 9.272727272727273e-05,
+      "loss": 4.211,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 52,
+      "tokens_per_second_per_gpu": 26.32
+    },
+    {
+      "epoch": 0.954954954954955,
+      "grad_norm": 0.39360716938972473,
+      "learning_rate": 9.454545454545455e-05,
+      "loss": 4.1027,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 53,
+      "tokens_per_second_per_gpu": 36.47
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 0.358804851770401,
+      "learning_rate": 9.636363636363637e-05,
+      "loss": 4.1262,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 54,
+      "tokens_per_second_per_gpu": 35.0
+    },
+    {
+      "epoch": 0.990990990990991,
+      "grad_norm": 0.3619638681411743,
+      "learning_rate": 9.818181818181818e-05,
+      "loss": 3.9671,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 55,
+      "tokens_per_second_per_gpu": 21.34
+    },
+    {
+      "epoch": 0.990990990990991,
+      "eval_loss": 4.040650367736816,
+      "eval_runtime": 179.0976,
+      "eval_samples_per_second": 0.558,
+      "eval_steps_per_second": 0.073,
+      "memory/device_reserved (GiB)": 57.95,
+      "memory/max_active (GiB)": 43.5,
+      "memory/max_allocated (GiB)": 43.5,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3906014859676361,
+      "learning_rate": 0.0001,
+      "loss": 4.1367,
+      "memory/device_reserved (GiB)": 57.88,
+      "memory/max_active (GiB)": 52.55,
+      "memory/max_allocated (GiB)": 52.55,
+      "step": 56,
+      "tokens_per_second_per_gpu": 28.38
+    },
+    {
+      "epoch": 1.018018018018018,
+      "grad_norm": 0.34430640935897827,
+      "learning_rate": 0.00010181818181818181,
+      "loss": 3.9357,
+      "memory/device_reserved (GiB)": 57.91,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 57,
+      "tokens_per_second_per_gpu": 26.74
+    },
+    {
+      "epoch": 1.0360360360360361,
+      "grad_norm": 0.348283588886261,
+      "learning_rate": 0.00010363636363636364,
+      "loss": 3.9594,
+      "memory/device_reserved (GiB)": 57.91,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 58,
+      "tokens_per_second_per_gpu": 25.8
+    },
+    {
+      "epoch": 1.054054054054054,
+      "grad_norm": 0.3484898507595062,
+      "learning_rate": 0.00010545454545454545,
+      "loss": 4.0163,
+      "memory/device_reserved (GiB)": 57.91,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 59,
+      "tokens_per_second_per_gpu": 26.23
+    },
+    {
+      "epoch": 1.072072072072072,
+      "grad_norm": 0.3627394735813141,
+      "learning_rate": 0.00010727272727272728,
+      "loss": 3.9347,
+      "memory/device_reserved (GiB)": 57.91,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 60,
+      "tokens_per_second_per_gpu": 32.7
+    },
+    {
+      "epoch": 1.09009009009009,
+      "grad_norm": 0.3439123034477234,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 3.9091,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.64,
+      "memory/max_allocated (GiB)": 52.64,
+      "step": 61,
+      "tokens_per_second_per_gpu": 46.09
+    },
+    {
+      "epoch": 1.1081081081081081,
+      "grad_norm": 0.34011831879615784,
+      "learning_rate": 0.00011090909090909092,
+      "loss": 3.8579,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 62,
+      "tokens_per_second_per_gpu": 34.82
+    },
+    {
+      "epoch": 1.1261261261261262,
+      "grad_norm": 0.3363277018070221,
+      "learning_rate": 0.00011272727272727272,
+      "loss": 3.8762,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 63,
+      "tokens_per_second_per_gpu": 41.68
+    },
+    {
+      "epoch": 1.1441441441441442,
+      "grad_norm": 0.30976247787475586,
+      "learning_rate": 0.00011454545454545456,
+      "loss": 3.8585,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.63,
+      "memory/max_allocated (GiB)": 52.63,
+      "step": 64,
+      "tokens_per_second_per_gpu": 37.27
+    },
+    {
+      "epoch": 1.1621621621621623,
+      "grad_norm": 0.3248283565044403,
+      "learning_rate": 0.00011636363636363636,
+      "loss": 3.7179,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 65,
+      "tokens_per_second_per_gpu": 26.17
+    },
+    {
+      "epoch": 1.1801801801801801,
+      "grad_norm": 0.3173442482948303,
+      "learning_rate": 0.0001181818181818182,
+      "loss": 3.8197,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 66,
+      "tokens_per_second_per_gpu": 28.41
+    },
+    {
+      "epoch": 1.1981981981981982,
+      "grad_norm": 0.33076199889183044,
+      "learning_rate": 0.00012,
+      "loss": 3.6631,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 67,
+      "tokens_per_second_per_gpu": 32.3
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.32531851530075073,
+      "learning_rate": 0.00012181818181818183,
+      "loss": 3.6563,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 68,
+      "tokens_per_second_per_gpu": 32.11
+    },
+    {
+      "epoch": 1.2342342342342343,
+      "grad_norm": 0.295604944229126,
+      "learning_rate": 0.00012363636363636364,
+      "loss": 3.6487,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 69,
+      "tokens_per_second_per_gpu": 31.08
+    },
+    {
+      "epoch": 1.2522522522522523,
+      "grad_norm": 0.3253607749938965,
+      "learning_rate": 0.00012545454545454546,
+      "loss": 3.741,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 70,
+      "tokens_per_second_per_gpu": 29.52
+    },
+    {
+      "epoch": 1.2702702702702702,
+      "grad_norm": 0.28945258259773254,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 3.6727,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 71,
+      "tokens_per_second_per_gpu": 38.43
+    },
+    {
+      "epoch": 1.2882882882882882,
+      "grad_norm": 0.287298321723938,
+      "learning_rate": 0.0001290909090909091,
+      "loss": 3.5821,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 72,
+      "tokens_per_second_per_gpu": 29.55
+    },
+    {
+      "epoch": 1.3063063063063063,
+      "grad_norm": 0.26835423707962036,
+      "learning_rate": 0.00013090909090909093,
+      "loss": 3.648,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 73,
+      "tokens_per_second_per_gpu": 37.82
+    },
+    {
+      "epoch": 1.3243243243243243,
+      "grad_norm": 0.27674639225006104,
+      "learning_rate": 0.00013272727272727275,
+      "loss": 3.4623,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 74,
+      "tokens_per_second_per_gpu": 48.99
+    },
+    {
+      "epoch": 1.3423423423423424,
+      "grad_norm": 0.28284698724746704,
+      "learning_rate": 0.00013454545454545455,
+      "loss": 3.4366,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 75,
+      "tokens_per_second_per_gpu": 32.8
+    },
+    {
+      "epoch": 1.3603603603603602,
+      "grad_norm": 0.2780005931854248,
+      "learning_rate": 0.00013636363636363637,
+      "loss": 3.4308,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 76,
+      "tokens_per_second_per_gpu": 33.52
+    },
+    {
+      "epoch": 1.3783783783783785,
+      "grad_norm": 0.2978385388851166,
+      "learning_rate": 0.0001381818181818182,
+      "loss": 3.4822,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 77,
+      "tokens_per_second_per_gpu": 35.74
+    },
+    {
+      "epoch": 1.3963963963963963,
+      "grad_norm": 0.28048908710479736,
+      "learning_rate": 0.00014,
+      "loss": 3.4922,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.62,
+      "memory/max_allocated (GiB)": 52.62,
+      "step": 78,
+      "tokens_per_second_per_gpu": 32.76
+    },
+    {
+      "epoch": 1.4144144144144144,
+      "grad_norm": 0.2921410799026489,
+      "learning_rate": 0.00014181818181818184,
+      "loss": 3.5634,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 79,
+      "tokens_per_second_per_gpu": 22.05
+    },
+    {
+      "epoch": 1.4324324324324325,
+      "grad_norm": 0.28046825528144836,
+      "learning_rate": 0.00014363636363636363,
+      "loss": 3.4562,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 80,
+      "tokens_per_second_per_gpu": 27.93
+    },
+    {
+      "epoch": 1.4504504504504505,
+      "grad_norm": 0.28950053453445435,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 3.4771,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 81,
+      "tokens_per_second_per_gpu": 43.19
+    },
+    {
+      "epoch": 1.4684684684684686,
+      "grad_norm": 0.2990242838859558,
+      "learning_rate": 0.00014727272727272728,
+      "loss": 3.4552,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 82,
+      "tokens_per_second_per_gpu": 39.02
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.3110749125480652,
+      "learning_rate": 0.0001490909090909091,
+      "loss": 3.3635,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 83,
+      "tokens_per_second_per_gpu": 28.78
+    },
+    {
+      "epoch": 1.5045045045045045,
+      "grad_norm": 0.2659832537174225,
+      "learning_rate": 0.0001509090909090909,
+      "loss": 3.309,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 84,
+      "tokens_per_second_per_gpu": 26.52
+    },
+    {
+      "epoch": 1.5225225225225225,
+      "grad_norm": 0.2891514003276825,
+      "learning_rate": 0.00015272727272727275,
+      "loss": 3.2953,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 85,
+      "tokens_per_second_per_gpu": 37.61
+    },
+    {
+      "epoch": 1.5405405405405406,
+      "grad_norm": 0.2862309217453003,
+      "learning_rate": 0.00015454545454545454,
+      "loss": 3.3016,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 86,
+      "tokens_per_second_per_gpu": 49.89
+    },
+    {
+      "epoch": 1.5585585585585586,
+      "grad_norm": 0.3269289433956146,
+      "learning_rate": 0.00015636363636363637,
+      "loss": 3.4022,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 87,
+      "tokens_per_second_per_gpu": 30.66
+    },
+    {
+      "epoch": 1.5765765765765765,
+      "grad_norm": 0.2758469581604004,
+      "learning_rate": 0.0001581818181818182,
+      "loss": 3.1596,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 88,
+      "tokens_per_second_per_gpu": 39.43
+    },
+    {
+      "epoch": 1.5945945945945947,
+      "grad_norm": 0.2842893600463867,
+      "learning_rate": 0.00016,
+      "loss": 3.2368,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 89,
+      "tokens_per_second_per_gpu": 23.64
+    },
+    {
+      "epoch": 1.6126126126126126,
+      "grad_norm": 0.27873268723487854,
+      "learning_rate": 0.00016181818181818184,
+      "loss": 3.1778,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 90,
+      "tokens_per_second_per_gpu": 24.52
+    },
+    {
+      "epoch": 1.6306306306306306,
+      "grad_norm": 0.25983887910842896,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 3.2287,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 91,
+      "tokens_per_second_per_gpu": 34.4
+    },
+    {
+      "epoch": 1.6486486486486487,
+      "grad_norm": 0.2840956151485443,
+      "learning_rate": 0.00016545454545454545,
+      "loss": 3.1411,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 92,
+      "tokens_per_second_per_gpu": 33.89
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.2628091275691986,
+      "learning_rate": 0.00016727272727272728,
+      "loss": 3.1159,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 93,
+      "tokens_per_second_per_gpu": 29.27
+    },
+    {
+      "epoch": 1.6846846846846848,
+      "grad_norm": 0.2681942582130432,
+      "learning_rate": 0.0001690909090909091,
+      "loss": 3.1647,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 94,
+      "tokens_per_second_per_gpu": 30.7
+    },
+    {
+      "epoch": 1.7027027027027026,
+      "grad_norm": 0.2515859603881836,
+      "learning_rate": 0.0001709090909090909,
+      "loss": 3.1587,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 95,
+      "tokens_per_second_per_gpu": 40.07
+    },
+    {
+      "epoch": 1.7207207207207207,
+      "grad_norm": 0.2735103666782379,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 3.1537,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 96,
+      "tokens_per_second_per_gpu": 37.91
+    },
+    {
+      "epoch": 1.7387387387387387,
+      "grad_norm": 0.24973994493484497,
+      "learning_rate": 0.00017454545454545454,
+      "loss": 3.2266,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 97,
+      "tokens_per_second_per_gpu": 28.61
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.26508864760398865,
+      "learning_rate": 0.00017636363636363637,
+      "loss": 3.135,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 98,
+      "tokens_per_second_per_gpu": 34.76
+    },
+    {
+      "epoch": 1.7747747747747749,
+      "grad_norm": 0.2922559678554535,
+      "learning_rate": 0.0001781818181818182,
+      "loss": 3.359,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 99,
+      "tokens_per_second_per_gpu": 26.34
+    },
+    {
+      "epoch": 1.7927927927927927,
+      "grad_norm": 0.2632916271686554,
+      "learning_rate": 0.00018,
+      "loss": 3.1131,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 100,
+      "tokens_per_second_per_gpu": 42.17
+    },
+    {
+      "epoch": 1.810810810810811,
+      "grad_norm": 0.2974204123020172,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 3.1127,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 101,
+      "tokens_per_second_per_gpu": 30.71
+    },
+    {
+      "epoch": 1.8288288288288288,
+      "grad_norm": 0.28947019577026367,
+      "learning_rate": 0.00018363636363636366,
+      "loss": 3.1019,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 102,
+      "tokens_per_second_per_gpu": 40.45
+    },
+    {
+      "epoch": 1.8468468468468469,
+      "grad_norm": 0.29779183864593506,
+      "learning_rate": 0.00018545454545454545,
+      "loss": 2.8855,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 103,
+      "tokens_per_second_per_gpu": 38.82
+    },
+    {
+      "epoch": 1.864864864864865,
+      "grad_norm": 0.27393272519111633,
+      "learning_rate": 0.00018727272727272728,
+      "loss": 2.9937,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 104,
+      "tokens_per_second_per_gpu": 26.96
+    },
+    {
+      "epoch": 1.8828828828828827,
+      "grad_norm": 0.28197985887527466,
+      "learning_rate": 0.0001890909090909091,
+      "loss": 3.1189,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 105,
+      "tokens_per_second_per_gpu": 37.87
+    },
+    {
+      "epoch": 1.900900900900901,
+      "grad_norm": 0.27397748827934265,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 3.0858,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.59,
+      "memory/max_allocated (GiB)": 52.59,
+      "step": 106,
+      "tokens_per_second_per_gpu": 35.13
+    },
+    {
+      "epoch": 1.9189189189189189,
+      "grad_norm": 0.274027943611145,
+      "learning_rate": 0.00019272727272727274,
+      "loss": 2.9537,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.59,
+      "memory/max_allocated (GiB)": 52.59,
+      "step": 107,
+      "tokens_per_second_per_gpu": 33.48
+    },
+    {
+      "epoch": 1.936936936936937,
+      "grad_norm": 0.2898459732532501,
+      "learning_rate": 0.00019454545454545457,
+      "loss": 2.9996,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.6,
+      "memory/max_allocated (GiB)": 52.6,
+      "step": 108,
+      "tokens_per_second_per_gpu": 27.65
+    },
+    {
+      "epoch": 1.954954954954955,
+      "grad_norm": 0.2991600036621094,
+      "learning_rate": 0.00019636363636363636,
+      "loss": 2.9123,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 109,
+      "tokens_per_second_per_gpu": 39.01
+    },
+    {
+      "epoch": 1.972972972972973,
+      "grad_norm": 0.27946925163269043,
+      "learning_rate": 0.00019818181818181821,
+      "loss": 3.0439,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 52.61,
+      "memory/max_allocated (GiB)": 52.61,
+      "step": 110,
+      "tokens_per_second_per_gpu": 35.44
+    },
+    {
+      "epoch": 1.972972972972973,
+      "eval_loss": 2.936415672302246,
+      "eval_runtime": 158.8267,
+      "eval_samples_per_second": 0.63,
+      "eval_steps_per_second": 0.082,
+      "memory/device_reserved (GiB)": 57.92,
+      "memory/max_active (GiB)": 43.5,
+      "memory/max_allocated (GiB)": 43.5,
+      "step": 110
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 55,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0902735727406088e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ccf0ff07d5c330083c9eacf2c2e0e307a13dbd2363503c35a015caa695253a
+size 7313