StockEx CH Trader: QLoRA fine-tuned Qwen2.5-7B-Instruct (adapter)

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-423/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,13 @@
 ---
-library_name: transformers
-tags: []
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
 ---
 
 # Model Card for Model ID
@@ -15,7 +22,7 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
 
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +203,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "v_proj",
     "o_proj",
+    "v_proj",
     "up_proj",
+    "k_proj",
     "gate_proj",
     "q_proj",
-    "k_proj"
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6023e97e3bd626492f7eb62f9885ec36dfa78ad032f5f61e977a65deaf826aa
+oid sha256:9617c0bd790e5efa896cfa11500811bcf897ed9a9ff9edf0842d1832b88712c7
 size 161533192

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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' }}
+{%- endif %}

checkpoint-423/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

checkpoint-423/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-423/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6023e97e3bd626492f7eb62f9885ec36dfa78ad032f5f61e977a65deaf826aa
+size 161533192

checkpoint-423/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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' }}
+{%- endif %}

checkpoint-423/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c4040070f5867e591afc163b22285f943975ea412e769a481cb8a13bb2197a
+size 83485139

checkpoint-423/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6454c38a39bdfdf1a11c0572ad919dfdf405e82214c65f15ef25acef9e838ce9
+size 14645

checkpoint-423/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46dbb23a7f7568c49d5fd63ef60f502240d770b6864697d79e1f163063e33e79
+size 1465

checkpoint-423/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-423/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 512,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-423/trainer_state.json

@@ -0,0 +1,916 @@
+{
+  "best_global_step": 420,
+  "best_metric": 0.3298604488372803,
+  "best_model_checkpoint": "./stockex-ch-trader/checkpoint-420",
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 423,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.2963156521320343,
+      "epoch": 0.07104795737122557,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.7593653678894043,
+      "mean_token_accuracy": 0.8261439204216003,
+      "num_tokens": 64549.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.07104795737122557,
+      "eval_entropy": 1.3787318827613952,
+      "eval_loss": 0.4136860966682434,
+      "eval_mean_token_accuracy": 0.8562367170576065,
+      "eval_num_tokens": 64549.0,
+      "eval_runtime": 300.6877,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.21,
+      "step": 10
+    },
+    {
+      "entropy": 1.4298876911401748,
+      "epoch": 0.14209591474245115,
+      "grad_norm": 0.13671875,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 0.3840687990188599,
+      "mean_token_accuracy": 0.8652397453784942,
+      "num_tokens": 129221.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.14209591474245115,
+      "eval_entropy": 1.4505654403141566,
+      "eval_loss": 0.3602067232131958,
+      "eval_mean_token_accuracy": 0.8688105836747184,
+      "eval_num_tokens": 129221.0,
+      "eval_runtime": 300.6696,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.21,
+      "step": 20
+    },
+    {
+      "entropy": 1.4376762628555297,
+      "epoch": 0.21314387211367672,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 0.00019984966218416245,
+      "loss": 0.3509472370147705,
+      "mean_token_accuracy": 0.8688564792275428,
+      "num_tokens": 193940.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.21314387211367672,
+      "eval_entropy": 1.4176286780644978,
+      "eval_loss": 0.3576105833053589,
+      "eval_mean_token_accuracy": 0.8698482201212928,
+      "eval_num_tokens": 193940.0,
+      "eval_runtime": 300.6563,
+      "eval_samples_per_second": 0.832,
+      "eval_steps_per_second": 0.21,
+      "step": 30
+    },
+    {
+      "entropy": 1.4242034316062928,
+      "epoch": 0.2841918294849023,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 0.0001991144016749207,
+      "loss": 0.3552170038223267,
+      "mean_token_accuracy": 0.8700723454356194,
+      "num_tokens": 259229.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.2841918294849023,
+      "eval_entropy": 1.426317640713283,
+      "eval_loss": 0.35458239912986755,
+      "eval_mean_token_accuracy": 0.8706632767404828,
+      "eval_num_tokens": 259229.0,
+      "eval_runtime": 300.6427,
+      "eval_samples_per_second": 0.832,
+      "eval_steps_per_second": 0.21,
+      "step": 40
+    },
+    {
+      "entropy": 1.4179179966449738,
+      "epoch": 0.3552397868561279,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 0.00019777111031006231,
+      "loss": 0.35140392780303953,
+      "mean_token_accuracy": 0.8776277780532837,
+      "num_tokens": 324466.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3552397868561279,
+      "eval_entropy": 1.4232942149752663,
+      "eval_loss": 0.345210462808609,
+      "eval_mean_token_accuracy": 0.8669123583369784,
+      "eval_num_tokens": 324466.0,
+      "eval_runtime": 300.6312,
+      "eval_samples_per_second": 0.832,
+      "eval_steps_per_second": 0.21,
+      "step": 50
+    },
+    {
+      "entropy": 1.4408947974443436,
+      "epoch": 0.42628774422735344,
+      "grad_norm": 0.060546875,
+      "learning_rate": 0.00019582802869422307,
+      "loss": 0.3457732439041138,
+      "mean_token_accuracy": 0.8727102458477021,
+      "num_tokens": 389340.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.42628774422735344,
+      "eval_entropy": 1.4362683882789007,
+      "eval_loss": 0.3460199534893036,
+      "eval_mean_token_accuracy": 0.87255583112202,
+      "eval_num_tokens": 389340.0,
+      "eval_runtime": 300.6626,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.21,
+      "step": 60
+    },
+    {
+      "entropy": 1.4305267930030823,
+      "epoch": 0.49733570159857904,
+      "grad_norm": 0.06884765625,
+      "learning_rate": 0.00019329707692738288,
+      "loss": 0.34513719081878663,
+      "mean_token_accuracy": 0.8745817050337792,
+      "num_tokens": 454284.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.49733570159857904,
+      "eval_entropy": 1.4227766763596308,
+      "eval_loss": 0.3442724645137787,
+      "eval_mean_token_accuracy": 0.8681343954706949,
+      "eval_num_tokens": 454284.0,
+      "eval_runtime": 300.6703,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.21,
+      "step": 70
+    },
+    {
+      "entropy": 1.4214028120040894,
+      "epoch": 0.5683836589698046,
+      "grad_norm": 0.044189453125,
+      "learning_rate": 0.00019019378147938176,
+      "loss": 0.34772319793701173,
+      "mean_token_accuracy": 0.8682249620556831,
+      "num_tokens": 519145.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.5683836589698046,
+      "eval_entropy": 1.4160598156944153,
+      "eval_loss": 0.3454609215259552,
+      "eval_mean_token_accuracy": 0.8694430192311605,
+      "eval_num_tokens": 519145.0,
+      "eval_runtime": 300.6511,
+      "eval_samples_per_second": 0.832,
+      "eval_steps_per_second": 0.21,
+      "step": 80
+    },
+    {
+      "entropy": 1.4053258925676346,
+      "epoch": 0.6394316163410302,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 0.0001865371799406666,
+      "loss": 0.3419625282287598,
+      "mean_token_accuracy": 0.8665244862437248,
+      "num_tokens": 584882.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.6394316163410302,
+      "eval_entropy": 1.4048999642568922,
+      "eval_loss": 0.34549078345298767,
+      "eval_mean_token_accuracy": 0.8717382484012179,
+      "eval_num_tokens": 584882.0,
+      "eval_runtime": 300.6179,
+      "eval_samples_per_second": 0.832,
+      "eval_steps_per_second": 0.21,
+      "step": 90
+    },
+    {
+      "entropy": 1.4104130774736405,
+      "epoch": 0.7104795737122558,
+      "grad_norm": 0.0625,
+      "learning_rate": 0.0001823497042335884,
+      "loss": 0.3392710447311401,
+      "mean_token_accuracy": 0.8716825649142266,
+      "num_tokens": 649766.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.7104795737122558,
+      "eval_entropy": 1.399895053061228,
+      "eval_loss": 0.34557268023490906,
+      "eval_mean_token_accuracy": 0.8675587830089387,
+      "eval_num_tokens": 649766.0,
+      "eval_runtime": 300.6377,
+      "eval_samples_per_second": 0.832,
+      "eval_steps_per_second": 0.21,
+      "step": 100
+    },
+    {
+      "entropy": 1.4029030323028564,
+      "epoch": 0.7815275310834814,
+      "grad_norm": 0.06884765625,
+      "learning_rate": 0.0001776570430007059,
+      "loss": 0.34670975208282473,
+      "mean_token_accuracy": 0.8702039152383805,
+      "num_tokens": 715180.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.7815275310834814,
+      "eval_entropy": 1.4114291081352839,
+      "eval_loss": 0.34050390124320984,
+      "eval_mean_token_accuracy": 0.8724132274824475,
+      "eval_num_tokens": 715180.0,
+      "eval_runtime": 300.6403,
+      "eval_samples_per_second": 0.832,
+      "eval_steps_per_second": 0.21,
+      "step": 110
+    },
+    {
+      "entropy": 1.4146249413490295,
+      "epoch": 0.8525754884547069,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 0.0001724879840142936,
+      "loss": 0.34205806255340576,
+      "mean_token_accuracy": 0.8725002616643905,
+      "num_tokens": 779956.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.8525754884547069,
+      "eval_entropy": 1.4029388465578594,
+      "eval_loss": 0.337764173746109,
+      "eval_mean_token_accuracy": 0.8708018386174762,
+      "eval_num_tokens": 779956.0,
+      "eval_runtime": 300.6454,
+      "eval_samples_per_second": 0.832,
+      "eval_steps_per_second": 0.21,
+      "step": 120
+    },
+    {
+      "entropy": 1.4079937398433686,
+      "epoch": 0.9236234458259325,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 0.0001668742375738149,
+      "loss": 0.3406423330307007,
+      "mean_token_accuracy": 0.8678194597363472,
+      "num_tokens": 844746.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.9236234458259325,
+      "eval_entropy": 1.404384105924576,
+      "eval_loss": 0.3414382338523865,
+      "eval_mean_token_accuracy": 0.8703954522571866,
+      "eval_num_tokens": 844746.0,
+      "eval_runtime": 300.7534,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 130
+    },
+    {
+      "entropy": 1.4128191709518432,
+      "epoch": 0.9946714031971581,
+      "grad_norm": 0.0546875,
+      "learning_rate": 0.00016085024197475196,
+      "loss": 0.3400874137878418,
+      "mean_token_accuracy": 0.8687706053256988,
+      "num_tokens": 909826.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.9946714031971581,
+      "eval_entropy": 1.4133274138919891,
+      "eval_loss": 0.3403981924057007,
+      "eval_mean_token_accuracy": 0.8667604989475675,
+      "eval_num_tokens": 909826.0,
+      "eval_runtime": 300.673,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.21,
+      "step": 140
+    },
+    {
+      "entropy": 1.4142790054663634,
+      "epoch": 1.063943161634103,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00015445295224217107,
+      "loss": 0.33670949935913086,
+      "mean_token_accuracy": 0.8746435443560282,
+      "num_tokens": 972179.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.063943161634103,
+      "eval_entropy": 1.4076765340472024,
+      "eval_loss": 0.3379535377025604,
+      "eval_mean_token_accuracy": 0.873747069684286,
+      "eval_num_tokens": 972179.0,
+      "eval_runtime": 300.6766,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.21,
+      "step": 150
+    },
+    {
+      "entropy": 1.404336929321289,
+      "epoch": 1.1349911190053286,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 0.00014772161342506613,
+      "loss": 0.3300167560577393,
+      "mean_token_accuracy": 0.8760040670633316,
+      "num_tokens": 1037424.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.1349911190053286,
+      "eval_entropy": 1.4067519070610168,
+      "eval_loss": 0.3369215130805969,
+      "eval_mean_token_accuracy": 0.8731053793241107,
+      "eval_num_tokens": 1037424.0,
+      "eval_runtime": 300.7459,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 160
+    },
+    {
+      "entropy": 1.4114000707864762,
+      "epoch": 1.206039076376554,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.0001406975198422368,
+      "loss": 0.33290348052978513,
+      "mean_token_accuracy": 0.8732595324516297,
+      "num_tokens": 1101802.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.206039076376554,
+      "eval_entropy": 1.4023287220606728,
+      "eval_loss": 0.33860695362091064,
+      "eval_mean_token_accuracy": 0.8725330839081417,
+      "eval_num_tokens": 1101802.0,
+      "eval_runtime": 300.743,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 170
+    },
+    {
+      "entropy": 1.405304503440857,
+      "epoch": 1.2770870337477798,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 0.00013342376175664114,
+      "loss": 0.33488993644714354,
+      "mean_token_accuracy": 0.8727252542972564,
+      "num_tokens": 1166893.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.2770870337477798,
+      "eval_entropy": 1.4046104332757374,
+      "eval_loss": 0.3399215638637543,
+      "eval_mean_token_accuracy": 0.8705378837055631,
+      "eval_num_tokens": 1166893.0,
+      "eval_runtime": 300.7542,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 180
+    },
+    {
+      "entropy": 1.4051885157823563,
+      "epoch": 1.3481349911190053,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00012594496103228274,
+      "loss": 0.3381678342819214,
+      "mean_token_accuracy": 0.8746153846383095,
+      "num_tokens": 1232126.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.3481349911190053,
+      "eval_entropy": 1.408092459042867,
+      "eval_loss": 0.33658185601234436,
+      "eval_mean_token_accuracy": 0.8732467946552095,
+      "eval_num_tokens": 1232126.0,
+      "eval_runtime": 300.7565,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 190
+    },
+    {
+      "entropy": 1.4089335173368454,
+      "epoch": 1.419182948490231,
+      "grad_norm": 0.04443359375,
+      "learning_rate": 0.00011830699739528186,
+      "loss": 0.33224356174468994,
+      "mean_token_accuracy": 0.8684082984924316,
+      "num_tokens": 1297007.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.419182948490231,
+      "eval_entropy": 1.4018082372725955,
+      "eval_loss": 0.33901074528694153,
+      "eval_mean_token_accuracy": 0.8686280610069396,
+      "eval_num_tokens": 1297007.0,
+      "eval_runtime": 300.7465,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 200
+    },
+    {
+      "entropy": 1.3996795892715455,
+      "epoch": 1.4902309058614565,
+      "grad_norm": 0.037353515625,
+      "learning_rate": 0.0001105567269784193,
+      "loss": 0.3279148578643799,
+      "mean_token_accuracy": 0.8745489582419396,
+      "num_tokens": 1362371.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.4902309058614565,
+      "eval_entropy": 1.4018028804234095,
+      "eval_loss": 0.3412929177284241,
+      "eval_mean_token_accuracy": 0.8701217420517452,
+      "eval_num_tokens": 1362371.0,
+      "eval_runtime": 300.7302,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 210
+    },
+    {
+      "entropy": 1.4049654960632325,
+      "epoch": 1.561278863232682,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 0.00010274169487578025,
+      "loss": 0.3324852705001831,
+      "mean_token_accuracy": 0.8769623816013337,
+      "num_tokens": 1427085.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.561278863232682,
+      "eval_entropy": 1.4000725386634705,
+      "eval_loss": 0.33717405796051025,
+      "eval_mean_token_accuracy": 0.8721385986085922,
+      "eval_num_tokens": 1427085.0,
+      "eval_runtime": 300.7392,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 220
+    },
+    {
+      "entropy": 1.4034211605787277,
+      "epoch": 1.6323268206039077,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 9.490984347087035e-05,
+      "loss": 0.3351150035858154,
+      "mean_token_accuracy": 0.8740972504019737,
+      "num_tokens": 1491911.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.6323268206039077,
+      "eval_entropy": 1.4025771315135653,
+      "eval_loss": 0.3377071022987366,
+      "eval_mean_token_accuracy": 0.8724007142914666,
+      "eval_num_tokens": 1491911.0,
+      "eval_runtime": 300.7481,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 230
+    },
+    {
+      "entropy": 1.4066081583499908,
+      "epoch": 1.7033747779751334,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 8.710921832750599e-05,
+      "loss": 0.3293110132217407,
+      "mean_token_accuracy": 0.8752981394529342,
+      "num_tokens": 1556614.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.7033747779751334,
+      "eval_entropy": 1.3935221093041557,
+      "eval_loss": 0.33765721321105957,
+      "eval_mean_token_accuracy": 0.8718693719969856,
+      "eval_num_tokens": 1556614.0,
+      "eval_runtime": 300.7184,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 240
+    },
+    {
+      "entropy": 1.3865844041109086,
+      "epoch": 1.7744227353463589,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 7.938767344773037e-05,
+      "loss": 0.3345181465148926,
+      "mean_token_accuracy": 0.8729749575257302,
+      "num_tokens": 1622085.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.7744227353463589,
+      "eval_entropy": 1.389842949216328,
+      "eval_loss": 0.33758464455604553,
+      "eval_mean_token_accuracy": 0.8717279178755624,
+      "eval_num_tokens": 1622085.0,
+      "eval_runtime": 300.7398,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 250
+    },
+    {
+      "entropy": 1.3939575046300887,
+      "epoch": 1.8454706927175843,
+      "grad_norm": 0.0546875,
+      "learning_rate": 7.179257770489181e-05,
+      "loss": 0.324985408782959,
+      "mean_token_accuracy": 0.8755759671330452,
+      "num_tokens": 1686979.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.8454706927175843,
+      "eval_entropy": 1.3957371106223455,
+      "eval_loss": 0.33793696761131287,
+      "eval_mean_token_accuracy": 0.8721340374341087,
+      "eval_num_tokens": 1686979.0,
+      "eval_runtime": 300.7408,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 260
+    },
+    {
+      "entropy": 1.39389927983284,
+      "epoch": 1.9165186500888098,
+      "grad_norm": 0.048583984375,
+      "learning_rate": 6.437052425281023e-05,
+      "loss": 0.33145718574523925,
+      "mean_token_accuracy": 0.8743691191077232,
+      "num_tokens": 1752330.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.9165186500888098,
+      "eval_entropy": 1.390679262933277,
+      "eval_loss": 0.3360918462276459,
+      "eval_mean_token_accuracy": 0.8732259661432297,
+      "eval_num_tokens": 1752330.0,
+      "eval_runtime": 300.7292,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 270
+    },
+    {
+      "entropy": 1.3945425242185592,
+      "epoch": 1.9875666074600356,
+      "grad_norm": 0.042724609375,
+      "learning_rate": 5.7167044693701265e-05,
+      "loss": 0.33205204010009765,
+      "mean_token_accuracy": 0.8732210874557496,
+      "num_tokens": 1817167.0,
+      "step": 280
+    },
+    {
+      "epoch": 1.9875666074600356,
+      "eval_entropy": 1.3890694436572848,
+      "eval_loss": 0.337794691324234,
+      "eval_mean_token_accuracy": 0.869381708758218,
+      "eval_num_tokens": 1817167.0,
+      "eval_runtime": 300.7319,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 280
+    },
+    {
+      "entropy": 1.3927310644051967,
+      "epoch": 2.0568383658969807,
+      "grad_norm": 0.04931640625,
+      "learning_rate": 5.022632975833377e-05,
+      "loss": 0.32566084861755373,
+      "mean_token_accuracy": 0.8772806036166656,
+      "num_tokens": 1879244.0,
+      "step": 290
+    },
+    {
+      "epoch": 2.0568383658969807,
+      "eval_entropy": 1.3810661066146124,
+      "eval_loss": 0.33844009041786194,
+      "eval_mean_token_accuracy": 0.8736514789717538,
+      "eval_num_tokens": 1879244.0,
+      "eval_runtime": 300.7285,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 290
+    },
+    {
+      "entropy": 1.3756731271743774,
+      "epoch": 2.127886323268206,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 4.3590958211947086e-05,
+      "loss": 0.3194483041763306,
+      "mean_token_accuracy": 0.8763641104102134,
+      "num_tokens": 1944628.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.127886323268206,
+      "eval_entropy": 1.377114220271035,
+      "eval_loss": 0.3398720622062683,
+      "eval_mean_token_accuracy": 0.8727051256194948,
+      "eval_num_tokens": 1944628.0,
+      "eval_runtime": 300.7359,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 300
+    },
+    {
+      "entropy": 1.379591926932335,
+      "epoch": 2.1989342806394316,
+      "grad_norm": 0.0537109375,
+      "learning_rate": 3.7301635648990665e-05,
+      "loss": 0.32204880714416506,
+      "mean_token_accuracy": 0.8778151571750641,
+      "num_tokens": 2009741.0,
+      "step": 310
+    },
+    {
+      "epoch": 2.1989342806394316,
+      "eval_entropy": 1.377741853396098,
+      "eval_loss": 0.33864760398864746,
+      "eval_mean_token_accuracy": 0.8733364845079089,
+      "eval_num_tokens": 2009741.0,
+      "eval_runtime": 300.7271,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 310
+    },
+    {
+      "entropy": 1.3746213018894196,
+      "epoch": 2.269982238010657,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 3.139694477908672e-05,
+      "loss": 0.321340537071228,
+      "mean_token_accuracy": 0.8815709397196769,
+      "num_tokens": 2075182.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.269982238010657,
+      "eval_entropy": 1.3763913597379411,
+      "eval_loss": 0.337005615234375,
+      "eval_mean_token_accuracy": 0.8732053438822428,
+      "eval_num_tokens": 2075182.0,
+      "eval_runtime": 300.7109,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.21,
+      "step": 320
+    },
+    {
+      "entropy": 1.3788879275321961,
+      "epoch": 2.3410301953818826,
+      "grad_norm": 0.05517578125,
+      "learning_rate": 2.591310873612006e-05,
+      "loss": 0.323813796043396,
+      "mean_token_accuracy": 0.8769636407494545,
+      "num_tokens": 2140183.0,
+      "step": 330
+    },
+    {
+      "epoch": 2.3410301953818826,
+      "eval_entropy": 1.3787981498809088,
+      "eval_loss": 0.3364172577857971,
+      "eval_mean_token_accuracy": 0.8745575878355238,
+      "eval_num_tokens": 2140183.0,
+      "eval_runtime": 300.7322,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.209,
+      "step": 330
+    },
+    {
+      "entropy": 1.378483882546425,
+      "epoch": 2.412078152753108,
+      "grad_norm": 0.044677734375,
+      "learning_rate": 2.08837688624679e-05,
+      "loss": 0.322164249420166,
+      "mean_token_accuracy": 0.8781917616724968,
+      "num_tokens": 2205198.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.412078152753108,
+      "eval_entropy": 1.3776758587549602,
+      "eval_loss": 0.33581486344337463,
+      "eval_mean_token_accuracy": 0.8758961652952527,
+      "eval_num_tokens": 2205198.0,
+      "eval_runtime": 300.709,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.21,
+      "step": 340
+    },
+    {
+      "entropy": 1.380396232008934,
+      "epoch": 2.483126110124334,
+      "grad_norm": 0.047119140625,
+      "learning_rate": 1.6339778331583267e-05,
+      "loss": 0.3238497495651245,
+      "mean_token_accuracy": 0.8786081805825233,
+      "num_tokens": 2270293.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.483126110124334,
+      "eval_entropy": 1.376171973016527,
+      "eval_loss": 0.3355788290500641,
+      "eval_mean_token_accuracy": 0.8753649223418463,
+      "eval_num_tokens": 2270293.0,
+      "eval_runtime": 300.6615,
+      "eval_samples_per_second": 0.831,
+      "eval_steps_per_second": 0.21,
+      "step": 350
+    },
+    {
+      "entropy": 1.3808670938014984,
+      "epoch": 2.5541740674955595,
+      "grad_norm": 0.051025390625,
+      "learning_rate": 1.2309012874981617e-05,
+      "loss": 0.319537878036499,
+      "mean_token_accuracy": 0.8801632314920426,
+      "num_tokens": 2335208.0,
+      "step": 360
+    },
+    {
+      "epoch": 2.5541740674955595,
+      "eval_entropy": 1.3766641105924333,
+      "eval_loss": 0.33599570393562317,
+      "eval_mean_token_accuracy": 0.8745634517972432,
+      "eval_num_tokens": 2335208.0,
+      "eval_runtime": 300.6583,
+      "eval_samples_per_second": 0.832,
+      "eval_steps_per_second": 0.21,
+      "step": 360
+    },
+    {
+      "entropy": 1.3781378537416458,
+      "epoch": 2.625222024866785,
+      "grad_norm": 0.05339883267879486,
+      "learning_rate": 8.816199774752664e-06,
+      "loss": 0.33472251892089844,
+      "mean_token_accuracy": 0.8747120544314384,
+      "num_tokens": 65009.0,
+      "step": 370
+    },
+    {
+      "epoch": 2.625222024866785,
+      "eval_entropy": 1.3772984913417272,
+      "eval_loss": 0.33236590027809143,
+      "eval_mean_token_accuracy": 0.8738551376357911,
+      "eval_num_tokens": 65009.0,
+      "eval_runtime": 300.0305,
+      "eval_samples_per_second": 0.833,
+      "eval_steps_per_second": 0.21,
+      "step": 370
+    },
+    {
+      "entropy": 1.3793672323226929,
+      "epoch": 2.6962699822380105,
+      "grad_norm": 0.051000893115997314,
+      "learning_rate": 5.882766170665721e-06,
+      "loss": 0.33954639434814454,
+      "mean_token_accuracy": 0.8684806168079376,
+      "num_tokens": 130121.0,
+      "step": 380
+    },
+    {
+      "epoch": 2.6962699822380105,
+      "eval_entropy": 1.3772703030752758,
+      "eval_loss": 0.33121782541275024,
+      "eval_mean_token_accuracy": 0.8729122527061947,
+      "eval_num_tokens": 130121.0,
+      "eval_runtime": 299.9899,
+      "eval_samples_per_second": 0.833,
+      "eval_steps_per_second": 0.21,
+      "step": 380
+    },
+    {
+      "entropy": 1.3861564517021179,
+      "epoch": 2.767317939609236,
+      "grad_norm": 0.06085659936070442,
+      "learning_rate": 3.5267076124496645e-06,
+      "loss": 0.32278053760528563,
+      "mean_token_accuracy": 0.8717913642525673,
+      "num_tokens": 194755.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.767317939609236,
+      "eval_entropy": 1.377075269108727,
+      "eval_loss": 0.33130699396133423,
+      "eval_mean_token_accuracy": 0.872777887753078,
+      "eval_num_tokens": 194755.0,
+      "eval_runtime": 299.975,
+      "eval_samples_per_second": 0.833,
+      "eval_steps_per_second": 0.21,
+      "step": 390
+    },
+    {
+      "entropy": 1.3833425641059875,
+      "epoch": 2.838365896980462,
+      "grad_norm": 0.038919005542993546,
+      "learning_rate": 1.7624776636313346e-06,
+      "loss": 0.33400089740753175,
+      "mean_token_accuracy": 0.8762208908796311,
+      "num_tokens": 64908.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.838365896980462,
+      "eval_entropy": 1.382653968674796,
+      "eval_loss": 0.33011674880981445,
+      "eval_mean_token_accuracy": 0.8771265158577571,
+      "eval_num_tokens": 64908.0,
+      "eval_runtime": 299.5478,
+      "eval_samples_per_second": 0.835,
+      "eval_steps_per_second": 0.21,
+      "step": 400
+    },
+    {
+      "entropy": 1.3813997507095337,
+      "epoch": 2.9094138543516874,
+      "grad_norm": 0.05077703669667244,
+      "learning_rate": 6.008992341729469e-07,
+      "loss": 0.3278736352920532,
+      "mean_token_accuracy": 0.8779149636626243,
+      "num_tokens": 129920.0,
+      "step": 410
+    },
+    {
+      "epoch": 2.9094138543516874,
+      "eval_entropy": 1.383932490197439,
+      "eval_loss": 0.330141544342041,
+      "eval_mean_token_accuracy": 0.8756397148919484,
+      "eval_num_tokens": 129920.0,
+      "eval_runtime": 299.5186,
+      "eval_samples_per_second": 0.835,
+      "eval_steps_per_second": 0.21,
+      "step": 410
+    },
+    {
+      "entropy": 1.3849560827016831,
+      "epoch": 2.980461811722913,
+      "grad_norm": 0.0427376925945282,
+      "learning_rate": 4.909818585031589e-08,
+      "loss": 0.3287132024765015,
+      "mean_token_accuracy": 0.8746293559670448,
+      "num_tokens": 194470.0,
+      "step": 420
+    },
+    {
+      "epoch": 2.980461811722913,
+      "eval_entropy": 1.3841619680798243,
+      "eval_loss": 0.3298604488372803,
+      "eval_mean_token_accuracy": 0.8752325612401205,
+      "eval_num_tokens": 194470.0,
+      "eval_runtime": 299.5246,
+      "eval_samples_per_second": 0.835,
+      "eval_steps_per_second": 0.21,
+      "step": 420
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 423,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2407220018828902e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-423/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f6270b625c1e4dcfb4a14c5be9e6bb40ab178077a35f00e50a3d7cd4e080ee
+size 5649

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 512,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}