c926ab54640f: checkpoint-1000

.gitattributes

@@ -44,3 +44,4 @@ c926ab54640f/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 c926ab54640f/checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 c926ab54640f/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 c926ab54640f/checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+c926ab54640f/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

c926ab54640f/checkpoint-1000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B-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 0.20.0

c926ab54640f/checkpoint-1000/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B-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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

c926ab54640f/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f669413f4223ac11f077938116c0dee6b18651dbc2ab40693b78c75baa630d
+size 73911112

c926ab54640f/checkpoint-1000/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 %}

c926ab54640f/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18bc5f2427b7d62934bf2a48a7a170b66b26ffb62aa342daba5a482f0cc02d52
+size 148053627

c926ab54640f/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e72969f06af9c6f87381461ea7c42d2c619034c05d6bde5f0a1b791cdda29062
+size 14645

c926ab54640f/checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+size 1383

c926ab54640f/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e78cf599f427503687f21827f6ef2e5f0ef68e863059048e2ec9f6d975aac25
+size 1465

c926ab54640f/checkpoint-1000/tokenizer.json

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

c926ab54640f/checkpoint-1000/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

c926ab54640f/checkpoint-1000/trainer_state.json

@@ -0,0 +1,1034 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.309647602541883,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.25053702369332315,
+      "epoch": 0.023108030040439053,
+      "grad_norm": 0.3855944275856018,
+      "learning_rate": 0.00018968727415326884,
+      "loss": 0.2840240240097046,
+      "mean_token_accuracy": 0.9133788526058197,
+      "num_tokens": 91409.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.2452327784150839,
+      "epoch": 0.046216060080878106,
+      "grad_norm": 0.436616450548172,
+      "learning_rate": 0.00014422886902190014,
+      "loss": 0.20089757442474365,
+      "mean_token_accuracy": 0.9353952407836914,
+      "num_tokens": 186627.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.19640089981257916,
+      "epoch": 0.06932409012131716,
+      "grad_norm": 0.4252662658691406,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.18276022672653197,
+      "mean_token_accuracy": 0.938230411708355,
+      "num_tokens": 276604.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.1965320620685816,
+      "epoch": 0.09243212016175621,
+      "grad_norm": 0.4219682216644287,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.1999036192893982,
+      "mean_token_accuracy": 0.9345726266503334,
+      "num_tokens": 368108.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.1977928763255477,
+      "epoch": 0.11554015020219527,
+      "grad_norm": 0.3416396677494049,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.1896825909614563,
+      "mean_token_accuracy": 0.9379530012607574,
+      "num_tokens": 457334.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.20226533226668836,
+      "epoch": 0.1386481802426343,
+      "grad_norm": 0.5229596495628357,
+      "learning_rate": 0.00019987569212189224,
+      "loss": 0.1918914794921875,
+      "mean_token_accuracy": 0.9407946109771729,
+      "num_tokens": 90124.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.2129991866648197,
+      "epoch": 0.16175621028307338,
+      "grad_norm": 0.38087597489356995,
+      "learning_rate": 0.00019972037971811802,
+      "loss": 0.19346315860748292,
+      "mean_token_accuracy": 0.9426828250288963,
+      "num_tokens": 176242.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.20487470366060734,
+      "epoch": 0.18486424032351242,
+      "grad_norm": 0.35892292857170105,
+      "learning_rate": 0.00019950307753654017,
+      "loss": 0.18932828903198243,
+      "mean_token_accuracy": 0.9358784079551696,
+      "num_tokens": 267687.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.18303043842315675,
+      "epoch": 0.20797227036395147,
+      "grad_norm": 0.5852434635162354,
+      "learning_rate": 0.00019922392066001722,
+      "loss": 0.18723020553588868,
+      "mean_token_accuracy": 0.9429863467812538,
+      "num_tokens": 352134.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.17160551846027375,
+      "epoch": 0.23108030040439054,
+      "grad_norm": 0.5159252285957336,
+      "learning_rate": 0.00019888308262251285,
+      "loss": 0.15068645477294923,
+      "mean_token_accuracy": 0.9512565016746521,
+      "num_tokens": 440851.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.16275491286069155,
+      "epoch": 0.2541883304448296,
+      "grad_norm": 0.5486075282096863,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.16782530546188354,
+      "mean_token_accuracy": 0.9473349168896675,
+      "num_tokens": 531156.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.1631414294242859,
+      "epoch": 0.2772963604852686,
+      "grad_norm": 0.360660582780838,
+      "learning_rate": 0.00019801724878485438,
+      "loss": 0.1489890694618225,
+      "mean_token_accuracy": 0.9537395715713501,
+      "num_tokens": 621556.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.16629892718046904,
+      "epoch": 0.30040439052570767,
+      "grad_norm": 0.5829369425773621,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 0.1609186887741089,
+      "mean_token_accuracy": 0.9493778333067894,
+      "num_tokens": 714122.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.15167794916778804,
+      "epoch": 0.32351242056614676,
+      "grad_norm": 0.3773649334907532,
+      "learning_rate": 0.0001969077286229078,
+      "loss": 0.14646281003952027,
+      "mean_token_accuracy": 0.9529520198702812,
+      "num_tokens": 809857.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.1419608134776354,
+      "epoch": 0.3466204506065858,
+      "grad_norm": 0.4423299729824066,
+      "learning_rate": 0.0001962624246950012,
+      "loss": 0.1439625382423401,
+      "mean_token_accuracy": 0.9514987796545029,
+      "num_tokens": 896746.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.17105115856975317,
+      "epoch": 0.36972848064702485,
+      "grad_norm": 0.44132688641548157,
+      "learning_rate": 0.0001955572805786141,
+      "loss": 0.14246749877929688,
+      "mean_token_accuracy": 0.948833154141903,
+      "num_tokens": 984865.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.14561160299926995,
+      "epoch": 0.3928365106874639,
+      "grad_norm": 0.3809663653373718,
+      "learning_rate": 0.0001947927346167132,
+      "loss": 0.15373014211654662,
+      "mean_token_accuracy": 0.952961015701294,
+      "num_tokens": 1080231.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.16094056274741889,
+      "epoch": 0.41594454072790293,
+      "grad_norm": 0.368802934885025,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.14946006536483764,
+      "mean_token_accuracy": 0.9532878756523132,
+      "num_tokens": 1174200.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.14007117301225663,
+      "epoch": 0.439052570768342,
+      "grad_norm": 0.6444777846336365,
+      "learning_rate": 0.00019308737486442045,
+      "loss": 0.1405700922012329,
+      "mean_token_accuracy": 0.9617422357201576,
+      "num_tokens": 1261095.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.1333176439628005,
+      "epoch": 0.4621606008087811,
+      "grad_norm": 0.4077698886394501,
+      "learning_rate": 0.00019214762118704076,
+      "loss": 0.14433506727218628,
+      "mean_token_accuracy": 0.9545276626944542,
+      "num_tokens": 1347013.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.14489816222339869,
+      "epoch": 0.4852686308492201,
+      "grad_norm": 0.4106835424900055,
+      "learning_rate": 0.00019115058523116733,
+      "loss": 0.12317780256271363,
+      "mean_token_accuracy": 0.9603971764445305,
+      "num_tokens": 1436520.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.12729622349143027,
+      "epoch": 0.5083766608896592,
+      "grad_norm": 0.2570558190345764,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.12025457620620728,
+      "mean_token_accuracy": 0.9619329497218132,
+      "num_tokens": 1526164.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.12943572215735913,
+      "epoch": 0.5314846909300982,
+      "grad_norm": 0.4023452401161194,
+      "learning_rate": 0.0001889871808811469,
+      "loss": 0.13672986030578613,
+      "mean_token_accuracy": 0.9565972954034805,
+      "num_tokens": 1612243.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.11833337713032961,
+      "epoch": 0.5545927209705372,
+      "grad_norm": 0.7690483331680298,
+      "learning_rate": 0.00018782215733702286,
+      "loss": 0.10976905822753906,
+      "mean_token_accuracy": 0.9637095719575882,
+      "num_tokens": 1708578.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.11379784885793924,
+      "epoch": 0.5777007510109763,
+      "grad_norm": 0.31654056906700134,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.1196696400642395,
+      "mean_token_accuracy": 0.9632119759917259,
+      "num_tokens": 1800795.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.1469706142321229,
+      "epoch": 0.6008087810514153,
+      "grad_norm": 0.48627087473869324,
+      "learning_rate": 0.00018532908816321558,
+      "loss": 0.13480278253555297,
+      "mean_token_accuracy": 0.9569883048534393,
+      "num_tokens": 1895156.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.12755432203412057,
+      "epoch": 0.6239168110918544,
+      "grad_norm": 0.49406057596206665,
+      "learning_rate": 0.00018400259231507717,
+      "loss": 0.11772323846817016,
+      "mean_token_accuracy": 0.9615781545639038,
+      "num_tokens": 1992605.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.10990294981747865,
+      "epoch": 0.6470248411322935,
+      "grad_norm": 0.44597575068473816,
+      "learning_rate": 0.0001826238774315995,
+      "loss": 0.11711924076080323,
+      "mean_token_accuracy": 0.9635483607649803,
+      "num_tokens": 2078981.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.12252486441284419,
+      "epoch": 0.6701328711727326,
+      "grad_norm": 0.6590924859046936,
+      "learning_rate": 0.00018119380057158568,
+      "loss": 0.12246577739715576,
+      "mean_token_accuracy": 0.9635076820850372,
+      "num_tokens": 2163127.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.11667787805199623,
+      "epoch": 0.6932409012131716,
+      "grad_norm": 0.30897030234336853,
+      "learning_rate": 0.00017971325072229226,
+      "loss": 0.11207195520401,
+      "mean_token_accuracy": 0.9664140149950982,
+      "num_tokens": 2250020.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.10723365237936378,
+      "epoch": 0.7163489312536107,
+      "grad_norm": 0.35012784600257874,
+      "learning_rate": 0.000178183148246803,
+      "loss": 0.10141674280166627,
+      "mean_token_accuracy": 0.9667504042387008,
+      "num_tokens": 2342180.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.10656228372827173,
+      "epoch": 0.7394569612940497,
+      "grad_norm": 0.6778198480606079,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.11167047023773194,
+      "mean_token_accuracy": 0.9646604552865028,
+      "num_tokens": 2428901.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.12334352433681488,
+      "epoch": 0.7625649913344887,
+      "grad_norm": 0.3929327428340912,
+      "learning_rate": 0.00017497812029677344,
+      "loss": 0.13769056797027587,
+      "mean_token_accuracy": 0.9574923142790794,
+      "num_tokens": 2524924.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.115700420178473,
+      "epoch": 0.7856730213749278,
+      "grad_norm": 0.35736656188964844,
+      "learning_rate": 0.00017330518718298264,
+      "loss": 0.1097031831741333,
+      "mean_token_accuracy": 0.9680601879954338,
+      "num_tokens": 2616261.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.11344754723832011,
+      "epoch": 0.8087810514153668,
+      "grad_norm": 0.3905283510684967,
+      "learning_rate": 0.00017158668492597186,
+      "loss": 0.09722363948822021,
+      "mean_token_accuracy": 0.9685764014720917,
+      "num_tokens": 2706875.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.10129693355411291,
+      "epoch": 0.8318890814558059,
+      "grad_norm": 0.33620545268058777,
+      "learning_rate": 0.00016982368180860728,
+      "loss": 0.10325313806533813,
+      "mean_token_accuracy": 0.9673566803336143,
+      "num_tokens": 2794064.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.10174256730824709,
+      "epoch": 0.8549971114962449,
+      "grad_norm": 0.35370293259620667,
+      "learning_rate": 0.00016801727377709194,
+      "loss": 0.0895127534866333,
+      "mean_token_accuracy": 0.9702110648155212,
+      "num_tokens": 2881845.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.10100147491320968,
+      "epoch": 0.878105141536684,
+      "grad_norm": 0.33359017968177795,
+      "learning_rate": 0.00016616858375968595,
+      "loss": 0.11089967489242554,
+      "mean_token_accuracy": 0.9662180259823799,
+      "num_tokens": 2975509.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.11788110584020614,
+      "epoch": 0.901213171577123,
+      "grad_norm": 0.5891948938369751,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.11323659420013428,
+      "mean_token_accuracy": 0.967065966129303,
+      "num_tokens": 3069718.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.1004796303808689,
+      "epoch": 0.9243212016175621,
+      "grad_norm": 0.5099625587463379,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.09161977767944336,
+      "mean_token_accuracy": 0.9722862154245376,
+      "num_tokens": 3157514.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.09554047212004661,
+      "epoch": 0.9474292316580012,
+      "grad_norm": 0.4334423243999481,
+      "learning_rate": 0.00016038044103254775,
+      "loss": 0.10389481782913208,
+      "mean_token_accuracy": 0.9688831776380539,
+      "num_tokens": 3253608.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.11286892779171467,
+      "epoch": 0.9705372616984402,
+      "grad_norm": 0.5343768000602722,
+      "learning_rate": 0.000158374367223479,
+      "loss": 0.10636662244796753,
+      "mean_token_accuracy": 0.9680440634489059,
+      "num_tokens": 3339127.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.10603147987276315,
+      "epoch": 0.9936452917388793,
+      "grad_norm": 0.4976741671562195,
+      "learning_rate": 0.0001563320058063622,
+      "loss": 0.09392367601394654,
+      "mean_token_accuracy": 0.9700029551982879,
+      "num_tokens": 3426446.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.08927198938834362,
+      "epoch": 1.0161756210283073,
+      "grad_norm": 0.3850901126861572,
+      "learning_rate": 0.00015425462638657595,
+      "loss": 0.08777095079421997,
+      "mean_token_accuracy": 0.9736012770579412,
+      "num_tokens": 3509651.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.0771227509714663,
+      "epoch": 1.0392836510687464,
+      "grad_norm": 0.6629709601402283,
+      "learning_rate": 0.0001521435203379498,
+      "loss": 0.06896573901176453,
+      "mean_token_accuracy": 0.9790179893374443,
+      "num_tokens": 3600316.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.06483586076647044,
+      "epoch": 1.0623916811091854,
+      "grad_norm": 0.2478586584329605,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.059802645444869997,
+      "mean_token_accuracy": 0.9834248185157776,
+      "num_tokens": 3687453.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.055846321303397416,
+      "epoch": 1.0854997111496245,
+      "grad_norm": 0.4622909128665924,
+      "learning_rate": 0.00014782539786213183,
+      "loss": 0.054994475841522214,
+      "mean_token_accuracy": 0.9826823636889458,
+      "num_tokens": 3774980.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.05830292827449739,
+      "epoch": 1.1086077411900634,
+      "grad_norm": 0.4814852774143219,
+      "learning_rate": 0.0001456210657353163,
+      "loss": 0.05833314657211304,
+      "mean_token_accuracy": 0.9774734809994697,
+      "num_tokens": 3868848.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.0672043870203197,
+      "epoch": 1.1317157712305026,
+      "grad_norm": 0.31145647168159485,
+      "learning_rate": 0.00014338837391175582,
+      "loss": 0.06549112796783448,
+      "mean_token_accuracy": 0.9800179317593575,
+      "num_tokens": 3958195.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.06734551358968019,
+      "epoch": 1.1548238012709415,
+      "grad_norm": 0.38005223870277405,
+      "learning_rate": 0.00014112871031306119,
+      "loss": 0.07287130355834961,
+      "mean_token_accuracy": 0.979092413187027,
+      "num_tokens": 4043372.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.07410327121615409,
+      "epoch": 1.1779318313113807,
+      "grad_norm": 0.4899892210960388,
+      "learning_rate": 0.00013884347962746948,
+      "loss": 0.06940968036651611,
+      "mean_token_accuracy": 0.9783615455031395,
+      "num_tokens": 4132319.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.06618062341585755,
+      "epoch": 1.2010398613518198,
+      "grad_norm": 0.2635834515094757,
+      "learning_rate": 0.00013653410243663952,
+      "loss": 0.055328965187072754,
+      "mean_token_accuracy": 0.9836301594972611,
+      "num_tokens": 4228755.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.06513854041695595,
+      "epoch": 1.2241478913922588,
+      "grad_norm": 0.39269688725471497,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.06558798551559449,
+      "mean_token_accuracy": 0.9794289872050286,
+      "num_tokens": 4319565.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.062254238640889525,
+      "epoch": 1.247255921432698,
+      "grad_norm": 0.4004075527191162,
+      "learning_rate": 0.00013184866502516845,
+      "loss": 0.05614538192749023,
+      "mean_token_accuracy": 0.9825843557715416,
+      "num_tokens": 4408534.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.06734559782780707,
+      "epoch": 1.2703639514731369,
+      "grad_norm": 0.4320114552974701,
+      "learning_rate": 0.00012947551744109043,
+      "loss": 0.06545217037200927,
+      "mean_token_accuracy": 0.9746319189667701,
+      "num_tokens": 4499330.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.06069298703223467,
+      "epoch": 1.293471981513576,
+      "grad_norm": 0.3763878047466278,
+      "learning_rate": 0.00012708404681430053,
+      "loss": 0.04800793528556824,
+      "mean_token_accuracy": 0.9849550426006317,
+      "num_tokens": 4596459.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.0649140477180481,
+      "epoch": 1.316580011554015,
+      "grad_norm": 0.5567355155944824,
+      "learning_rate": 0.00012467573976902935,
+      "loss": 0.06543132662773132,
+      "mean_token_accuracy": 0.9804893583059311,
+      "num_tokens": 4683324.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.06983062694780529,
+      "epoch": 1.339688041594454,
+      "grad_norm": 0.3690188229084015,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.05921154618263245,
+      "mean_token_accuracy": 0.979171933233738,
+      "num_tokens": 4776192.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.05803882866166532,
+      "epoch": 1.362796071634893,
+      "grad_norm": 0.4643764793872833,
+      "learning_rate": 0.00011981461431993977,
+      "loss": 0.0567037045955658,
+      "mean_token_accuracy": 0.9825309008359909,
+      "num_tokens": 4868753.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.06131467376835644,
+      "epoch": 1.3859041016753322,
+      "grad_norm": 0.2811519205570221,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.05465059876441956,
+      "mean_token_accuracy": 0.9829435467720031,
+      "num_tokens": 4954973.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.05336195956915617,
+      "epoch": 1.4090121317157713,
+      "grad_norm": 0.3655995726585388,
+      "learning_rate": 0.00011490422661761744,
+      "loss": 0.044907957315444946,
+      "mean_token_accuracy": 0.9845176979899406,
+      "num_tokens": 5045663.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.056381219532340765,
+      "epoch": 1.4321201617562103,
+      "grad_norm": 0.5765703916549683,
+      "learning_rate": 0.00011243437046474853,
+      "loss": 0.05860241651535034,
+      "mean_token_accuracy": 0.9793657884001732,
+      "num_tokens": 5138332.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.05941152316518128,
+      "epoch": 1.4552281917966494,
+      "grad_norm": 0.4769803285598755,
+      "learning_rate": 0.00010995678465958168,
+      "loss": 0.05846758484840393,
+      "mean_token_accuracy": 0.9831168636679649,
+      "num_tokens": 5235297.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.05932227531448007,
+      "epoch": 1.4783362218370883,
+      "grad_norm": 0.3836939334869385,
+      "learning_rate": 0.00010747300935864243,
+      "loss": 0.05561003088951111,
+      "mean_token_accuracy": 0.979756586253643,
+      "num_tokens": 5324180.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.06048546452075243,
+      "epoch": 1.5014442518775275,
+      "grad_norm": 0.3636479675769806,
+      "learning_rate": 0.00010498458856606972,
+      "loss": 0.06015471816062927,
+      "mean_token_accuracy": 0.9834305003285408,
+      "num_tokens": 5414375.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.05355621734634042,
+      "epoch": 1.5245522819179667,
+      "grad_norm": 0.18880754709243774,
+      "learning_rate": 0.0001024930691738073,
+      "loss": 0.05090702176094055,
+      "mean_token_accuracy": 0.9835599064826965,
+      "num_tokens": 5509152.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.062485543685033916,
+      "epoch": 1.5476603119584056,
+      "grad_norm": 0.5280900597572327,
+      "learning_rate": 0.0001,
+      "loss": 0.05413004159927368,
+      "mean_token_accuracy": 0.9808856308460235,
+      "num_tokens": 5600257.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.05261599705554545,
+      "epoch": 1.5707683419988445,
+      "grad_norm": 0.43818485736846924,
+      "learning_rate": 9.750693082619273e-05,
+      "loss": 0.056223487854003905,
+      "mean_token_accuracy": 0.9810379788279533,
+      "num_tokens": 5689300.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.05766241885721683,
+      "epoch": 1.5938763720392837,
+      "grad_norm": 0.35383379459381104,
+      "learning_rate": 9.501541143393028e-05,
+      "loss": 0.05723288059234619,
+      "mean_token_accuracy": 0.9839297741651535,
+      "num_tokens": 5781511.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.05827973254490644,
+      "epoch": 1.6169844020797228,
+      "grad_norm": 0.5599336624145508,
+      "learning_rate": 9.252699064135758e-05,
+      "loss": 0.05382978320121765,
+      "mean_token_accuracy": 0.9801423370838165,
+      "num_tokens": 5874858.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.05071314079686999,
+      "epoch": 1.6400924321201618,
+      "grad_norm": 0.30956578254699707,
+      "learning_rate": 9.004321534041835e-05,
+      "loss": 0.048029133677482606,
+      "mean_token_accuracy": 0.9838623449206352,
+      "num_tokens": 5965600.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.05675939819775522,
+      "epoch": 1.6632004621606007,
+      "grad_norm": 0.3796592652797699,
+      "learning_rate": 8.756562953525152e-05,
+      "loss": 0.05276126265525818,
+      "mean_token_accuracy": 0.9829048261046409,
+      "num_tokens": 6060326.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.049542685598134996,
+      "epoch": 1.6863084922010398,
+      "grad_norm": 1.2343695163726807,
+      "learning_rate": 8.509577338238255e-05,
+      "loss": 0.056018334627151486,
+      "mean_token_accuracy": 0.982017770409584,
+      "num_tokens": 6150119.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.053010733076371254,
+      "epoch": 1.709416522241479,
+      "grad_norm": 0.4369167387485504,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.04325876533985138,
+      "mean_token_accuracy": 0.9853935018181801,
+      "num_tokens": 6236359.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.05330478888936341,
+      "epoch": 1.732524552281918,
+      "grad_norm": 0.4538385570049286,
+      "learning_rate": 8.018538568006027e-05,
+      "loss": 0.043788546323776247,
+      "mean_token_accuracy": 0.9850618049502373,
+      "num_tokens": 6327884.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.05375363389030099,
+      "epoch": 1.7556325823223569,
+      "grad_norm": 0.7549631595611572,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 0.04628949463367462,
+      "mean_token_accuracy": 0.9835410952568054,
+      "num_tokens": 6417306.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.04637230115476996,
+      "epoch": 1.778740612362796,
+      "grad_norm": 0.356107234954834,
+      "learning_rate": 7.532426023097063e-05,
+      "loss": 0.05348780155181885,
+      "mean_token_accuracy": 0.9835655644536019,
+      "num_tokens": 6505692.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.04872691249474883,
+      "epoch": 1.8018486424032352,
+      "grad_norm": 0.37483975291252136,
+      "learning_rate": 7.291595318569951e-05,
+      "loss": 0.04384237229824066,
+      "mean_token_accuracy": 0.9868102520704269,
+      "num_tokens": 6591038.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.04930867259390652,
+      "epoch": 1.8249566724436743,
+      "grad_norm": 0.4880582392215729,
+      "learning_rate": 7.052448255890957e-05,
+      "loss": 0.04446132481098175,
+      "mean_token_accuracy": 0.9854639306664467,
+      "num_tokens": 6683075.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.042057307437062263,
+      "epoch": 1.8480647024841133,
+      "grad_norm": 0.862926721572876,
+      "learning_rate": 6.815133497483157e-05,
+      "loss": 0.045346221327781676,
+      "mean_token_accuracy": 0.9870812594890594,
+      "num_tokens": 6773946.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.0443664045073092,
+      "epoch": 1.8711727325245522,
+      "grad_norm": 0.2753954529762268,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 0.040318018198013304,
+      "mean_token_accuracy": 0.9870508715510369,
+      "num_tokens": 6860906.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.043758259457536045,
+      "epoch": 1.8942807625649913,
+      "grad_norm": 0.5021117925643921,
+      "learning_rate": 6.34658975633605e-05,
+      "loss": 0.04408907890319824,
+      "mean_token_accuracy": 0.9874476924538612,
+      "num_tokens": 6950989.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.05261732591316104,
+      "epoch": 1.9173887926054305,
+      "grad_norm": 0.3293974697589874,
+      "learning_rate": 6.115652037253053e-05,
+      "loss": 0.05084437131881714,
+      "mean_token_accuracy": 0.9828155979514122,
+      "num_tokens": 7043566.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.049157765973359344,
+      "epoch": 1.9404968226458694,
+      "grad_norm": 0.6247967481613159,
+      "learning_rate": 5.887128968693887e-05,
+      "loss": 0.049098473787307736,
+      "mean_token_accuracy": 0.9854553818702698,
+      "num_tokens": 7133065.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.049550878209993245,
+      "epoch": 1.9636048526863084,
+      "grad_norm": 0.2307836264371872,
+      "learning_rate": 5.6611626088244194e-05,
+      "loss": 0.04479062855243683,
+      "mean_token_accuracy": 0.9846531033515931,
+      "num_tokens": 7221516.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.0435835994547233,
+      "epoch": 1.9867128827267475,
+      "grad_norm": 0.24384470283985138,
+      "learning_rate": 5.43789342646837e-05,
+      "loss": 0.03907274603843689,
+      "mean_token_accuracy": 0.9867141246795654,
+      "num_tokens": 7309025.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.04322688312580188,
+      "epoch": 2.009243212016176,
+      "grad_norm": 0.21144774556159973,
+      "learning_rate": 5.217460213786821e-05,
+      "loss": 0.0391358882188797,
+      "mean_token_accuracy": 0.986832701242887,
+      "num_tokens": 7396115.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.03581508058123291,
+      "epoch": 2.0323512420566145,
+      "grad_norm": 0.28638023138046265,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.02226865738630295,
+      "mean_token_accuracy": 0.9927692636847496,
+      "num_tokens": 7490375.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.030983813642524182,
+      "epoch": 2.0554592720970537,
+      "grad_norm": 0.17771832644939423,
+      "learning_rate": 4.78564796620502e-05,
+      "loss": 0.019702091813087463,
+      "mean_token_accuracy": 0.9947595551609993,
+      "num_tokens": 7578846.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.026725827786140143,
+      "epoch": 2.078567302137493,
+      "grad_norm": 0.5979490280151367,
+      "learning_rate": 4.574537361342407e-05,
+      "loss": 0.0201450914144516,
+      "mean_token_accuracy": 0.9922356709837914,
+      "num_tokens": 7666642.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.024782690638676285,
+      "epoch": 2.101675332177932,
+      "grad_norm": 0.4277927279472351,
+      "learning_rate": 4.3667994193637796e-05,
+      "loss": 0.02080860733985901,
+      "mean_token_accuracy": 0.9937450751662255,
+      "num_tokens": 7755801.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.025407701497897506,
+      "epoch": 2.1247833622183707,
+      "grad_norm": 0.29362452030181885,
+      "learning_rate": 4.1625632776521037e-05,
+      "loss": 0.019558851420879365,
+      "mean_token_accuracy": 0.9934525847434997,
+      "num_tokens": 7842920.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.029032097558956593,
+      "epoch": 2.14789139225881,
+      "grad_norm": 0.3597257733345032,
+      "learning_rate": 3.961955896745224e-05,
+      "loss": 0.02659837603569031,
+      "mean_token_accuracy": 0.9918435022234917,
+      "num_tokens": 7938579.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.02991311177611351,
+      "epoch": 2.170999422299249,
+      "grad_norm": 0.19675660133361816,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.02174474149942398,
+      "mean_token_accuracy": 0.9930533483624459,
+      "num_tokens": 8032966.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.029429485229775308,
+      "epoch": 2.194107452339688,
+      "grad_norm": 0.3623603582382202,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.02167274206876755,
+      "mean_token_accuracy": 0.9943236753344535,
+      "num_tokens": 8119614.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.023378267791122197,
+      "epoch": 2.217215482380127,
+      "grad_norm": 0.2948749363422394,
+      "learning_rate": 3.383141624031408e-05,
+      "loss": 0.015380550920963288,
+      "mean_token_accuracy": 0.9945817112922668,
+      "num_tokens": 8210511.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.026587225706316532,
+      "epoch": 2.240323512420566,
+      "grad_norm": 0.7488850355148315,
+      "learning_rate": 3.198272622290804e-05,
+      "loss": 0.025915104150772094,
+      "mean_token_accuracy": 0.9911931097507477,
+      "num_tokens": 8303818.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.027203144447412342,
+      "epoch": 2.263431542461005,
+      "grad_norm": 0.6022213101387024,
+      "learning_rate": 3.0176318191392726e-05,
+      "loss": 0.02036922574043274,
+      "mean_token_accuracy": 0.9930319502949715,
+      "num_tokens": 8400133.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.02855561631731689,
+      "epoch": 2.2865395725014444,
+      "grad_norm": 0.22805671393871307,
+      "learning_rate": 2.8413315074028158e-05,
+      "loss": 0.018108007311820985,
+      "mean_token_accuracy": 0.994237132370472,
+      "num_tokens": 8491445.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.02661266502691433,
+      "epoch": 2.309647602541883,
+      "grad_norm": 0.25784555077552795,
+      "learning_rate": 2.669481281701739e-05,
+      "loss": 0.01786753386259079,
+      "mean_token_accuracy": 0.9943538159132004,
+      "num_tokens": 8580828.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1299,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1005888994156544e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

c926ab54640f/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590a0797f1cb9af93f293e5538244672d5aa3922e4ac279c9baa8f2267c2ccf8
+size 5777