c926ab54640f: checkpoint-500

.gitattributes

@@ -39,3 +39,4 @@ c926ab54640f/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 c926ab54640f/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 c926ab54640f/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 c926ab54640f/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+c926ab54640f/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

c926ab54640f/checkpoint-500/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-500/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-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11ca636a0ad501f1b30e701cab46aba690668d5efcb3959249e158954c44a23
+size 73911112

c926ab54640f/checkpoint-500/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-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:209d9b161637ca9b47532c4407e99cdc6109f225be1ea737d88f33288f4c39a5
+size 148053627

c926ab54640f/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92ba0812c892400798413a7f63295814fc4b9dbd35182e7532ea11aef0f6b40
+size 14645

c926ab54640f/checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
+size 1383

c926ab54640f/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fdb6bbcc39bde0d76fb201f3aceeba6fcd645c733688d4dc471422303550a95
+size 1465

c926ab54640f/checkpoint-500/tokenizer.json

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

c926ab54640f/checkpoint-500/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-500/trainer_state.json

@@ -0,0 +1,534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1548238012709415,
+  "eval_steps": 500,
+  "global_step": 500,
+  "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
+    }
+  ],
+  "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": 5.486931860775322e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

c926ab54640f/checkpoint-500/training_args.bin

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