Auto-save: checkpoint-500

checkpoint-500/README.md

@@ -0,0 +1,209 @@
+---
+base_model: arnir0/Tiny-LLM
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:arnir0/Tiny-LLM
+- 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 0.16.0

checkpoint-500/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "arnir0/Tiny-LLM",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b7a5b995b753926ee4ed409a8713b1d60469a7e999a9342e6482c0ce2e096f1
+size 161544

checkpoint-500/chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46194714e9cc284a38f13f2d69fe5a611e52f3a7028276e70dcf137c8dd423da
+size 331380

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6ac71967fcea72f54557e43d13a20eaa2538ba4f9213770763e20cb37bb62a
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:692b4198164fe483d83e148382735ebb94f9a812e7d8daa84882790e0416772b
+size 1064

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1e-05,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 4.681882086396217,
+      "epoch": 2e-07,
+      "grad_norm": 1.8101623058319092,
+      "learning_rate": 0.00019999996400000002,
+      "loss": 4.7488,
+      "mean_token_accuracy": 0.21048998106271027,
+      "num_tokens": 163840.0,
+      "step": 10
+    },
+    {
+      "entropy": 4.630608141422272,
+      "epoch": 4e-07,
+      "grad_norm": 1.4383951425552368,
+      "learning_rate": 0.00019999992400000002,
+      "loss": 4.5281,
+      "mean_token_accuracy": 0.23297898340970277,
+      "num_tokens": 327680.0,
+      "step": 20
+    },
+    {
+      "entropy": 4.616623382270336,
+      "epoch": 6e-07,
+      "grad_norm": 0.9552226066589355,
+      "learning_rate": 0.000199999884,
+      "loss": 4.4224,
+      "mean_token_accuracy": 0.2532991207204759,
+      "num_tokens": 491520.0,
+      "step": 30
+    },
+    {
+      "entropy": 4.476823356747627,
+      "epoch": 8e-07,
+      "grad_norm": 0.7593826055526733,
+      "learning_rate": 0.000199999844,
+      "loss": 4.2919,
+      "mean_token_accuracy": 0.2635325016453862,
+      "num_tokens": 655360.0,
+      "step": 40
+    },
+    {
+      "entropy": 4.496281471848488,
+      "epoch": 1e-06,
+      "grad_norm": 0.7781745195388794,
+      "learning_rate": 0.000199999804,
+      "loss": 4.2526,
+      "mean_token_accuracy": 0.2696419832296669,
+      "num_tokens": 819200.0,
+      "step": 50
+    },
+    {
+      "entropy": 4.38021636158228,
+      "epoch": 1.2e-06,
+      "grad_norm": 0.8273451924324036,
+      "learning_rate": 0.000199999764,
+      "loss": 4.1605,
+      "mean_token_accuracy": 0.28010752722620963,
+      "num_tokens": 983040.0,
+      "step": 60
+    },
+    {
+      "entropy": 4.35167231708765,
+      "epoch": 1.4e-06,
+      "grad_norm": 0.7806651592254639,
+      "learning_rate": 0.000199999724,
+      "loss": 4.1294,
+      "mean_token_accuracy": 0.2855694043450058,
+      "num_tokens": 1146880.0,
+      "step": 70
+    },
+    {
+      "entropy": 4.289483310282231,
+      "epoch": 1.6e-06,
+      "grad_norm": 1.1951167583465576,
+      "learning_rate": 0.00019999968400000003,
+      "loss": 4.0522,
+      "mean_token_accuracy": 0.29565004920586946,
+      "num_tokens": 1310720.0,
+      "step": 80
+    },
+    {
+      "entropy": 4.2617059499025345,
+      "epoch": 1.8e-06,
+      "grad_norm": 0.7983517050743103,
+      "learning_rate": 0.00019999964400000002,
+      "loss": 4.0425,
+      "mean_token_accuracy": 0.2970735584385693,
+      "num_tokens": 1474560.0,
+      "step": 90
+    },
+    {
+      "entropy": 4.291365940868855,
+      "epoch": 2e-06,
+      "grad_norm": 0.876205563545227,
+      "learning_rate": 0.00019999960400000002,
+      "loss": 4.0675,
+      "mean_token_accuracy": 0.3046859731897712,
+      "num_tokens": 1638400.0,
+      "step": 100
+    },
+    {
+      "entropy": 4.177960188686848,
+      "epoch": 2.2e-06,
+      "grad_norm": 0.941405177116394,
+      "learning_rate": 0.00019999956400000002,
+      "loss": 3.9484,
+      "mean_token_accuracy": 0.31035557202994823,
+      "num_tokens": 1802240.0,
+      "step": 110
+    },
+    {
+      "entropy": 4.215415245294571,
+      "epoch": 2.4e-06,
+      "grad_norm": 0.9774227738380432,
+      "learning_rate": 0.00019999952400000001,
+      "loss": 3.9721,
+      "mean_token_accuracy": 0.31370967756956813,
+      "num_tokens": 1966080.0,
+      "step": 120
+    },
+    {
+      "entropy": 4.165915034711361,
+      "epoch": 2.6e-06,
+      "grad_norm": 0.8901327252388,
+      "learning_rate": 0.000199999484,
+      "loss": 3.9121,
+      "mean_token_accuracy": 0.32175586447119714,
+      "num_tokens": 2129920.0,
+      "step": 130
+    },
+    {
+      "entropy": 4.166300415992737,
+      "epoch": 2.8e-06,
+      "grad_norm": 0.8631859421730042,
+      "learning_rate": 0.000199999444,
+      "loss": 3.9235,
+      "mean_token_accuracy": 0.3200329922139645,
+      "num_tokens": 2293760.0,
+      "step": 140
+    },
+    {
+      "entropy": 4.1618256404995915,
+      "epoch": 3e-06,
+      "grad_norm": 1.145038366317749,
+      "learning_rate": 0.000199999404,
+      "loss": 3.8996,
+      "mean_token_accuracy": 0.32328323619440197,
+      "num_tokens": 2457600.0,
+      "step": 150
+    },
+    {
+      "entropy": 4.137338411808014,
+      "epoch": 3.2e-06,
+      "grad_norm": 0.7997400164604187,
+      "learning_rate": 0.000199999364,
+      "loss": 3.8569,
+      "mean_token_accuracy": 0.3280364129692316,
+      "num_tokens": 2621440.0,
+      "step": 160
+    },
+    {
+      "entropy": 4.117797307670116,
+      "epoch": 3.4e-06,
+      "grad_norm": 0.7961279153823853,
+      "learning_rate": 0.000199999324,
+      "loss": 3.8678,
+      "mean_token_accuracy": 0.33163489773869514,
+      "num_tokens": 2785280.0,
+      "step": 170
+    },
+    {
+      "entropy": 4.0607512786984445,
+      "epoch": 3.6e-06,
+      "grad_norm": 0.7493350505828857,
+      "learning_rate": 0.000199999284,
+      "loss": 3.831,
+      "mean_token_accuracy": 0.3335166173055768,
+      "num_tokens": 2949120.0,
+      "step": 180
+    },
+    {
+      "entropy": 4.085338307917118,
+      "epoch": 3.8e-06,
+      "grad_norm": 1.129760503768921,
+      "learning_rate": 0.000199999244,
+      "loss": 3.8072,
+      "mean_token_accuracy": 0.3388257572427392,
+      "num_tokens": 3112960.0,
+      "step": 190
+    },
+    {
+      "entropy": 4.057117411494255,
+      "epoch": 4e-06,
+      "grad_norm": 0.8071986436843872,
+      "learning_rate": 0.00019999920400000002,
+      "loss": 3.7947,
+      "mean_token_accuracy": 0.33903348054736854,
+      "num_tokens": 3276800.0,
+      "step": 200
+    },
+    {
+      "entropy": 4.037219819426537,
+      "epoch": 4.2e-06,
+      "grad_norm": 0.8994059562683105,
+      "learning_rate": 0.00019999916400000002,
+      "loss": 3.7657,
+      "mean_token_accuracy": 0.34161779154092076,
+      "num_tokens": 3440640.0,
+      "step": 210
+    },
+    {
+      "entropy": 4.041350077092647,
+      "epoch": 4.4e-06,
+      "grad_norm": 0.7302452921867371,
+      "learning_rate": 0.000199999124,
+      "loss": 3.8119,
+      "mean_token_accuracy": 0.3382453568279743,
+      "num_tokens": 3604480.0,
+      "step": 220
+    },
+    {
+      "entropy": 4.035373999178409,
+      "epoch": 4.6e-06,
+      "grad_norm": 0.9680087566375732,
+      "learning_rate": 0.000199999084,
+      "loss": 3.7489,
+      "mean_token_accuracy": 0.3464503912255168,
+      "num_tokens": 3768320.0,
+      "step": 230
+    },
+    {
+      "entropy": 3.9953515723347666,
+      "epoch": 4.8e-06,
+      "grad_norm": 0.7697106003761292,
+      "learning_rate": 0.000199999044,
+      "loss": 3.7248,
+      "mean_token_accuracy": 0.3462060123682022,
+      "num_tokens": 3932160.0,
+      "step": 240
+    },
+    {
+      "entropy": 3.9689931511878966,
+      "epoch": 5e-06,
+      "grad_norm": 1.1667910814285278,
+      "learning_rate": 0.000199999004,
+      "loss": 3.7164,
+      "mean_token_accuracy": 0.34726906241849065,
+      "num_tokens": 4096000.0,
+      "step": 250
+    },
+    {
+      "entropy": 4.021870079636574,
+      "epoch": 5.2e-06,
+      "grad_norm": 0.8651186227798462,
+      "learning_rate": 0.000199998964,
+      "loss": 3.7351,
+      "mean_token_accuracy": 0.3484176443889737,
+      "num_tokens": 4259840.0,
+      "step": 260
+    },
+    {
+      "entropy": 3.9606954142451287,
+      "epoch": 5.4e-06,
+      "grad_norm": 0.8886153697967529,
+      "learning_rate": 0.000199998924,
+      "loss": 3.6983,
+      "mean_token_accuracy": 0.3521566468290985,
+      "num_tokens": 4423680.0,
+      "step": 270
+    },
+    {
+      "entropy": 3.98917995095253,
+      "epoch": 5.6e-06,
+      "grad_norm": 0.8162663578987122,
+      "learning_rate": 0.00019999888400000002,
+      "loss": 3.7142,
+      "mean_token_accuracy": 0.35303030218929055,
+      "num_tokens": 4587520.0,
+      "step": 280
+    },
+    {
+      "entropy": 3.9785293996334077,
+      "epoch": 5.8e-06,
+      "grad_norm": 0.8422560691833496,
+      "learning_rate": 0.00019999884400000002,
+      "loss": 3.7103,
+      "mean_token_accuracy": 0.3540017107501626,
+      "num_tokens": 4751360.0,
+      "step": 290
+    },
+    {
+      "entropy": 3.95225318223238,
+      "epoch": 6e-06,
+      "grad_norm": 0.7754431366920471,
+      "learning_rate": 0.00019999880400000002,
+      "loss": 3.6983,
+      "mean_token_accuracy": 0.3531586013734341,
+      "num_tokens": 4915200.0,
+      "step": 300
+    },
+    {
+      "entropy": 3.9309102073311806,
+      "epoch": 6.2e-06,
+      "grad_norm": 0.7777474522590637,
+      "learning_rate": 0.00019999876400000002,
+      "loss": 3.655,
+      "mean_token_accuracy": 0.3573313795030117,
+      "num_tokens": 5079040.0,
+      "step": 310
+    },
+    {
+      "entropy": 3.962353430688381,
+      "epoch": 6.4e-06,
+      "grad_norm": 0.821111261844635,
+      "learning_rate": 0.000199998724,
+      "loss": 3.702,
+      "mean_token_accuracy": 0.3523032732307911,
+      "num_tokens": 5242880.0,
+      "step": 320
+    },
+    {
+      "entropy": 3.917423368990421,
+      "epoch": 6.6e-06,
+      "grad_norm": 0.8956252336502075,
+      "learning_rate": 0.000199998684,
+      "loss": 3.6602,
+      "mean_token_accuracy": 0.3550891989842057,
+      "num_tokens": 5406720.0,
+      "step": 330
+    },
+    {
+      "entropy": 3.9431545346975327,
+      "epoch": 6.8e-06,
+      "grad_norm": 1.007882833480835,
+      "learning_rate": 0.000199998644,
+      "loss": 3.6942,
+      "mean_token_accuracy": 0.35562072321772575,
+      "num_tokens": 5570560.0,
+      "step": 340
+    },
+    {
+      "entropy": 3.9284002274274825,
+      "epoch": 7e-06,
+      "grad_norm": 0.9456566572189331,
+      "learning_rate": 0.000199998604,
+      "loss": 3.6595,
+      "mean_token_accuracy": 0.36055718529969455,
+      "num_tokens": 5734400.0,
+      "step": 350
+    },
+    {
+      "entropy": 3.909215646982193,
+      "epoch": 7.2e-06,
+      "grad_norm": 0.8078492879867554,
+      "learning_rate": 0.000199998564,
+      "loss": 3.6582,
+      "mean_token_accuracy": 0.360257819108665,
+      "num_tokens": 5898240.0,
+      "step": 360
+    },
+    {
+      "entropy": 3.8888073176145554,
+      "epoch": 7.4e-06,
+      "grad_norm": 0.7833829522132874,
+      "learning_rate": 0.000199998524,
+      "loss": 3.6101,
+      "mean_token_accuracy": 0.361834067478776,
+      "num_tokens": 6062080.0,
+      "step": 370
+    },
+    {
+      "entropy": 3.9230842366814613,
+      "epoch": 7.6e-06,
+      "grad_norm": 0.9458137154579163,
+      "learning_rate": 0.000199998484,
+      "loss": 3.652,
+      "mean_token_accuracy": 0.3581683767028153,
+      "num_tokens": 6225920.0,
+      "step": 380
+    },
+    {
+      "entropy": 3.8731665804982187,
+      "epoch": 7.8e-06,
+      "grad_norm": 0.9032741785049438,
+      "learning_rate": 0.00019999844400000002,
+      "loss": 3.593,
+      "mean_token_accuracy": 0.36429007835686206,
+      "num_tokens": 6389760.0,
+      "step": 390
+    },
+    {
+      "entropy": 3.8826796427369117,
+      "epoch": 8e-06,
+      "grad_norm": 1.0131497383117676,
+      "learning_rate": 0.00019999840400000002,
+      "loss": 3.6275,
+      "mean_token_accuracy": 0.3626038616523147,
+      "num_tokens": 6553600.0,
+      "step": 400
+    },
+    {
+      "entropy": 3.797895699739456,
+      "epoch": 8.2e-06,
+      "grad_norm": 1.8830029964447021,
+      "learning_rate": 0.00019999836400000001,
+      "loss": 3.5907,
+      "mean_token_accuracy": 0.3668621705844998,
+      "num_tokens": 6717440.0,
+      "step": 410
+    },
+    {
+      "entropy": 4.125404280424118,
+      "epoch": 8.4e-06,
+      "grad_norm": 1.2633025646209717,
+      "learning_rate": 0.000199998324,
+      "loss": 4.0048,
+      "mean_token_accuracy": 0.31696603083983066,
+      "num_tokens": 6881280.0,
+      "step": 420
+    },
+    {
+      "entropy": 4.128296630084515,
+      "epoch": 8.6e-06,
+      "grad_norm": 1.0745359659194946,
+      "learning_rate": 0.000199998284,
+      "loss": 3.9063,
+      "mean_token_accuracy": 0.33364491648972033,
+      "num_tokens": 7045120.0,
+      "step": 430
+    },
+    {
+      "entropy": 4.24590267688036,
+      "epoch": 8.8e-06,
+      "grad_norm": 1.1425697803497314,
+      "learning_rate": 0.000199998244,
+      "loss": 4.0033,
+      "mean_token_accuracy": 0.33159213066101073,
+      "num_tokens": 7208960.0,
+      "step": 440
+    },
+    {
+      "entropy": 4.121617695689201,
+      "epoch": 9e-06,
+      "grad_norm": 0.974037766456604,
+      "learning_rate": 0.000199998204,
+      "loss": 3.8761,
+      "mean_token_accuracy": 0.33751832917332647,
+      "num_tokens": 7372800.0,
+      "step": 450
+    },
+    {
+      "entropy": 4.072012856602669,
+      "epoch": 9.2e-06,
+      "grad_norm": 1.1092954874038696,
+      "learning_rate": 0.000199998164,
+      "loss": 3.7707,
+      "mean_token_accuracy": 0.3500672049820423,
+      "num_tokens": 7536640.0,
+      "step": 460
+    },
+    {
+      "entropy": 4.049280053377151,
+      "epoch": 9.4e-06,
+      "grad_norm": 0.7694963812828064,
+      "learning_rate": 0.00019999812400000002,
+      "loss": 3.7629,
+      "mean_token_accuracy": 0.35735581498593094,
+      "num_tokens": 7700480.0,
+      "step": 470
+    },
+    {
+      "entropy": 4.024319298565388,
+      "epoch": 9.6e-06,
+      "grad_norm": 0.8389015197753906,
+      "learning_rate": 0.00019999808400000002,
+      "loss": 3.7232,
+      "mean_token_accuracy": 0.3568609481677413,
+      "num_tokens": 7864320.0,
+      "step": 480
+    },
+    {
+      "entropy": 4.112220963835716,
+      "epoch": 9.8e-06,
+      "grad_norm": 1.2819980382919312,
+      "learning_rate": 0.00019999804400000002,
+      "loss": 3.9523,
+      "mean_token_accuracy": 0.333504399843514,
+      "num_tokens": 8028160.0,
+      "step": 490
+    },
+    {
+      "entropy": 4.133245687186718,
+      "epoch": 1e-05,
+      "grad_norm": 1.538874864578247,
+      "learning_rate": 0.00019999800400000002,
+      "loss": 3.9121,
+      "mean_token_accuracy": 0.34392106607556344,
+      "num_tokens": 8192000.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 50000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "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": 338407981056000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ebd22e1fad503768058246be728421e65c3b0259f299df149463b1c85a1671
+size 5752