checkpoint-1750 | loss=?

checkpoint-1750/README.md

@@ -0,0 +1,208 @@
+---
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:HuggingFaceTB/SmolLM2-135M-Instruct
+- lora
+- sft
+- 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 0.19.1

checkpoint-1750/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M-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,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29890cb41f53e1f5482887af0134edb716f36f8815730374fb2f1b925064d9a
+size 7408448

checkpoint-1750/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-1750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65c11b1d3f2d4fb1504e154acce055e2a7db93ad5387c51d531bbf7cfa9d710
+size 14950667

checkpoint-1750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17985cc82964fd9666e7fe1dcf4731bf957632fcc5bba70edb8b1e8e7062c23d
+size 14645

checkpoint-1750/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f9facd156f274d558585c8beffeda844e22f840dd0b18f6d2c35abbad24bd0
+size 1383

checkpoint-1750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dfa19d0aafe75eafc37d0a43e7cd22139a91edaa29612fcf9645fd07e0b0caa
+size 1465

checkpoint-1750/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-1750/trainer_state.json

@@ -0,0 +1,461 @@
+{
+  "best_global_step": 1750,
+  "best_metric": 1.0002270936965942,
+  "best_model_checkpoint": "/content/work/checkpoints/checkpoint-1750",
+  "epoch": 0.15659955257270694,
+  "eval_steps": 250,
+  "global_step": 1750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.651820396184921,
+      "epoch": 0.0044742729306487695,
+      "grad_norm": 0.442557692527771,
+      "learning_rate": 9.8e-05,
+      "loss": 3.280501403808594,
+      "mean_token_accuracy": 0.4026365186274052,
+      "num_tokens": 130832.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.7069850754737854,
+      "epoch": 0.008948545861297539,
+      "grad_norm": 0.41429346799850464,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 2.666520690917969,
+      "mean_token_accuracy": 0.4684834870696068,
+      "num_tokens": 261056.0,
+      "step": 100
+    },
+    {
+      "entropy": 2.2673240077495573,
+      "epoch": 0.013422818791946308,
+      "grad_norm": 0.5210320353507996,
+      "learning_rate": 0.00019999760668343463,
+      "loss": 2.216226806640625,
+      "mean_token_accuracy": 0.5265978004038334,
+      "num_tokens": 391278.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.015401030778885,
+      "epoch": 0.017897091722595078,
+      "grad_norm": 0.5778504610061646,
+      "learning_rate": 0.00019999023048426428,
+      "loss": 1.9369810485839845,
+      "mean_token_accuracy": 0.5647277806699276,
+      "num_tokens": 522585.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.8627986872196198,
+      "epoch": 0.02237136465324385,
+      "grad_norm": 1.007725715637207,
+      "learning_rate": 0.00019997787077331475,
+      "loss": 1.7507638549804687,
+      "mean_token_accuracy": 0.5964532348513604,
+      "num_tokens": 653608.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.02237136465324385,
+      "eval_entropy": 1.7570730288181717,
+      "eval_loss": 1.663292407989502,
+      "eval_mean_token_accuracy": 0.6118261234789669,
+      "eval_num_tokens": 653608.0,
+      "eval_runtime": 231.339,
+      "eval_samples_per_second": 81.352,
+      "eval_steps_per_second": 10.171,
+      "step": 250
+    },
+    {
+      "entropy": 2.790428400039673,
+      "epoch": 0.026845637583892617,
+      "grad_norm": 0.3708084523677826,
+      "learning_rate": 0.0001999605281665939,
+      "loss": 2.9912448120117188,
+      "mean_token_accuracy": 0.4324784705042839,
+      "num_tokens": 129363.0,
+      "step": 300
+    },
+    {
+      "entropy": 2.5292794728279113,
+      "epoch": 0.03131991051454139,
+      "grad_norm": 0.504848301410675,
+      "learning_rate": 0.00019993820352845704,
+      "loss": 2.4664991760253905,
+      "mean_token_accuracy": 0.4925511160492897,
+      "num_tokens": 259293.0,
+      "step": 350
+    },
+    {
+      "entropy": 2.227354944348335,
+      "epoch": 0.035794183445190156,
+      "grad_norm": 0.47856974601745605,
+      "learning_rate": 0.00019991089797156378,
+      "loss": 2.183813171386719,
+      "mean_token_accuracy": 0.5316948869824409,
+      "num_tokens": 389682.0,
+      "step": 400
+    },
+    {
+      "entropy": 2.036482437252998,
+      "epoch": 0.040268456375838924,
+      "grad_norm": 0.6903976202011108,
+      "learning_rate": 0.00019987861285682276,
+      "loss": 1.9621383666992187,
+      "mean_token_accuracy": 0.5651841352880002,
+      "num_tokens": 521242.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.8924587434530258,
+      "epoch": 0.0447427293064877,
+      "grad_norm": 1.118765950202942,
+      "learning_rate": 0.00019984134979332365,
+      "loss": 1.7855641174316406,
+      "mean_token_accuracy": 0.5903938812017441,
+      "num_tokens": 650935.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.0447427293064877,
+      "eval_entropy": 1.7746684214838808,
+      "eval_loss": 1.6794711351394653,
+      "eval_mean_token_accuracy": 0.608957466980877,
+      "eval_num_tokens": 650935.0,
+      "eval_runtime": 223.3119,
+      "eval_samples_per_second": 84.277,
+      "eval_steps_per_second": 10.537,
+      "step": 500
+    },
+    {
+      "entropy": 1.7242326444387437,
+      "epoch": 0.049217002237136466,
+      "grad_norm": 0.7724726796150208,
+      "learning_rate": 0.00019979911063825706,
+      "loss": 1.6321617126464845,
+      "mean_token_accuracy": 0.6168254449963569,
+      "num_tokens": 781036.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.6163885343074798,
+      "epoch": 0.053691275167785234,
+      "grad_norm": 0.7551260590553284,
+      "learning_rate": 0.00019975189749682197,
+      "loss": 1.518061981201172,
+      "mean_token_accuracy": 0.6360310778021813,
+      "num_tokens": 911151.0,
+      "step": 600
+    },
+    {
+      "entropy": 1.5225655400753022,
+      "epoch": 0.058165548098434,
+      "grad_norm": 0.828091561794281,
+      "learning_rate": 0.00019969971272212067,
+      "loss": 1.42819580078125,
+      "mean_token_accuracy": 0.653648351430893,
+      "num_tokens": 1042446.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.458768675327301,
+      "epoch": 0.06263982102908278,
+      "grad_norm": 0.8204870223999023,
+      "learning_rate": 0.00019964255891504167,
+      "loss": 1.365126190185547,
+      "mean_token_accuracy": 0.6648625639081002,
+      "num_tokens": 1173209.0,
+      "step": 700
+    },
+    {
+      "entropy": 1.4292363184690475,
+      "epoch": 0.06711409395973154,
+      "grad_norm": 0.7856907844543457,
+      "learning_rate": 0.00019958043892412996,
+      "loss": 1.3346669006347656,
+      "mean_token_accuracy": 0.6717766770720481,
+      "num_tokens": 1303838.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.06711409395973154,
+      "eval_entropy": 1.397561838664352,
+      "eval_loss": 1.309268832206726,
+      "eval_mean_token_accuracy": 0.6755058221040864,
+      "eval_num_tokens": 1303838.0,
+      "eval_runtime": 222.6658,
+      "eval_samples_per_second": 84.521,
+      "eval_steps_per_second": 10.567,
+      "step": 750
+    },
+    {
+      "entropy": 1.3611693698167802,
+      "epoch": 0.07158836689038031,
+      "grad_norm": 0.8001652359962463,
+      "learning_rate": 0.00019951335584544508,
+      "loss": 1.2735862731933594,
+      "mean_token_accuracy": 0.6819746169447899,
+      "num_tokens": 1435829.0,
+      "step": 800
+    },
+    {
+      "entropy": 1.3399207586050033,
+      "epoch": 0.07606263982102908,
+      "grad_norm": 0.7596322894096375,
+      "learning_rate": 0.0001994413130224068,
+      "loss": 1.2516276550292968,
+      "mean_token_accuracy": 0.6869581064581871,
+      "num_tokens": 1566040.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.2940440517663956,
+      "epoch": 0.08053691275167785,
+      "grad_norm": 0.7932069897651672,
+      "learning_rate": 0.0001993643140456285,
+      "loss": 1.2029429626464845,
+      "mean_token_accuracy": 0.6938760960102082,
+      "num_tokens": 1697705.0,
+      "step": 900
+    },
+    {
+      "entropy": 1.2705094563961028,
+      "epoch": 0.08501118568232663,
+      "grad_norm": 0.7709512710571289,
+      "learning_rate": 0.0001992823627527381,
+      "loss": 1.1883332061767578,
+      "mean_token_accuracy": 0.6987017118930816,
+      "num_tokens": 1829189.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.257964146733284,
+      "epoch": 0.0894854586129754,
+      "grad_norm": 0.794852077960968,
+      "learning_rate": 0.00019919546322818703,
+      "loss": 1.1787289428710936,
+      "mean_token_accuracy": 0.7000182312726975,
+      "num_tokens": 1960750.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0894854586129754,
+      "eval_entropy": 1.254803528164581,
+      "eval_loss": 1.1655369997024536,
+      "eval_mean_token_accuracy": 0.7024362733705571,
+      "eval_num_tokens": 1960750.0,
+      "eval_runtime": 216.8801,
+      "eval_samples_per_second": 86.776,
+      "eval_steps_per_second": 10.849,
+      "step": 1000
+    },
+    {
+      "entropy": 1.231136965751648,
+      "epoch": 0.09395973154362416,
+      "grad_norm": 0.8129546046257019,
+      "learning_rate": 0.00019910361980304646,
+      "loss": 1.1491018676757812,
+      "mean_token_accuracy": 0.7032070714235306,
+      "num_tokens": 2090761.0,
+      "step": 1050
+    },
+    {
+      "entropy": 1.2148332485556603,
+      "epoch": 0.09843400447427293,
+      "grad_norm": 0.7990450859069824,
+      "learning_rate": 0.00019900683705479147,
+      "loss": 1.1374418640136719,
+      "mean_token_accuracy": 0.7060695806145668,
+      "num_tokens": 2222147.0,
+      "step": 1100
+    },
+    {
+      "entropy": 1.208145708143711,
+      "epoch": 0.1029082774049217,
+      "grad_norm": 0.7982318997383118,
+      "learning_rate": 0.00019890511980707296,
+      "loss": 1.1248248291015626,
+      "mean_token_accuracy": 0.7086962693929673,
+      "num_tokens": 2353159.0,
+      "step": 1150
+    },
+    {
+      "entropy": 1.1811901706457137,
+      "epoch": 0.10738255033557047,
+      "grad_norm": 0.8226000666618347,
+      "learning_rate": 0.00019879847312947725,
+      "loss": 1.1086264038085938,
+      "mean_token_accuracy": 0.7128409042954444,
+      "num_tokens": 2484594.0,
+      "step": 1200
+    },
+    {
+      "entropy": 1.1749517038464545,
+      "epoch": 0.11185682326621924,
+      "grad_norm": 0.8299795985221863,
+      "learning_rate": 0.00019868690233727337,
+      "loss": 1.1017638397216798,
+      "mean_token_accuracy": 0.7125484347343445,
+      "num_tokens": 2615149.0,
+      "step": 1250
+    },
+    {
+      "epoch": 0.11185682326621924,
+      "eval_entropy": 1.1516895890995842,
+      "eval_loss": 1.0878593921661377,
+      "eval_mean_token_accuracy": 0.7167255235032431,
+      "eval_num_tokens": 2615149.0,
+      "eval_runtime": 222.8313,
+      "eval_samples_per_second": 84.458,
+      "eval_steps_per_second": 10.56,
+      "step": 1250
+    },
+    {
+      "entropy": 1.1464633461833,
+      "epoch": 0.116331096196868,
+      "grad_norm": 0.7202898859977722,
+      "learning_rate": 0.00019857041299114808,
+      "loss": 1.0679573822021484,
+      "mean_token_accuracy": 0.7206197878718377,
+      "num_tokens": 2746727.0,
+      "step": 1300
+    },
+    {
+      "entropy": 1.1379328405857085,
+      "epoch": 0.12080536912751678,
+      "grad_norm": 0.8328574895858765,
+      "learning_rate": 0.00019844901089692893,
+      "loss": 1.0696997833251953,
+      "mean_token_accuracy": 0.7188817489147187,
+      "num_tokens": 2877531.0,
+      "step": 1350
+    },
+    {
+      "entropy": 1.131972982287407,
+      "epoch": 0.12527964205816555,
+      "grad_norm": 0.8093060851097107,
+      "learning_rate": 0.00019832270210529466,
+      "loss": 1.058395538330078,
+      "mean_token_accuracy": 0.7203070876002312,
+      "num_tokens": 3008803.0,
+      "step": 1400
+    },
+    {
+      "entropy": 1.12234389513731,
+      "epoch": 0.1297539149888143,
+      "grad_norm": 0.742972195148468,
+      "learning_rate": 0.00019819149291147383,
+      "loss": 1.0534366607666015,
+      "mean_token_accuracy": 0.7222018876671791,
+      "num_tokens": 3137965.0,
+      "step": 1450
+    },
+    {
+      "entropy": 1.1006340074539185,
+      "epoch": 0.1342281879194631,
+      "grad_norm": 0.7162765860557556,
+      "learning_rate": 0.00019805538985493096,
+      "loss": 1.028353729248047,
+      "mean_token_accuracy": 0.7277802819013596,
+      "num_tokens": 3269555.0,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1342281879194631,
+      "eval_entropy": 1.1096204250759638,
+      "eval_loss": 1.0371356010437012,
+      "eval_mean_token_accuracy": 0.7253242311354045,
+      "eval_num_tokens": 3269555.0,
+      "eval_runtime": 211.312,
+      "eval_samples_per_second": 89.063,
+      "eval_steps_per_second": 11.135,
+      "step": 1500
+    },
+    {
+      "entropy": 1.0943984407186509,
+      "epoch": 0.13870246085011187,
+      "grad_norm": 0.737978458404541,
+      "learning_rate": 0.00019791439971904054,
+      "loss": 1.0289594268798827,
+      "mean_token_accuracy": 0.7275757938623428,
+      "num_tokens": 3400488.0,
+      "step": 1550
+    },
+    {
+      "entropy": 1.0984211310744285,
+      "epoch": 0.14317673378076062,
+      "grad_norm": 0.7294973731040955,
+      "learning_rate": 0.00019776852953074916,
+      "loss": 1.0274142456054687,
+      "mean_token_accuracy": 0.7268362134695053,
+      "num_tokens": 3531555.0,
+      "step": 1600
+    },
+    {
+      "entropy": 1.08658686876297,
+      "epoch": 0.1476510067114094,
+      "grad_norm": 0.7807707190513611,
+      "learning_rate": 0.00019761778656022505,
+      "loss": 1.0233070373535156,
+      "mean_token_accuracy": 0.7277577331662178,
+      "num_tokens": 3662724.0,
+      "step": 1650
+    },
+    {
+      "entropy": 1.0737271896004676,
+      "epoch": 0.15212527964205816,
+      "grad_norm": 0.7554745078086853,
+      "learning_rate": 0.0001974621783204959,
+      "loss": 1.007247314453125,
+      "mean_token_accuracy": 0.7310737103223801,
+      "num_tokens": 3792301.0,
+      "step": 1700
+    },
+    {
+      "entropy": 1.0761739972233773,
+      "epoch": 0.15659955257270694,
+      "grad_norm": 0.7434770464897156,
+      "learning_rate": 0.0001973017125670744,
+      "loss": 1.010123519897461,
+      "mean_token_accuracy": 0.7281501796841622,
+      "num_tokens": 3923244.0,
+      "step": 1750
+    },
+    {
+      "epoch": 0.15659955257270694,
+      "eval_entropy": 1.0884551091291426,
+      "eval_loss": 1.0002270936965942,
+      "eval_mean_token_accuracy": 0.7324172373381362,
+      "eval_num_tokens": 3923244.0,
+      "eval_runtime": 222.3676,
+      "eval_samples_per_second": 84.635,
+      "eval_steps_per_second": 10.582,
+      "step": 1750
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 22350,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3799475352585216.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104f85937520e28216c832e9214554f46be2b0495d85b4111df01a6c6a97996b
+size 5649