From fd4beaa5e37959ca12d503eea1cd02a1aebfaf8c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 8 Jun 2026 14:29:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: PygmalionAI/metharme-1.3b Source: Original Platform --- .gitattributes | 51 +++ README.md | 108 +++++++ config.json | 26 ++ configuration.json | 1 + generation_config.json | 6 + model.safetensors | 3 + pytorch_model.bin | 3 + special_tokens_map.json | 28 ++ tokenizer.json | 3 + tokenizer_config.json | 10 + trainer_state.json | 691 ++++++++++++++++++++++++++++++++++++++++ 11 files changed, 930 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 pytorch_model.bin create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 trainer_state.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..18ef366 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,51 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text + +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text +pytorch_model.bin filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..ed97e37 --- /dev/null +++ b/README.md @@ -0,0 +1,108 @@ +--- +license: apache-2.0 +language: +- en +--- +

Metharme 1.3B

+

An instruction-tuned Pythia biased towards fiction writing and conversation.

+ +## Model Details + +Metharme 1.3B is an instruct model based on EleutherAI's [Pythia 1.4B Deduped](https://huggingface.co/EleutherAI/pythia-1.4b-deduped). + +This is an experiment to try and get a model that is usable for conversation, roleplaying and storywriting, but which can be guided using natural language like other instruct models. See the [prompting](#prompting) section below for examples. + +It was trained by doing supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories and conversations with synthetically generated instructions attached. + +## Prompting + +The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`. + +The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history. + +### Prompting example + +Here's a concrete example. Let's say you have the following system prompt: + +> This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn. + +And the user has typed in the following message: + +> Start! + +To perform inference against the model, the prompt should be formatted like this: + +``` +<|system|>This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.<|user|>Start!<|model|> +``` + +The model might generate something like: + +> You are standing in front of an old, abandoned house. The windows are boarded up, and there's no sign of life around it. As you approach, you notice a strange feeling emanating from within. Suddenly, you hear a voice calling out to you... 'Come inside!' +> +> - Go inside the house. +> - Ignore the call and move away. +> - Run as fast as you can. + +It will automatically emit an end-of-text token (`<|endoftext|>`) when it judges that the response is complete. + +Pretend then that the user has replied with `go inside`. The next prompt should then be: + +``` +<|system|>This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.<|user|>Start!<|model|>You are standing in front of an old, abandoned house. The windows are boarded up, and there's no sign of life around it. As you approach, you notice a strange feeling emanating from within. Suddenly, you hear a voice calling out to you... 'Come inside!' + +- Go inside the house. +- Ignore the call and move away. +- Run as fast as you can.<|user|>go inside<|model|> +``` + +Which might generate something like: + +> You enter the house, and immediately, a wave of unsettling energy washes over you. Your senses seem heightened, but your mind feels foggy. A figure appears before you - a tall man with piercing eyes. He speaks to you in a language you don't understand. +> +> - Ask him what he wants. +> - Attack him. +> - Run away. + +Same process applies. Usually, it is best to do a sliding window over the user and model turns, but keep the system prompt fixed at the start of the context window. + +## Evaluation Metrics +The model was evaluated using EleutherAI's [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) test suite. It was evaluated on the following tasks: + + +| Task |Version| Metric |Value | |Stderr| +|-------------|------:|--------|-----:|---|-----:| +|anli_r1 | 0|acc |0.3430|± |0.0150| +|anli_r2 | 0|acc |0.3330|± |0.0149| +|anli_r3 | 0|acc |0.3350|± |0.0136| +|arc_challenge| 0|acc |0.2747|± |0.0130| +| | |acc_norm|0.3114|± |0.0135| +|arc_easy | 0|acc |0.6237|± |0.0099| +| | |acc_norm|0.5631|± |0.0102| +|boolq | 1|acc |0.6214|± |0.0085| +|cb | 1|acc |0.1964|± |0.0536| +| | |f1 |0.1712| | | +|hellaswag | 0|acc |0.4295|± |0.0049| +| | |acc_norm|0.5496|± |0.0050| +|openbookqa | 0|acc |0.2360|± |0.0190| +| | |acc_norm|0.3360|± |0.0211| +|piqa | 0|acc |0.7285|± |0.0104| +| | |acc_norm|0.7318|± |0.0103| +|rte | 0|acc |0.5235|± |0.0301| +|truthfulqa_mc| 1|mc1 |0.2436|± |0.0150| +| | |mc2 |0.3791|± |0.0142| +|wic | 0|acc |0.5000|± |0.0198| +|winogrande | 0|acc |0.5675|± |0.0139| +|wsc | 0|acc |0.3654|± |0.0474| + + +Illustrated comparison of Metharme-1.3B's performance on benchmarks to Pygmalion-6B, Metharme-7B, and [RedPajama-INCITE-Chat-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1): +![Eval](https://i.imgur.com/hW8Owbc.png) + +## Limitations and biases + +Due to being a smaller model than Metharme 7B and 13B, the coherency will very likely suffer. + +The intended use-case for this model is fictional writing for entertainment purposes. Any other sort of usage is out of scope. + +As such, it was **not** fine-tuned to be safe and harmless: the base model _and_ this fine-tune have been trained on data known to contain profanity and texts that are lewd or otherwise offensive. It may produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. Outputs might often be factually wrong or misleading. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..0a45cdf --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "/home/alpin/ramdisk/trained-models/metharme-1.3b", + "architectures": [ + "GPTNeoXForCausalLM" + ], + "bos_token_id": 0, + "classifier_dropout": 0.1, + "eos_token_id": 0, + "hidden_act": "gelu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 16, + "num_hidden_layers": 24, + "rotary_emb_base": 10000, + "rotary_pct": 0.25, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.30.0.dev0", + "use_cache": true, + "use_parallel_residual": true, + "vocab_size": 50304 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..df41ce5 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 0, + "transformers_version": "4.30.0.dev0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..90875fa --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9cc9d21a1036f9efd2f258104254cfe0b5d6cd569540cdaa8b928a9f19a7c6a +size 2930003008 diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..148720a --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf01554e4d49a3029c6c61e1a8d5938511dce9da4b8f1d278e8c16ce00bd946 +size 2930083453 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..c5cd16a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + { + "content": "<|system|>", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": false + }, + { + "content": "<|user|>", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": false + }, + { + "content": "<|model|>", + "lstrip": true, + "normalized": false, + "rstrip": true, + "single_word": false + } + ], + "bos_token": "<|endoftext|>", + "eos_token": "<|endoftext|>", + "unk_token": "<|endoftext|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..60e60f2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9778b932320ef907cb0b3179c74fdaa73fc8e32d2bb436e15a87457f82121162 +size 2114287 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..57b2717 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,10 @@ +{ + "add_prefix_space": false, + "bos_token": "<|endoftext|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|endoftext|>", + "model_max_length": 1000000000000000019884624838656, + "padding_side": "right", + "tokenizer_class": "GPTNeoXTokenizer", + "unk_token": "<|endoftext|>" +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..eae9a20 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,691 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.998109640831758, + "global_step": 99, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.01, + "learning_rate": 6.25e-07, + "loss": 0.2195, + "step": 1 + }, + { + "epoch": 0.02, + "learning_rate": 1.25e-06, + "loss": 0.2205, + "step": 2 + }, + { + "epoch": 0.03, + "learning_rate": 1.8750000000000003e-06, + "loss": 0.22, + "step": 3 + }, + { + "epoch": 0.04, + "learning_rate": 2.5e-06, + "loss": 0.2206, + "step": 4 + }, + { + "epoch": 0.05, + "learning_rate": 3.125e-06, + "loss": 0.2181, + "step": 5 + }, + { + "epoch": 0.06, + "learning_rate": 3.7500000000000005e-06, + "loss": 0.2178, + "step": 6 + }, + { + "epoch": 0.07, + "learning_rate": 4.3750000000000005e-06, + "loss": 0.218, + "step": 7 + }, + { + "epoch": 0.08, + "learning_rate": 5e-06, + "loss": 0.2159, + "step": 8 + }, + { + "epoch": 0.09, + "learning_rate": 5.625e-06, + "loss": 0.2109, + "step": 9 + }, + { + "epoch": 0.1, + "learning_rate": 6.25e-06, + "loss": 0.2079, + "step": 10 + }, + { + "epoch": 0.1, + "eval_loss": 0.20295506715774536, + "eval_runtime": 7.6664, + "eval_samples_per_second": 124.439, + "eval_steps_per_second": 15.653, + "step": 10 + }, + { + "epoch": 0.11, + "learning_rate": 6.875e-06, + "loss": 0.2063, + "step": 11 + }, + { + "epoch": 0.12, + "learning_rate": 7.500000000000001e-06, + "loss": 0.201, + "step": 12 + }, + { + "epoch": 0.13, + "learning_rate": 8.125000000000001e-06, + "loss": 0.2004, + "step": 13 + }, + { + "epoch": 0.14, + "learning_rate": 8.750000000000001e-06, + "loss": 0.196, + "step": 14 + }, + { + "epoch": 0.15, + "learning_rate": 9.375000000000001e-06, + "loss": 0.1929, + "step": 15 + }, + { + "epoch": 0.16, + "learning_rate": 1e-05, + "loss": 0.1892, + "step": 16 + }, + { + "epoch": 0.17, + "learning_rate": 9.681174353198687e-06, + "loss": 0.1894, + "step": 17 + }, + { + "epoch": 0.18, + "learning_rate": 8.765357330018056e-06, + "loss": 0.1845, + "step": 18 + }, + { + "epoch": 0.19, + "learning_rate": 7.369343312364994e-06, + "loss": 0.1832, + "step": 19 + }, + { + "epoch": 0.2, + "learning_rate": 5.671166329088278e-06, + "loss": 0.1823, + "step": 20 + }, + { + "epoch": 0.2, + "eval_loss": 0.18013226985931396, + "eval_runtime": 7.9493, + "eval_samples_per_second": 120.011, + "eval_steps_per_second": 15.096, + "step": 20 + }, + { + "epoch": 0.21, + "learning_rate": 3.887395330218429e-06, + "loss": 0.182, + "step": 21 + }, + { + "epoch": 0.22, + "learning_rate": 2.245515092739488e-06, + "loss": 0.1818, + "step": 22 + }, + { + "epoch": 0.23, + "learning_rate": 9.549150281252633e-07, + "loss": 0.1828, + "step": 23 + }, + { + "epoch": 0.24, + "learning_rate": 1.801856965207338e-07, + "loss": 0.1803, + "step": 24 + }, + { + "epoch": 0.25, + "learning_rate": 2.012853002380466e-08, + "loss": 0.181, + "step": 25 + }, + { + "epoch": 0.26, + "learning_rate": 4.951556604879043e-07, + "loss": 0.1796, + "step": 26 + }, + { + "epoch": 0.27, + "learning_rate": 1.5446867550656763e-06, + "loss": 0.1838, + "step": 27 + }, + { + "epoch": 0.28, + "learning_rate": 3.0348748417303813e-06, + "loss": 0.1815, + "step": 28 + }, + { + "epoch": 0.29, + "learning_rate": 4.775675848247425e-06, + "loss": 0.1799, + "step": 29 + }, + { + "epoch": 0.3, + "learning_rate": 6.545084971874737e-06, + "loss": 0.1816, + "step": 30 + }, + { + "epoch": 0.3, + "eval_loss": 0.17906256020069122, + "eval_runtime": 7.8801, + "eval_samples_per_second": 121.065, + "eval_steps_per_second": 15.228, + "step": 30 + }, + { + "epoch": 0.31, + "learning_rate": 8.117449009293668e-06, + "loss": 0.18, + "step": 31 + }, + { + "epoch": 0.32, + "learning_rate": 9.292243968009332e-06, + "loss": 0.1797, + "step": 32 + }, + { + "epoch": 0.33, + "learning_rate": 9.91964794299315e-06, + "loss": 0.1809, + "step": 33 + }, + { + "epoch": 0.34, + "learning_rate": 9.91964794299315e-06, + "loss": 0.1782, + "step": 34 + }, + { + "epoch": 0.35, + "learning_rate": 9.292243968009333e-06, + "loss": 0.1781, + "step": 35 + }, + { + "epoch": 0.36, + "learning_rate": 8.11744900929367e-06, + "loss": 0.1759, + "step": 36 + }, + { + "epoch": 0.37, + "learning_rate": 6.545084971874739e-06, + "loss": 0.1752, + "step": 37 + }, + { + "epoch": 0.38, + "learning_rate": 4.775675848247427e-06, + "loss": 0.1786, + "step": 38 + }, + { + "epoch": 0.39, + "learning_rate": 3.0348748417303834e-06, + "loss": 0.1757, + "step": 39 + }, + { + "epoch": 0.4, + "learning_rate": 1.544686755065678e-06, + "loss": 0.1755, + "step": 40 + }, + { + "epoch": 0.4, + "eval_loss": 0.17424167692661285, + "eval_runtime": 7.7899, + "eval_samples_per_second": 122.466, + "eval_steps_per_second": 15.405, + "step": 40 + }, + { + "epoch": 0.41, + "learning_rate": 4.951556604879054e-07, + "loss": 0.1749, + "step": 41 + }, + { + "epoch": 0.42, + "learning_rate": 2.0128530023805216e-08, + "loss": 0.1763, + "step": 42 + }, + { + "epoch": 0.43, + "learning_rate": 1.8018569652073326e-07, + "loss": 0.1761, + "step": 43 + }, + { + "epoch": 0.44, + "learning_rate": 9.549150281252616e-07, + "loss": 0.1782, + "step": 44 + }, + { + "epoch": 0.45, + "learning_rate": 2.245515092739486e-06, + "loss": 0.176, + "step": 45 + }, + { + "epoch": 0.46, + "learning_rate": 3.887395330218426e-06, + "loss": 0.1769, + "step": 46 + }, + { + "epoch": 0.47, + "learning_rate": 5.671166329088275e-06, + "loss": 0.1768, + "step": 47 + }, + { + "epoch": 0.48, + "learning_rate": 7.369343312364992e-06, + "loss": 0.1751, + "step": 48 + }, + { + "epoch": 0.49, + "learning_rate": 8.765357330018054e-06, + "loss": 0.1744, + "step": 49 + }, + { + "epoch": 0.5, + "learning_rate": 9.681174353198685e-06, + "loss": 0.1751, + "step": 50 + }, + { + "epoch": 0.5, + "eval_loss": 0.17338795959949493, + "eval_runtime": 7.6323, + "eval_samples_per_second": 124.995, + "eval_steps_per_second": 15.723, + "step": 50 + }, + { + "epoch": 0.51, + "learning_rate": 1e-05, + "loss": 0.1758, + "step": 51 + }, + { + "epoch": 0.52, + "learning_rate": 9.68117435319869e-06, + "loss": 0.1768, + "step": 52 + }, + { + "epoch": 0.53, + "learning_rate": 8.765357330018058e-06, + "loss": 0.1752, + "step": 53 + }, + { + "epoch": 0.54, + "learning_rate": 7.369343312365004e-06, + "loss": 0.1746, + "step": 54 + }, + { + "epoch": 0.55, + "learning_rate": 5.6711663290882805e-06, + "loss": 0.1722, + "step": 55 + }, + { + "epoch": 0.56, + "learning_rate": 3.887395330218431e-06, + "loss": 0.1735, + "step": 56 + }, + { + "epoch": 0.57, + "learning_rate": 2.24551509273949e-06, + "loss": 0.1727, + "step": 57 + }, + { + "epoch": 0.58, + "learning_rate": 9.549150281252646e-07, + "loss": 0.1713, + "step": 58 + }, + { + "epoch": 0.59, + "learning_rate": 1.8018569652073214e-07, + "loss": 0.1732, + "step": 59 + }, + { + "epoch": 0.6, + "learning_rate": 2.012853002380466e-08, + "loss": 0.1738, + "step": 60 + }, + { + "epoch": 0.6, + "eval_loss": 0.1722276508808136, + "eval_runtime": 7.8157, + "eval_samples_per_second": 122.061, + "eval_steps_per_second": 15.354, + "step": 60 + }, + { + "epoch": 0.61, + "learning_rate": 4.951556604879032e-07, + "loss": 0.1744, + "step": 61 + }, + { + "epoch": 0.63, + "learning_rate": 1.5446867550656746e-06, + "loss": 0.1741, + "step": 62 + }, + { + "epoch": 0.64, + "learning_rate": 3.034874841730379e-06, + "loss": 0.1749, + "step": 63 + }, + { + "epoch": 0.65, + "learning_rate": 4.775675848247422e-06, + "loss": 0.1745, + "step": 64 + }, + { + "epoch": 0.66, + "learning_rate": 6.545084971874734e-06, + "loss": 0.1751, + "step": 65 + }, + { + "epoch": 0.67, + "learning_rate": 8.117449009293666e-06, + "loss": 0.1751, + "step": 66 + }, + { + "epoch": 0.68, + "learning_rate": 9.292243968009328e-06, + "loss": 0.1757, + "step": 67 + }, + { + "epoch": 0.69, + "learning_rate": 9.91964794299315e-06, + "loss": 0.174, + "step": 68 + }, + { + "epoch": 0.7, + "learning_rate": 9.91964794299315e-06, + "loss": 0.1723, + "step": 69 + }, + { + "epoch": 0.71, + "learning_rate": 9.292243968009333e-06, + "loss": 0.1734, + "step": 70 + }, + { + "epoch": 0.71, + "eval_loss": 0.17138364911079407, + "eval_runtime": 7.8154, + "eval_samples_per_second": 122.067, + "eval_steps_per_second": 15.354, + "step": 70 + }, + { + "epoch": 0.72, + "learning_rate": 8.117449009293671e-06, + "loss": 0.1725, + "step": 71 + }, + { + "epoch": 0.73, + "learning_rate": 6.545084971874741e-06, + "loss": 0.1738, + "step": 72 + }, + { + "epoch": 0.74, + "learning_rate": 4.77567584824743e-06, + "loss": 0.1728, + "step": 73 + }, + { + "epoch": 0.75, + "learning_rate": 3.034874841730386e-06, + "loss": 0.1723, + "step": 74 + }, + { + "epoch": 0.76, + "learning_rate": 1.5446867550656797e-06, + "loss": 0.1757, + "step": 75 + }, + { + "epoch": 0.77, + "learning_rate": 4.951556604879059e-07, + "loss": 0.174, + "step": 76 + }, + { + "epoch": 0.78, + "learning_rate": 2.0128530023805216e-08, + "loss": 0.1739, + "step": 77 + }, + { + "epoch": 0.79, + "learning_rate": 1.8018569652073214e-07, + "loss": 0.1728, + "step": 78 + }, + { + "epoch": 0.8, + "learning_rate": 9.549150281252605e-07, + "loss": 0.1723, + "step": 79 + }, + { + "epoch": 0.81, + "learning_rate": 2.2455150927394835e-06, + "loss": 0.1727, + "step": 80 + }, + { + "epoch": 0.81, + "eval_loss": 0.17097879946231842, + "eval_runtime": 7.8584, + "eval_samples_per_second": 121.399, + "eval_steps_per_second": 15.27, + "step": 80 + }, + { + "epoch": 0.82, + "learning_rate": 3.8873953302184244e-06, + "loss": 0.1725, + "step": 81 + }, + { + "epoch": 0.83, + "learning_rate": 5.671166329088274e-06, + "loss": 0.1725, + "step": 82 + }, + { + "epoch": 0.84, + "learning_rate": 7.369343312364989e-06, + "loss": 0.1728, + "step": 83 + }, + { + "epoch": 0.85, + "learning_rate": 8.765357330018051e-06, + "loss": 0.1724, + "step": 84 + }, + { + "epoch": 0.86, + "learning_rate": 9.681174353198685e-06, + "loss": 0.171, + "step": 85 + }, + { + "epoch": 0.87, + "learning_rate": 1e-05, + "loss": 0.1717, + "step": 86 + }, + { + "epoch": 0.88, + "learning_rate": 9.681174353198689e-06, + "loss": 0.174, + "step": 87 + }, + { + "epoch": 0.89, + "learning_rate": 8.76535733001807e-06, + "loss": 0.1716, + "step": 88 + }, + { + "epoch": 0.9, + "learning_rate": 7.369343312364998e-06, + "loss": 0.1715, + "step": 89 + }, + { + "epoch": 0.91, + "learning_rate": 5.671166329088282e-06, + "loss": 0.1712, + "step": 90 + }, + { + "epoch": 0.91, + "eval_loss": 0.17013530433177948, + "eval_runtime": 7.7133, + "eval_samples_per_second": 123.683, + "eval_steps_per_second": 15.558, + "step": 90 + }, + { + "epoch": 0.92, + "learning_rate": 3.887395330218433e-06, + "loss": 0.1729, + "step": 91 + }, + { + "epoch": 0.93, + "learning_rate": 2.245515092739507e-06, + "loss": 0.1731, + "step": 92 + }, + { + "epoch": 0.94, + "learning_rate": 9.549150281252557e-07, + "loss": 0.1726, + "step": 93 + }, + { + "epoch": 0.95, + "learning_rate": 1.8018569652073492e-07, + "loss": 0.1724, + "step": 94 + }, + { + "epoch": 0.96, + "learning_rate": 2.0128530023804104e-08, + "loss": 0.1695, + "step": 95 + }, + { + "epoch": 0.97, + "learning_rate": 4.951556604879021e-07, + "loss": 0.1711, + "step": 96 + }, + { + "epoch": 0.98, + "learning_rate": 1.5446867550656852e-06, + "loss": 0.1726, + "step": 97 + }, + { + "epoch": 0.99, + "learning_rate": 3.034874841730377e-06, + "loss": 0.1722, + "step": 98 + }, + { + "epoch": 1.0, + "learning_rate": 4.7756758482474195e-06, + "loss": 0.171, + "step": 99 + }, + { + "epoch": 1.0, + "step": 99, + "total_flos": 6.416685198968095e+18, + "train_loss": 0.18111299429879044, + "train_runtime": 16732.1456, + "train_samples_per_second": 48.562, + "train_steps_per_second": 0.006 + } + ], + "max_steps": 99, + "num_train_epochs": 1, + "total_flos": 6.416685198968095e+18, + "trial_name": null, + "trial_params": null +}