Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: HuggingFaceTB/SmolLM2-360M
+library_name: transformers
+model_name: smollm2-360M-sft_SmallThoughts
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for smollm2-360M-sft_SmallThoughts
+
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="assskelad/smollm2-360M-sft_SmallThoughts", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.2
+- Transformers: 4.49.0
+- Pytorch: 2.6.0+cu126
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin GallouГ©dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 6258600061401600.0,
+    "train_loss": 0.5569522526019659,
+    "train_runtime": 905.7572,
+    "train_samples": 2500,
+    "train_samples_per_second": 5.52,
+    "train_steps_per_second": 0.344
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "HuggingFaceTB/SmolLM2-360M",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea50847015dbad7e4352cdf83beb1af3f67f0b33d3629bad0ba0b3a21550548
+size 723674912

runs/Mar10_14-43-34_DESKTOP-T04P4ED/events.out.tfevents.1741607024.DESKTOP-T04P4ED.14000.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79b53b014e21a281ce33dd118065a457a17b0d381eb8d9cd4add4ff01e92145
+size 21839

runs/Mar10_17-22-19_DESKTOP-T04P4ED/events.out.tfevents.1741616667.DESKTOP-T04P4ED.16240.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08743dd8fa8cce7d0bcf33c49ef6b8378aebffa192aedd398acf7f57b7e5c8e4
+size 6367

runs/Mar10_17-26-23_DESKTOP-T04P4ED/events.out.tfevents.1741616831.DESKTOP-T04P4ED.15436.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd88bcbf7543100593252c27bd30cc5c466c576145bf2d436366ed66a0e9e601
+size 15914

runs/Mar10_17-48-12_DESKTOP-T04P4ED/events.out.tfevents.1741618129.DESKTOP-T04P4ED.11860.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b821f1bb0f921f9d2487120fd3cf900df1a4ad157ce038461c526baec923fab
+size 15928

special_tokens_map.json

@@ -0,0 +1,43 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,170 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 6258600061401600.0,
+    "train_loss": 0.5569522526019659,
+    "train_runtime": 905.7572,
+    "train_samples": 2500,
+    "train_samples_per_second": 5.52,
+    "train_steps_per_second": 0.344
+}

trainer_state.json

@@ -0,0 +1,565 @@
+{
+  "best_metric": 0.8502547144889832,
+  "best_model_checkpoint": "data/smollm2-1.7B-sft\\checkpoint-142",
+  "epoch": 1.9984,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.035398230088495575,
+      "grad_norm": 8.5625,
+      "learning_rate": 0.0001724137931034483,
+      "loss": 2.2924,
+      "mean_token_accuracy": 0.5223099514842033,
+      "step": 5
+    },
+    {
+      "epoch": 0.07079646017699115,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.0003448275862068966,
+      "loss": 1.07,
+      "mean_token_accuracy": 0.7215210050344467,
+      "step": 10
+    },
+    {
+      "epoch": 0.10619469026548672,
+      "grad_norm": 0.88671875,
+      "learning_rate": 0.0005172413793103448,
+      "loss": 0.8398,
+      "mean_token_accuracy": 0.7689230531454087,
+      "step": 15
+    },
+    {
+      "epoch": 0.1415929203539823,
+      "grad_norm": 0.96484375,
+      "learning_rate": 0.0006896551724137932,
+      "loss": 0.8466,
+      "mean_token_accuracy": 0.7690734684467315,
+      "step": 20
+    },
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.0008620689655172414,
+      "loss": 0.8315,
+      "mean_token_accuracy": 0.7698834031820297,
+      "step": 25
+    },
+    {
+      "epoch": 0.21238938053097345,
+      "grad_norm": 0.8984375,
+      "learning_rate": 0.000999961452773888,
+      "loss": 0.8657,
+      "mean_token_accuracy": 0.7694115966558457,
+      "step": 30
+    },
+    {
+      "epoch": 0.24778761061946902,
+      "grad_norm": 0.89453125,
+      "learning_rate": 0.0009986129238305635,
+      "loss": 0.9508,
+      "mean_token_accuracy": 0.7505242705345154,
+      "step": 35
+    },
+    {
+      "epoch": 0.2831858407079646,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.0009953429730181654,
+      "loss": 0.9422,
+      "mean_token_accuracy": 0.7508314579725266,
+      "step": 40
+    },
+    {
+      "epoch": 0.3185840707964602,
+      "grad_norm": 0.84765625,
+      "learning_rate": 0.0009901642012034213,
+      "loss": 0.9568,
+      "mean_token_accuracy": 0.7477447241544724,
+      "step": 45
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 0.75390625,
+      "learning_rate": 0.0009830965649597454,
+      "loss": 0.9577,
+      "mean_token_accuracy": 0.7479827046394348,
+      "step": 50
+    },
+    {
+      "epoch": 0.3893805309734513,
+      "grad_norm": 0.69921875,
+      "learning_rate": 0.0009741672996639047,
+      "loss": 0.9318,
+      "mean_token_accuracy": 0.7587000578641891,
+      "step": 55
+    },
+    {
+      "epoch": 0.4247787610619469,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.0009634108145435665,
+      "loss": 0.9259,
+      "mean_token_accuracy": 0.7593102544546128,
+      "step": 60
+    },
+    {
+      "epoch": 0.46017699115044247,
+      "grad_norm": 0.7109375,
+      "learning_rate": 0.0009508685600801703,
+      "loss": 0.8877,
+      "mean_token_accuracy": 0.768345057964325,
+      "step": 65
+    },
+    {
+      "epoch": 0.49557522123893805,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.0009365888682780861,
+      "loss": 0.9253,
+      "mean_token_accuracy": 0.7625227481126785,
+      "step": 70
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 0.61328125,
+      "learning_rate": 0.0009206267664155906,
+      "loss": 0.912,
+      "mean_token_accuracy": 0.7615309178829193,
+      "step": 75
+    },
+    {
+      "epoch": 0.5663716814159292,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0009030437649953789,
+      "loss": 0.9242,
+      "mean_token_accuracy": 0.7563268959522247,
+      "step": 80
+    },
+    {
+      "epoch": 0.6017699115044248,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0008839076207117484,
+      "loss": 0.8975,
+      "mean_token_accuracy": 0.7675409287214279,
+      "step": 85
+    },
+    {
+      "epoch": 0.6371681415929203,
+      "grad_norm": 0.60546875,
+      "learning_rate": 0.0008632920753478719,
+      "loss": 0.8901,
+      "mean_token_accuracy": 0.7678898781538009,
+      "step": 90
+    },
+    {
+      "epoch": 0.672566371681416,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.0008412765716093271,
+      "loss": 0.8868,
+      "mean_token_accuracy": 0.7646951735019684,
+      "step": 95
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0008179459469889268,
+      "loss": 0.9314,
+      "mean_token_accuracy": 0.7571736365556717,
+      "step": 100
+    },
+    {
+      "epoch": 0.7433628318584071,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0007933901068425538,
+      "loss": 0.8961,
+      "mean_token_accuracy": 0.7628611207008362,
+      "step": 105
+    },
+    {
+      "epoch": 0.7787610619469026,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.000767703677935813,
+      "loss": 0.891,
+      "mean_token_accuracy": 0.7617514222860337,
+      "step": 110
+    },
+    {
+      "epoch": 0.8141592920353983,
+      "grad_norm": 0.69140625,
+      "learning_rate": 0.000740985643796569,
+      "loss": 0.9057,
+      "mean_token_accuracy": 0.7621735870838166,
+      "step": 115
+    },
+    {
+      "epoch": 0.8495575221238938,
+      "grad_norm": 0.61328125,
+      "learning_rate": 0.0007133389632785542,
+      "loss": 0.8874,
+      "mean_token_accuracy": 0.7660593271255494,
+      "step": 120
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.0006848701738059226,
+      "loss": 0.8441,
+      "mean_token_accuracy": 0.7740032315254212,
+      "step": 125
+    },
+    {
+      "epoch": 0.9203539823008849,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.0006556889808276594,
+      "loss": 0.8767,
+      "mean_token_accuracy": 0.7661084860563279,
+      "step": 130
+    },
+    {
+      "epoch": 0.9557522123893806,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.0006259078350639009,
+      "loss": 0.8962,
+      "mean_token_accuracy": 0.7660992830991745,
+      "step": 135
+    },
+    {
+      "epoch": 0.9911504424778761,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.0005956414991732583,
+      "loss": 0.8515,
+      "mean_token_accuracy": 0.7711150646209717,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8502547144889832,
+      "eval_mean_token_accuracy": 0.7765891637120929,
+      "eval_runtime": 2.1657,
+      "eval_samples_per_second": 54.949,
+      "eval_steps_per_second": 13.853,
+      "step": 142
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.000649163469284578,
+      "loss": 1.5121,
+      "mean_token_accuracy": 0.6798420002063116,
+      "step": 145
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.000622170203068947,
+      "loss": 1.1683,
+      "mean_token_accuracy": 0.7228868573904037,
+      "step": 150
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0005947925441958392,
+      "loss": 1.1881,
+      "mean_token_accuracy": 0.7217638492584229,
+      "step": 155
+    },
+    {
+      "epoch": 0.9984,
+      "eval_loss": 1.1636234521865845,
+      "eval_mean_token_accuracy": 0.7250353273223428,
+      "eval_runtime": 70.0038,
+      "eval_samples_per_second": 14.285,
+      "eval_steps_per_second": 3.571,
+      "step": 156
+    },
+    {
+      "epoch": 1.0256,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.0005671166329088278,
+      "loss": 1.3735,
+      "mean_token_accuracy": 0.7168766930699348,
+      "step": 160
+    },
+    {
+      "epoch": 1.0576,
+      "grad_norm": 0.578125,
+      "learning_rate": 0.0005392295478639225,
+      "loss": 1.0769,
+      "mean_token_accuracy": 0.740374532341957,
+      "step": 165
+    },
+    {
+      "epoch": 1.0896,
+      "grad_norm": 0.5,
+      "learning_rate": 0.0005112190321479025,
+      "loss": 1.0308,
+      "mean_token_accuracy": 0.7460691720247269,
+      "step": 170
+    },
+    {
+      "epoch": 1.1216,
+      "grad_norm": 0.4609375,
+      "learning_rate": 0.0004831732172061032,
+      "loss": 1.1521,
+      "mean_token_accuracy": 0.7258656650781632,
+      "step": 175
+    },
+    {
+      "epoch": 1.1536,
+      "grad_norm": 0.466796875,
+      "learning_rate": 0.0004551803455482833,
+      "loss": 1.0695,
+      "mean_token_accuracy": 0.7392740726470948,
+      "step": 180
+    },
+    {
+      "epoch": 1.1856,
+      "grad_norm": 0.3671875,
+      "learning_rate": 0.0004273284931050438,
+      "loss": 1.0262,
+      "mean_token_accuracy": 0.7486750066280365,
+      "step": 185
+    },
+    {
+      "epoch": 1.2176,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00039970529210836363,
+      "loss": 1.1084,
+      "mean_token_accuracy": 0.7333114802837372,
+      "step": 190
+    },
+    {
+      "epoch": 1.2496,
+      "grad_norm": 0.431640625,
+      "learning_rate": 0.00037239765536817873,
+      "loss": 0.9957,
+      "mean_token_accuracy": 0.7531520247459411,
+      "step": 195
+    },
+    {
+      "epoch": 1.2816,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00034549150281252633,
+      "loss": 0.9807,
+      "mean_token_accuracy": 0.7547169893980026,
+      "step": 200
+    },
+    {
+      "epoch": 1.3136,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.000319071491151664,
+      "loss": 0.9396,
+      "mean_token_accuracy": 0.7626697480678558,
+      "step": 205
+    },
+    {
+      "epoch": 1.3456000000000001,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00029322074751673977,
+      "loss": 0.9961,
+      "mean_token_accuracy": 0.753812238574028,
+      "step": 210
+    },
+    {
+      "epoch": 1.3776,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.000268020607911083,
+      "loss": 0.9953,
+      "mean_token_accuracy": 0.7547316879034043,
+      "step": 215
+    },
+    {
+      "epoch": 1.4096,
+      "grad_norm": 0.3515625,
+      "learning_rate": 0.000243550361297047,
+      "loss": 0.975,
+      "mean_token_accuracy": 0.7559601426124573,
+      "step": 220
+    },
+    {
+      "epoch": 1.4416,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00021988700012359863,
+      "loss": 1.0118,
+      "mean_token_accuracy": 0.7498785346746445,
+      "step": 225
+    },
+    {
+      "epoch": 1.4736,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.0001971049780795901,
+      "loss": 0.9645,
+      "mean_token_accuracy": 0.757828313112259,
+      "step": 230
+    },
+    {
+      "epoch": 1.5056,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017527597583490823,
+      "loss": 0.9121,
+      "mean_token_accuracy": 0.7678615897893906,
+      "step": 235
+    },
+    {
+      "epoch": 1.5375999999999999,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00015446867550656773,
+      "loss": 1.0359,
+      "mean_token_accuracy": 0.7470418214797974,
+      "step": 240
+    },
+    {
+      "epoch": 1.5695999999999999,
+      "grad_norm": 0.416015625,
+      "learning_rate": 0.0001347485445593612,
+      "loss": 0.9479,
+      "mean_token_accuracy": 0.7594236731529236,
+      "step": 245
+    },
+    {
+      "epoch": 1.6016,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00011617762982099444,
+      "loss": 0.9621,
+      "mean_token_accuracy": 0.7574791193008423,
+      "step": 250
+    },
+    {
+      "epoch": 1.6336,
+      "grad_norm": 0.4140625,
+      "learning_rate": 9.881436225981105e-05,
+      "loss": 0.9807,
+      "mean_token_accuracy": 0.7525162696838379,
+      "step": 255
+    },
+    {
+      "epoch": 1.6656,
+      "grad_norm": 0.431640625,
+      "learning_rate": 8.271337313934873e-05,
+      "loss": 0.9372,
+      "mean_token_accuracy": 0.7655486732721328,
+      "step": 260
+    },
+    {
+      "epoch": 1.6976,
+      "grad_norm": 0.40625,
+      "learning_rate": 6.792532212817271e-05,
+      "loss": 0.9755,
+      "mean_token_accuracy": 0.7566721349954605,
+      "step": 265
+    },
+    {
+      "epoch": 1.7296,
+      "grad_norm": 0.44921875,
+      "learning_rate": 5.449673790581611e-05,
+      "loss": 0.9346,
+      "mean_token_accuracy": 0.7655843138694763,
+      "step": 270
+    },
+    {
+      "epoch": 1.7616,
+      "grad_norm": 0.443359375,
+      "learning_rate": 4.2469871766340095e-05,
+      "loss": 1.0262,
+      "mean_token_accuracy": 0.748220956325531,
+      "step": 275
+    },
+    {
+      "epoch": 1.7936,
+      "grad_norm": 0.416015625,
+      "learning_rate": 3.18825646801314e-05,
+      "loss": 0.973,
+      "mean_token_accuracy": 0.7554513663053513,
+      "step": 280
+    },
+    {
+      "epoch": 1.8256000000000001,
+      "grad_norm": 0.36328125,
+      "learning_rate": 2.276812823220964e-05,
+      "loss": 0.9479,
+      "mean_token_accuracy": 0.7615785777568818,
+      "step": 285
+    },
+    {
+      "epoch": 1.8576000000000001,
+      "grad_norm": 0.390625,
+      "learning_rate": 1.5155239811656562e-05,
+      "loss": 0.9759,
+      "mean_token_accuracy": 0.7542947381734848,
+      "step": 290
+    },
+    {
+      "epoch": 1.8896,
+      "grad_norm": 0.41796875,
+      "learning_rate": 9.0678523819408e-06,
+      "loss": 0.9293,
+      "mean_token_accuracy": 0.7637231528759003,
+      "step": 295
+    },
+    {
+      "epoch": 1.9216,
+      "grad_norm": 0.416015625,
+      "learning_rate": 4.52511911603265e-06,
+      "loss": 0.9287,
+      "mean_token_accuracy": 0.7664623886346817,
+      "step": 300
+    },
+    {
+      "epoch": 1.9536,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.541333133436018e-06,
+      "loss": 0.995,
+      "mean_token_accuracy": 0.7533135890960694,
+      "step": 305
+    },
+    {
+      "epoch": 1.9856,
+      "grad_norm": 0.384765625,
+      "learning_rate": 1.2588252874673466e-07,
+      "loss": 0.9186,
+      "mean_token_accuracy": 0.7667679220438004,
+      "step": 310
+    },
+    {
+      "epoch": 1.9984,
+      "eval_loss": 1.0249439477920532,
+      "eval_mean_token_accuracy": 0.7480296109073846,
+      "eval_runtime": 74.4351,
+      "eval_samples_per_second": 13.435,
+      "eval_steps_per_second": 3.359,
+      "step": 312
+    },
+    {
+      "epoch": 1.9984,
+      "step": 312,
+      "total_flos": 6258600061401600.0,
+      "train_loss": 0.5569522526019659,
+      "train_runtime": 905.7572,
+      "train_samples_per_second": 5.52,
+      "train_steps_per_second": 0.344
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6258600061401600.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0fe305d962f97164f1015eae1856be72b8587a1a543d77a5451ce4b3139ab55
+size 5624