Add HuggingFaceH4/qwen-1.5-1.8b-sft-v0.0 checkpoint

README.md

@@ -0,0 +1,67 @@
+---
+license: other
+base_model: Qwen/Qwen1.5-1.8B
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/deita-6k-v0-sft
+model-index:
+- name: qwen-1.5-1.8b-sft-v0.0
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen-1.5-1.8b-sft-v0.0
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on the HuggingFaceH4/deita-6k-v0-sft dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0886
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0963        | 1.0   | 237  | 1.0788          |
+| 0.9779        | 2.0   | 474  | 1.0728          |
+| 0.8734        | 3.0   | 711  | 1.0886          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.0886437892913818,
+    "eval_runtime": 4.9902,
+    "eval_samples": 300,
+    "eval_samples_per_second": 295.379,
+    "eval_steps_per_second": 4.809,
+    "perplexity": 2.970243064281644,
+    "train_loss": 0.9885472514458347,
+    "train_runtime": 1164.5291,
+    "train_samples": 5700,
+    "train_samples_per_second": 77.885,
+    "train_steps_per_second": 0.611
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151648
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.0886437892913818,
+    "eval_runtime": 4.9902,
+    "eval_samples": 300,
+    "eval_samples_per_second": 295.379,
+    "eval_steps_per_second": 4.809,
+    "perplexity": 2.970243064281644
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0528c447ff8ef58d7e4b75f6dffdc118c7e6265f71cba9d51f5f82568116307
+size 3671331400

runs/Mar13_15-55-26_ip-26-0-167-175/events.out.tfevents.1710345414.ip-26-0-167-175.47301.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fcbb00e9e4a6f8a9cff3001a39152ae4220f2a3ba65b4ed36428d04b9a238ae
+size 5110

runs/Mar13_16-10-47_ip-26-0-167-175/events.out.tfevents.1710346278.ip-26-0-167-175.49847.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167ac8274f99fda2d60119233034cad0bbe44b2aeb1f55df903356b9394d257d
+size 5110

runs/Mar13_16-17-22_ip-26-0-167-175/events.out.tfevents.1710346695.ip-26-0-167-175.50976.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a971f7d2d93ef149c56b264a95b1fe506e03c9a211259843b5e59aa52e9921
+size 5317

runs/Mar13_16-33-16_ip-26-0-167-175/events.out.tfevents.1710347631.ip-26-0-167-175.54812.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becc4d3160a74d30ac97faae40040b5977547de2d0e8779c770127e2151d21df
+size 5105

runs/Mar13_16-35-17_ip-26-0-167-175/events.out.tfevents.1710347746.ip-26-0-167-175.55966.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b941c9b2a5ddf02dc52346adf9c57b72e773e694d4cc30cb6046a3805a3d698
+size 5519

runs/Mar13_18-28-03_ip-26-0-166-244/events.out.tfevents.1710354517.ip-26-0-166-244.384933.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c12ca5f508bfce039e6123ea4eb46789c5bb749ec484f8831905745ee75c78c
+size 36317

runs/Mar13_18-28-03_ip-26-0-166-244/events.out.tfevents.1710355686.ip-26-0-166-244.384933.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad5e4f6ab8854be1b807b29c827115dab39773081d73145e925d633d9817241
+size 359

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.9885472514458347,
+    "train_runtime": 1164.5291,
+    "train_samples": 5700,
+    "train_samples_per_second": 77.885,
+    "train_steps_per_second": 0.611
+}

trainer_state.json

@@ -0,0 +1,1055 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 711,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 6.304776350824905,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 1.2835,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.1444154892612906,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": 1.2052,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.829285889985009,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 1.2292,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.1679705762984034,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 1.1597,
+      "step": 15
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.4357027628580525,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.1284,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.9452863213714234,
+      "learning_rate": 6.944444444444445e-06,
+      "loss": 1.1531,
+      "step": 25
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.8873033736663324,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.1549,
+      "step": 30
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.7881640401882983,
+      "learning_rate": 9.722222222222223e-06,
+      "loss": 1.1306,
+      "step": 35
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.7249086340452754,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 1.0851,
+      "step": 40
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.6764364880756644,
+      "learning_rate": 1.25e-05,
+      "loss": 1.139,
+      "step": 45
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.6897544761050797,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 1.1317,
+      "step": 50
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.6816142474216428,
+      "learning_rate": 1.5277777777777777e-05,
+      "loss": 1.1313,
+      "step": 55
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.6811212493739357,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.138,
+      "step": 60
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.6862844341255663,
+      "learning_rate": 1.8055555555555558e-05,
+      "loss": 1.1483,
+      "step": 65
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.4787128965985026,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 1.1395,
+      "step": 70
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.7775487986058592,
+      "learning_rate": 1.999891231617599e-05,
+      "loss": 1.1161,
+      "step": 75
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.7115088691454458,
+      "learning_rate": 1.9992266216318037e-05,
+      "loss": 1.0932,
+      "step": 80
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.6818793389006765,
+      "learning_rate": 1.997958229642588e-05,
+      "loss": 1.1178,
+      "step": 85
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.6928106880338162,
+      "learning_rate": 1.996086822074945e-05,
+      "loss": 1.1298,
+      "step": 90
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.6676196732940871,
+      "learning_rate": 1.9936135297256183e-05,
+      "loss": 1.1094,
+      "step": 95
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.713377771129619,
+      "learning_rate": 1.9905398470798207e-05,
+      "loss": 1.1224,
+      "step": 100
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.6855059849013185,
+      "learning_rate": 1.9868676314081907e-05,
+      "loss": 1.1123,
+      "step": 105
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.660806750689474,
+      "learning_rate": 1.9825991016445387e-05,
+      "loss": 1.1044,
+      "step": 110
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.6638994109236709,
+      "learning_rate": 1.9777368370450582e-05,
+      "loss": 1.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.6862841124125318,
+      "learning_rate": 1.9722837756298112e-05,
+      "loss": 1.1057,
+      "step": 120
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.6713561495513073,
+      "learning_rate": 1.9662432124074325e-05,
+      "loss": 1.1247,
+      "step": 125
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.6865654618803174,
+      "learning_rate": 1.9596187973841218e-05,
+      "loss": 1.0959,
+      "step": 130
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.6512909442458682,
+      "learning_rate": 1.9524145333581315e-05,
+      "loss": 1.1178,
+      "step": 135
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.542422418836288,
+      "learning_rate": 1.9446347735010765e-05,
+      "loss": 1.0984,
+      "step": 140
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.7206951642675766,
+      "learning_rate": 1.9362842187275354e-05,
+      "loss": 1.0812,
+      "step": 145
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.6984462641482525,
+      "learning_rate": 1.9273679148545246e-05,
+      "loss": 1.1129,
+      "step": 150
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.6657063460800421,
+      "learning_rate": 1.917891249552568e-05,
+      "loss": 1.1147,
+      "step": 155
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.6732684805189473,
+      "learning_rate": 1.9078599490901984e-05,
+      "loss": 1.0988,
+      "step": 160
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.6969660113279658,
+      "learning_rate": 1.897280074873868e-05,
+      "loss": 1.0901,
+      "step": 165
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.6545636951842201,
+      "learning_rate": 1.8861580197853423e-05,
+      "loss": 1.0808,
+      "step": 170
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.728879426031119,
+      "learning_rate": 1.8745005043188104e-05,
+      "loss": 1.1007,
+      "step": 175
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.6989476047236611,
+      "learning_rate": 1.862314572520028e-05,
+      "loss": 1.0972,
+      "step": 180
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.6937493330837292,
+      "learning_rate": 1.8496075877299585e-05,
+      "loss": 1.0751,
+      "step": 185
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7237715465824409,
+      "learning_rate": 1.8363872281354796e-05,
+      "loss": 1.1005,
+      "step": 190
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.665001160804127,
+      "learning_rate": 1.8226614821298444e-05,
+      "loss": 1.0979,
+      "step": 195
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.6512333420285555,
+      "learning_rate": 1.808438643485698e-05,
+      "loss": 1.0663,
+      "step": 200
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.6670845393437954,
+      "learning_rate": 1.793727306343574e-05,
+      "loss": 1.0479,
+      "step": 205
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.660996369149025,
+      "learning_rate": 1.7785363600188894e-05,
+      "loss": 1.0631,
+      "step": 210
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.6383025721204546,
+      "learning_rate": 1.762874983630582e-05,
+      "loss": 1.0594,
+      "step": 215
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.6481663495293073,
+      "learning_rate": 1.7467526405546344e-05,
+      "loss": 1.1117,
+      "step": 220
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.6526574717781632,
+      "learning_rate": 1.7301790727058344e-05,
+      "loss": 1.074,
+      "step": 225
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.6602485216423672,
+      "learning_rate": 1.7131642946512314e-05,
+      "loss": 1.1002,
+      "step": 230
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.703340110707448,
+      "learning_rate": 1.6957185875588403e-05,
+      "loss": 1.0963,
+      "step": 235
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0788308382034302,
+      "eval_runtime": 5.3118,
+      "eval_samples_per_second": 277.497,
+      "eval_steps_per_second": 4.518,
+      "step": 237
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.7492129279971655,
+      "learning_rate": 1.6778524929852513e-05,
+      "loss": 1.028,
+      "step": 240
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.8102380476622988,
+      "learning_rate": 1.659576806505905e-05,
+      "loss": 0.9794,
+      "step": 245
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.7121110613571635,
+      "learning_rate": 1.640902571191869e-05,
+      "loss": 0.9648,
+      "step": 250
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.7426962668349942,
+      "learning_rate": 1.6218410709370735e-05,
+      "loss": 0.9826,
+      "step": 255
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.675584007232439,
+      "learning_rate": 1.6024038236400246e-05,
+      "loss": 0.9454,
+      "step": 260
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.7129690280611058,
+      "learning_rate": 1.582602574244121e-05,
+      "loss": 0.9403,
+      "step": 265
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.6747033998323487,
+      "learning_rate": 1.562449287640781e-05,
+      "loss": 0.9864,
+      "step": 270
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.6837814023465153,
+      "learning_rate": 1.5419561414396657e-05,
+      "loss": 0.9864,
+      "step": 275
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.6969571002742431,
+      "learning_rate": 1.5211355186103655e-05,
+      "loss": 0.9567,
+      "step": 280
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.6630210250243682,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.9811,
+      "step": 285
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.6589068053142794,
+      "learning_rate": 1.4785623567312492e-05,
+      "loss": 0.9389,
+      "step": 290
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.6878317017661794,
+      "learning_rate": 1.4568355424854113e-05,
+      "loss": 1.0157,
+      "step": 295
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.7179535464777137,
+      "learning_rate": 1.4348326856751496e-05,
+      "loss": 0.9787,
+      "step": 300
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.6829129430840285,
+      "learning_rate": 1.412567081511659e-05,
+      "loss": 0.9639,
+      "step": 305
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.7030815356191583,
+      "learning_rate": 1.3900521839710428e-05,
+      "loss": 0.9486,
+      "step": 310
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.67559393512531,
+      "learning_rate": 1.367301597664757e-05,
+      "loss": 0.9795,
+      "step": 315
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.6780812345565891,
+      "learning_rate": 1.3443290696190335e-05,
+      "loss": 0.9785,
+      "step": 320
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.6710329710920228,
+      "learning_rate": 1.3211484809682482e-05,
+      "loss": 0.992,
+      "step": 325
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.6741452885754833,
+      "learning_rate": 1.2977738385672558e-05,
+      "loss": 1.0023,
+      "step": 330
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.6632729564225439,
+      "learning_rate": 1.2742192665277569e-05,
+      "loss": 0.995,
+      "step": 335
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.6601370650300007,
+      "learning_rate": 1.250498997683813e-05,
+      "loss": 0.9764,
+      "step": 340
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.6652011155656283,
+      "learning_rate": 1.2266273649916669e-05,
+      "loss": 0.9537,
+      "step": 345
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.6446717094616893,
+      "learning_rate": 1.202618792869063e-05,
+      "loss": 0.9525,
+      "step": 350
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.6721085026757567,
+      "learning_rate": 1.178487788479303e-05,
+      "loss": 0.9629,
+      "step": 355
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6629783449328003,
+      "learning_rate": 1.1542489329653024e-05,
+      "loss": 0.9842,
+      "step": 360
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.6522335344513943,
+      "learning_rate": 1.129916872638945e-05,
+      "loss": 1.0048,
+      "step": 365
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.6781899139396206,
+      "learning_rate": 1.1055063101310581e-05,
+      "loss": 0.9685,
+      "step": 370
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.6691172096591039,
+      "learning_rate": 1.08103199550736e-05,
+      "loss": 0.9747,
+      "step": 375
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6373869560949246,
+      "learning_rate": 1.0565087173557396e-05,
+      "loss": 0.9686,
+      "step": 380
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.6517373978992131,
+      "learning_rate": 1.0319512938502654e-05,
+      "loss": 0.9714,
+      "step": 385
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.6580577126773488,
+      "learning_rate": 1.0073745637973125e-05,
+      "loss": 0.9747,
+      "step": 390
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.6489932524871953,
+      "learning_rate": 9.827933776692236e-06,
+      "loss": 0.9874,
+      "step": 395
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.6407459560571601,
+      "learning_rate": 9.582225886309217e-06,
+      "loss": 0.9618,
+      "step": 400
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.6629610117016943,
+      "learning_rate": 9.336770435648963e-06,
+      "loss": 0.992,
+      "step": 405
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.6667119859349727,
+      "learning_rate": 9.091715740999829e-06,
+      "loss": 0.971,
+      "step": 410
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.6886862002448931,
+      "learning_rate": 8.84720987649363e-06,
+      "loss": 0.9556,
+      "step": 415
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.6426160780174832,
+      "learning_rate": 8.60340058463194e-06,
+      "loss": 0.9879,
+      "step": 420
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.6346609133677081,
+      "learning_rate": 8.360435187012789e-06,
+      "loss": 1.0061,
+      "step": 425
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.6483257723288812,
+      "learning_rate": 8.118460495311687e-06,
+      "loss": 1.0141,
+      "step": 430
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.7171449794590815,
+      "learning_rate": 7.877622722570772e-06,
+      "loss": 0.9675,
+      "step": 435
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.650114145091982,
+      "learning_rate": 7.638067394849672e-06,
+      "loss": 0.9742,
+      "step": 440
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.6929157157409924,
+      "learning_rate": 7.3999392632914936e-06,
+      "loss": 0.9872,
+      "step": 445
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.6361399427239406,
+      "learning_rate": 7.163382216657033e-06,
+      "loss": 0.9685,
+      "step": 450
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.6216240484506025,
+      "learning_rate": 6.928539194380101e-06,
+      "loss": 0.9648,
+      "step": 455
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.6162980824439727,
+      "learning_rate": 6.6955521001964526e-06,
+      "loss": 0.9608,
+      "step": 460
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.662006443614462,
+      "learning_rate": 6.464561716398565e-06,
+      "loss": 0.9555,
+      "step": 465
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.6525504751262218,
+      "learning_rate": 6.2357076187680325e-06,
+      "loss": 0.9779,
+      "step": 470
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0727574825286865,
+      "eval_runtime": 4.9769,
+      "eval_samples_per_second": 296.167,
+      "eval_steps_per_second": 4.822,
+      "step": 474
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9211908456070792,
+      "learning_rate": 6.009128092236983e-06,
+      "loss": 0.9304,
+      "step": 475
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 0.8532374349387694,
+      "learning_rate": 5.78496004732952e-06,
+      "loss": 0.8546,
+      "step": 480
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.7234550887455584,
+      "learning_rate": 5.563338937433622e-06,
+      "loss": 0.8819,
+      "step": 485
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.7126403603814161,
+      "learning_rate": 5.344398676953526e-06,
+      "loss": 0.9011,
+      "step": 490
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 0.640441506166026,
+      "learning_rate": 5.128271560392037e-06,
+      "loss": 0.8714,
+      "step": 495
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 0.6599554320566688,
+      "learning_rate": 4.915088182411674e-06,
+      "loss": 0.8918,
+      "step": 500
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.6420656415982475,
+      "learning_rate": 4.7049773589229306e-06,
+      "loss": 0.8936,
+      "step": 505
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.6624281801845274,
+      "learning_rate": 4.498066049247344e-06,
+      "loss": 0.9076,
+      "step": 510
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.6494624453990643,
+      "learning_rate": 4.29447927940242e-06,
+      "loss": 0.874,
+      "step": 515
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 0.62980438510625,
+      "learning_rate": 4.094340066554742e-06,
+      "loss": 0.8797,
+      "step": 520
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.6496965620768959,
+      "learning_rate": 3.897769344686929e-06,
+      "loss": 0.8783,
+      "step": 525
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.623988823063145,
+      "learning_rate": 3.7048858915233665e-06,
+      "loss": 0.8991,
+      "step": 530
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.6235243813957997,
+      "learning_rate": 3.5158062567588468e-06,
+      "loss": 0.8587,
+      "step": 535
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.6224524258972475,
+      "learning_rate": 3.330644691633492e-06,
+      "loss": 0.8742,
+      "step": 540
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.6267167014433769,
+      "learning_rate": 3.149513079896521e-06,
+      "loss": 0.9013,
+      "step": 545
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.6252594161210878,
+      "learning_rate": 2.9725208702005736e-06,
+      "loss": 0.8905,
+      "step": 550
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.6204178434773648,
+      "learning_rate": 2.7997750099674282e-06,
+      "loss": 0.8819,
+      "step": 555
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.6234939504584522,
+      "learning_rate": 2.631379880765107e-06,
+      "loss": 0.8844,
+      "step": 560
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.6404757813962814,
+      "learning_rate": 2.467437235235378e-06,
+      "loss": 0.8643,
+      "step": 565
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.6154655956232923,
+      "learning_rate": 2.3080461356097938e-06,
+      "loss": 0.8835,
+      "step": 570
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 0.6226597834743854,
+      "learning_rate": 2.153302893851401e-06,
+      "loss": 0.8547,
+      "step": 575
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.635711672458865,
+      "learning_rate": 2.0033010134583085e-06,
+      "loss": 0.8799,
+      "step": 580
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.6222216060732768,
+      "learning_rate": 1.8581311329642592e-06,
+      "loss": 0.8614,
+      "step": 585
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.6211538083313471,
+      "learning_rate": 1.7178809711703525e-06,
+      "loss": 0.8851,
+      "step": 590
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.6264778347828893,
+      "learning_rate": 1.5826352741410333e-06,
+      "loss": 0.8841,
+      "step": 595
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.6194165165737189,
+      "learning_rate": 1.452475763996326e-06,
+      "loss": 0.8519,
+      "step": 600
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.6156200040809161,
+      "learning_rate": 1.3274810895313083e-06,
+      "loss": 0.8595,
+      "step": 605
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.6268920763538539,
+      "learning_rate": 1.207726778692625e-06,
+      "loss": 0.8668,
+      "step": 610
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.6237602437342175,
+      "learning_rate": 1.0932851929407828e-06,
+      "loss": 0.8984,
+      "step": 615
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.6098041198161336,
+      "learning_rate": 9.842254835257792e-07,
+      "loss": 0.8889,
+      "step": 620
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.6047803478738842,
+      "learning_rate": 8.806135497025181e-07,
+      "loss": 0.8712,
+      "step": 625
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.6161378090035984,
+      "learning_rate": 7.825119989112173e-07,
+      "loss": 0.8885,
+      "step": 630
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.6233431696221546,
+      "learning_rate": 6.899801089469205e-07,
+      "loss": 0.8852,
+      "step": 635
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.6391554220139581,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.8773,
+      "step": 640
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 0.6245630190412572,
+      "learning_rate": 5.218455615757601e-07,
+      "loss": 0.8805,
+      "step": 645
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.6100529800808214,
+      "learning_rate": 4.4634449935427203e-07,
+      "loss": 0.8605,
+      "step": 650
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.6121972838225812,
+      "learning_rate": 3.7661622694171393e-07,
+      "loss": 0.9044,
+      "step": 655
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.6334525599084514,
+      "learning_rate": 3.127028775990515e-07,
+      "loss": 0.8752,
+      "step": 660
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.6246892070368814,
+      "learning_rate": 2.546430709239578e-07,
+      "loss": 0.873,
+      "step": 665
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.6189951160404621,
+      "learning_rate": 2.02471889514948e-07,
+      "loss": 0.8616,
+      "step": 670
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.612318312224187,
+      "learning_rate": 1.562208577727442e-07,
+      "loss": 0.8419,
+      "step": 675
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.597268698517341,
+      "learning_rate": 1.1591792285167603e-07,
+      "loss": 0.863,
+      "step": 680
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 0.6176692124122442,
+      "learning_rate": 8.158743777263334e-08,
+      "loss": 0.8801,
+      "step": 685
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.6020045294431875,
+      "learning_rate": 5.325014670776951e-08,
+      "loss": 0.8632,
+      "step": 690
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.6387655106971034,
+      "learning_rate": 3.092317244584919e-08,
+      "loss": 0.9029,
+      "step": 695
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.6272250942520349,
+      "learning_rate": 1.4620006045816814e-08,
+      "loss": 0.9094,
+      "step": 700
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.6245247048439003,
+      "learning_rate": 4.3504986848297295e-09,
+      "loss": 0.8741,
+      "step": 705
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6085774534918146,
+      "learning_rate": 1.2085570569642102e-10,
+      "loss": 0.8734,
+      "step": 710
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0886437892913818,
+      "eval_runtime": 5.0486,
+      "eval_samples_per_second": 291.961,
+      "eval_steps_per_second": 4.754,
+      "step": 711
+    },
+    {
+      "epoch": 3.0,
+      "step": 711,
+      "total_flos": 277125248581632.0,
+      "train_loss": 0.9885472514458347,
+      "train_runtime": 1164.5291,
+      "train_samples_per_second": 77.885,
+      "train_steps_per_second": 0.611
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 711,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 277125248581632.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa6275ea3a7ab0b52842a3362c23f21aec0ad272d596daabddb4e6c8543f247
+size 6520