upload model checkpoint

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip 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

README.md

@@ -1,3 +1,76 @@
----
-license: gemma
----
+---
+library_name: peft
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- llama-duo/synth_summarize_dataset_dedup
+base_model: google/gemma-7b
+model-index:
+- name: gemma7b-summarize-gemini1_5flash-32k
+  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. -->
+
+# gemma7b-summarize-gemini1_5flash-32k
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the llama-duo/synth_summarize_dataset_dedup dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5408
+
+## 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 7.4587        | 1.0   | 52   | 4.9639          |
+| 1.2656        | 2.0   | 104  | 2.7099          |
+| 1.1018        | 3.0   | 156  | 2.5878          |
+| 1.0198        | 4.0   | 208  | 2.5538          |
+| 0.9682        | 5.0   | 260  | 2.5424          |
+| 0.9349        | 6.0   | 312  | 2.5212          |
+| 0.9093        | 7.0   | 364  | 2.5261          |
+| 0.906         | 8.0   | 416  | 2.5334          |
+| 0.9005        | 9.0   | 468  | 2.5352          |
+| 0.8909        | 10.0  | 520  | 2.5408          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-7b",
+  "bias": "none",
+  "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_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ad46d8f3e0a1fe352ee907a71714709e03914a99365d6296cb57856a4a6494
+size 12860096

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 2.5407798290252686,
+    "eval_runtime": 0.2399,
+    "eval_samples": 25,
+    "eval_samples_per_second": 41.685,
+    "eval_steps_per_second": 4.168,
+    "total_flos": 1.586229114665173e+18,
+    "train_loss": 3.2695524289057807,
+    "train_runtime": 1270.6632,
+    "train_samples": 31676,
+    "train_samples_per_second": 26.183,
+    "train_steps_per_second": 0.409
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "google/gemma-7b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 256000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 2.5407798290252686,
+    "eval_runtime": 0.2399,
+    "eval_samples": 25,
+    "eval_samples_per_second": 41.685,
+    "eval_steps_per_second": 4.168
+}

runs/Jun13_16-38-17_gpu1-1/events.out.tfevents.1718268273.gpu1-1.630857.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b960da0d3a846227c195d046d107f4669c186f72307751e200c53aa28e4d035a
+size 30592

runs/Jun13_16-38-17_gpu1-1/events.out.tfevents.1718269544.gpu1-1.630857.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1355fa438922c0c0e87998f61d3bc2aa066d6f49aeda885188fd83dfc3b812
+size 359

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322a5f52ab5cab196761ab397a022d6fa3a2e1418585e532bb6efb2fedd2ae94
+size 17477501

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1.586229114665173e+18,
+    "train_loss": 3.2695524289057807,
+    "train_runtime": 1270.6632,
+    "train_samples": 31676,
+    "train_samples_per_second": 26.183,
+    "train_steps_per_second": 0.409
+}

trainer_state.json

@@ -0,0 +1,845 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 520,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019230769230769232,
+      "grad_norm": 304.0,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 51.2248,
+      "step": 1
+    },
+    {
+      "epoch": 0.09615384615384616,
+      "grad_norm": 230.0,
+      "learning_rate": 1.923076923076923e-05,
+      "loss": 49.4747,
+      "step": 5
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 117.5,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 40.9096,
+      "step": 10
+    },
+    {
+      "epoch": 0.28846153846153844,
+      "grad_norm": 21.0,
+      "learning_rate": 5.769230769230769e-05,
+      "loss": 28.3937,
+      "step": 15
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 17.5,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 24.1455,
+      "step": 20
+    },
+    {
+      "epoch": 0.4807692307692308,
+      "grad_norm": 5.21875,
+      "learning_rate": 9.615384615384617e-05,
+      "loss": 21.2416,
+      "step": 25
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 4.8125,
+      "learning_rate": 0.00011538461538461538,
+      "loss": 20.1092,
+      "step": 30
+    },
+    {
+      "epoch": 0.6730769230769231,
+      "grad_norm": 8.5625,
+      "learning_rate": 0.00013461538461538464,
+      "loss": 18.6551,
+      "step": 35
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 12.75,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 17.0793,
+      "step": 40
+    },
+    {
+      "epoch": 0.8653846153846154,
+      "grad_norm": 26.5,
+      "learning_rate": 0.0001730769230769231,
+      "loss": 13.6753,
+      "step": 45
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 29.125,
+      "learning_rate": 0.00019230769230769233,
+      "loss": 7.4587,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.9638800621032715,
+      "eval_runtime": 0.2381,
+      "eval_samples_per_second": 41.995,
+      "eval_steps_per_second": 4.199,
+      "step": 52
+    },
+    {
+      "epoch": 1.0576923076923077,
+      "grad_norm": 9.125,
+      "learning_rate": 0.00019997972289848503,
+      "loss": 2.9338,
+      "step": 55
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 6.125,
+      "learning_rate": 0.00019985583705641418,
+      "loss": 2.3661,
+      "step": 60
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 5.0,
+      "learning_rate": 0.00019961946980917456,
+      "loss": 1.8737,
+      "step": 65
+    },
+    {
+      "epoch": 1.3461538461538463,
+      "grad_norm": 5.40625,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 1.711,
+      "step": 70
+    },
+    {
+      "epoch": 1.4423076923076923,
+      "grad_norm": 1.65625,
+      "learning_rate": 0.0001988104825147528,
+      "loss": 1.5595,
+      "step": 75
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 3.234375,
+      "learning_rate": 0.00019823877374156647,
+      "loss": 1.4982,
+      "step": 80
+    },
+    {
+      "epoch": 1.6346153846153846,
+      "grad_norm": 0.98828125,
+      "learning_rate": 0.00019755640508470942,
+      "loss": 1.4297,
+      "step": 85
+    },
+    {
+      "epoch": 1.7307692307692308,
+      "grad_norm": 0.859375,
+      "learning_rate": 0.00019676414519013781,
+      "loss": 1.3676,
+      "step": 90
+    },
+    {
+      "epoch": 1.8269230769230769,
+      "grad_norm": 0.9140625,
+      "learning_rate": 0.00019586288648946947,
+      "loss": 1.321,
+      "step": 95
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00019485364419471454,
+      "loss": 1.2656,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.7099387645721436,
+      "eval_runtime": 0.239,
+      "eval_samples_per_second": 41.836,
+      "eval_steps_per_second": 4.184,
+      "step": 104
+    },
+    {
+      "epoch": 2.019230769230769,
+      "grad_norm": 0.80859375,
+      "learning_rate": 0.00019373755515470254,
+      "loss": 1.2309,
+      "step": 105
+    },
+    {
+      "epoch": 2.1153846153846154,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00019251587657449236,
+      "loss": 1.1992,
+      "step": 110
+    },
+    {
+      "epoch": 2.2115384615384617,
+      "grad_norm": 1.75,
+      "learning_rate": 0.00019118998459920902,
+      "loss": 1.1813,
+      "step": 115
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.0001897613727639014,
+      "loss": 1.1643,
+      "step": 120
+    },
+    {
+      "epoch": 2.4038461538461537,
+      "grad_norm": 3.4375,
+      "learning_rate": 0.0001882316503111678,
+      "loss": 1.1501,
+      "step": 125
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 1.1451,
+      "step": 130
+    },
+    {
+      "epoch": 2.5961538461538463,
+      "grad_norm": 12.4375,
+      "learning_rate": 0.00018487587805699526,
+      "loss": 1.124,
+      "step": 135
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.00018305360832480117,
+      "loss": 1.125,
+      "step": 140
+    },
+    {
+      "epoch": 2.7884615384615383,
+      "grad_norm": 4.375,
+      "learning_rate": 0.00018113778385565733,
+      "loss": 1.1124,
+      "step": 145
+    },
+    {
+      "epoch": 2.8846153846153846,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.0001791305627069662,
+      "loss": 1.106,
+      "step": 150
+    },
+    {
+      "epoch": 2.980769230769231,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.00017703420588881946,
+      "loss": 1.1018,
+      "step": 155
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.5878167152404785,
+      "eval_runtime": 0.2386,
+      "eval_samples_per_second": 41.914,
+      "eval_steps_per_second": 4.191,
+      "step": 156
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 1.0905,
+      "step": 160
+    },
+    {
+      "epoch": 3.173076923076923,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.00017258362865354426,
+      "loss": 1.0538,
+      "step": 165
+    },
+    {
+      "epoch": 3.269230769230769,
+      "grad_norm": 0.640625,
+      "learning_rate": 0.00017023442153554777,
+      "loss": 1.0444,
+      "step": 170
+    },
+    {
+      "epoch": 3.3653846153846154,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.0001678060996991891,
+      "loss": 1.0419,
+      "step": 175
+    },
+    {
+      "epoch": 3.4615384615384617,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.0001653013984983585,
+      "loss": 1.0547,
+      "step": 180
+    },
+    {
+      "epoch": 3.5576923076923075,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.00016272313932356162,
+      "loss": 1.0499,
+      "step": 185
+    },
+    {
+      "epoch": 3.6538461538461537,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.0001600742264237979,
+      "loss": 1.0271,
+      "step": 190
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.0001573576436351046,
+      "loss": 1.0199,
+      "step": 195
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 0.84765625,
+      "learning_rate": 0.00015457645101945046,
+      "loss": 1.0173,
+      "step": 200
+    },
+    {
+      "epoch": 3.9423076923076925,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.00015173378141776568,
+      "loss": 1.0198,
+      "step": 205
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.5538089275360107,
+      "eval_runtime": 0.2387,
+      "eval_samples_per_second": 41.901,
+      "eval_steps_per_second": 4.19,
+      "step": 208
+    },
+    {
+      "epoch": 4.038461538461538,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00014883283692099112,
+      "loss": 1.0044,
+      "step": 210
+    },
+    {
+      "epoch": 4.134615384615385,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00014587688526312143,
+      "loss": 0.9975,
+      "step": 215
+    },
+    {
+      "epoch": 4.230769230769231,
+      "grad_norm": 1.7734375,
+      "learning_rate": 0.00014286925614030542,
+      "loss": 0.9872,
+      "step": 220
+    },
+    {
+      "epoch": 4.326923076923077,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.0001398133374601501,
+      "loss": 0.9851,
+      "step": 225
+    },
+    {
+      "epoch": 4.423076923076923,
+      "grad_norm": 1.5234375,
+      "learning_rate": 0.00013671257152545277,
+      "loss": 0.9774,
+      "step": 230
+    },
+    {
+      "epoch": 4.519230769230769,
+      "grad_norm": 1.34375,
+      "learning_rate": 0.0001335704511566605,
+      "loss": 0.9794,
+      "step": 235
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.0001303905157574247,
+      "loss": 0.9764,
+      "step": 240
+    },
+    {
+      "epoch": 4.711538461538462,
+      "grad_norm": 0.90625,
+      "learning_rate": 0.00012717634732768243,
+      "loss": 0.9714,
+      "step": 245
+    },
+    {
+      "epoch": 4.8076923076923075,
+      "grad_norm": 1.4375,
+      "learning_rate": 0.0001239315664287558,
+      "loss": 0.9649,
+      "step": 250
+    },
+    {
+      "epoch": 4.903846153846154,
+      "grad_norm": 0.9921875,
+      "learning_rate": 0.00012065982810501404,
+      "loss": 0.9635,
+      "step": 255
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.3828125,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.9682,
+      "step": 260
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.542388439178467,
+      "eval_runtime": 0.2362,
+      "eval_samples_per_second": 42.339,
+      "eval_steps_per_second": 4.234,
+      "step": 260
+    },
+    {
+      "epoch": 5.096153846153846,
+      "grad_norm": 0.8046875,
+      "learning_rate": 0.00011405024703850929,
+      "loss": 0.9485,
+      "step": 265
+    },
+    {
+      "epoch": 5.1923076923076925,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00011071984957874479,
+      "loss": 0.95,
+      "step": 270
+    },
+    {
+      "epoch": 5.288461538461538,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00010737737687351284,
+      "loss": 0.9429,
+      "step": 275
+    },
+    {
+      "epoch": 5.384615384615385,
+      "grad_norm": 0.75,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 0.9439,
+      "step": 280
+    },
+    {
+      "epoch": 5.480769230769231,
+      "grad_norm": 0.8984375,
+      "learning_rate": 0.00010067127544003563,
+      "loss": 0.9454,
+      "step": 285
+    },
+    {
+      "epoch": 5.576923076923077,
+      "grad_norm": 0.984375,
+      "learning_rate": 9.73152007189939e-05,
+      "loss": 0.9446,
+      "step": 290
+    },
+    {
+      "epoch": 5.673076923076923,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.396215025777139e-05,
+      "loss": 0.9427,
+      "step": 295
+    },
+    {
+      "epoch": 5.769230769230769,
+      "grad_norm": 0.4765625,
+      "learning_rate": 9.061590105968208e-05,
+      "loss": 0.9351,
+      "step": 300
+    },
+    {
+      "epoch": 5.865384615384615,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.728022246683894e-05,
+      "loss": 0.94,
+      "step": 305
+    },
+    {
+      "epoch": 5.961538461538462,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.395887191422397e-05,
+      "loss": 0.9349,
+      "step": 310
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.521150588989258,
+      "eval_runtime": 0.2386,
+      "eval_samples_per_second": 41.905,
+      "eval_steps_per_second": 4.191,
+      "step": 312
+    },
+    {
+      "epoch": 6.0576923076923075,
+      "grad_norm": 2.0625,
+      "learning_rate": 8.065559069717088e-05,
+      "loss": 0.9261,
+      "step": 315
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 1.6875,
+      "learning_rate": 7.73740997570278e-05,
+      "loss": 0.9233,
+      "step": 320
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.546875,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.9199,
+      "step": 325
+    },
+    {
+      "epoch": 6.346153846153846,
+      "grad_norm": 0.71875,
+      "learning_rate": 7.089124558212871e-05,
+      "loss": 0.9295,
+      "step": 330
+    },
+    {
+      "epoch": 6.4423076923076925,
+      "grad_norm": 0.73828125,
+      "learning_rate": 6.769718488039023e-05,
+      "loss": 0.9141,
+      "step": 335
+    },
+    {
+      "epoch": 6.538461538461538,
+      "grad_norm": 0.69140625,
+      "learning_rate": 6.453951129574644e-05,
+      "loss": 0.9129,
+      "step": 340
+    },
+    {
+      "epoch": 6.634615384615385,
+      "grad_norm": 0.578125,
+      "learning_rate": 6.142178175158149e-05,
+      "loss": 0.917,
+      "step": 345
+    },
+    {
+      "epoch": 6.730769230769231,
+      "grad_norm": 0.7421875,
+      "learning_rate": 5.834750817679606e-05,
+      "loss": 0.9146,
+      "step": 350
+    },
+    {
+      "epoch": 6.826923076923077,
+      "grad_norm": 0.61328125,
+      "learning_rate": 5.5320153549837415e-05,
+      "loss": 0.9191,
+      "step": 355
+    },
+    {
+      "epoch": 6.923076923076923,
+      "grad_norm": 0.55078125,
+      "learning_rate": 5.234312799786921e-05,
+      "loss": 0.9093,
+      "step": 360
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.5261104106903076,
+      "eval_runtime": 0.2385,
+      "eval_samples_per_second": 41.933,
+      "eval_steps_per_second": 4.193,
+      "step": 364
+    },
+    {
+      "epoch": 7.019230769230769,
+      "grad_norm": 0.65625,
+      "learning_rate": 4.9419784955474524e-05,
+      "loss": 0.9152,
+      "step": 365
+    },
+    {
+      "epoch": 7.115384615384615,
+      "grad_norm": 0.447265625,
+      "learning_rate": 4.6553417387219886e-05,
+      "loss": 0.8965,
+      "step": 370
+    },
+    {
+      "epoch": 7.211538461538462,
+      "grad_norm": 0.5703125,
+      "learning_rate": 4.374725407833532e-05,
+      "loss": 0.9012,
+      "step": 375
+    },
+    {
+      "epoch": 7.3076923076923075,
+      "grad_norm": 0.46484375,
+      "learning_rate": 4.100445599768774e-05,
+      "loss": 0.9105,
+      "step": 380
+    },
+    {
+      "epoch": 7.403846153846154,
+      "grad_norm": 0.451171875,
+      "learning_rate": 3.832811273714569e-05,
+      "loss": 0.9071,
+      "step": 385
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.498046875,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.903,
+      "step": 390
+    },
+    {
+      "epoch": 7.596153846153846,
+      "grad_norm": 0.47265625,
+      "learning_rate": 3.318677136178228e-05,
+      "loss": 0.898,
+      "step": 395
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 0.470703125,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.9056,
+      "step": 400
+    },
+    {
+      "epoch": 7.788461538461538,
+      "grad_norm": 0.40625,
+      "learning_rate": 2.8346389036906828e-05,
+      "loss": 0.9032,
+      "step": 405
+    },
+    {
+      "epoch": 7.884615384615385,
+      "grad_norm": 0.4296875,
+      "learning_rate": 2.6045926771976303e-05,
+      "loss": 0.9025,
+      "step": 410
+    },
+    {
+      "epoch": 7.980769230769231,
+      "grad_norm": 0.59375,
+      "learning_rate": 2.382876918226409e-05,
+      "loss": 0.906,
+      "step": 415
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.533395528793335,
+      "eval_runtime": 0.2363,
+      "eval_samples_per_second": 42.318,
+      "eval_steps_per_second": 4.232,
+      "step": 416
+    },
+    {
+      "epoch": 8.076923076923077,
+      "grad_norm": 0.578125,
+      "learning_rate": 2.1697413758237784e-05,
+      "loss": 0.8984,
+      "step": 420
+    },
+    {
+      "epoch": 8.173076923076923,
+      "grad_norm": 0.6796875,
+      "learning_rate": 1.965426133954854e-05,
+      "loss": 0.8971,
+      "step": 425
+    },
+    {
+      "epoch": 8.26923076923077,
+      "grad_norm": 0.48046875,
+      "learning_rate": 1.7701613410634365e-05,
+      "loss": 0.8991,
+      "step": 430
+    },
+    {
+      "epoch": 8.365384615384615,
+      "grad_norm": 0.58984375,
+      "learning_rate": 1.584166950824061e-05,
+      "loss": 0.897,
+      "step": 435
+    },
+    {
+      "epoch": 8.461538461538462,
+      "grad_norm": 0.58984375,
+      "learning_rate": 1.4076524743778319e-05,
+      "loss": 0.8916,
+      "step": 440
+    },
+    {
+      "epoch": 8.557692307692308,
+      "grad_norm": 0.470703125,
+      "learning_rate": 1.2408167443311214e-05,
+      "loss": 0.8914,
+      "step": 445
+    },
+    {
+      "epoch": 8.653846153846153,
+      "grad_norm": 0.423828125,
+      "learning_rate": 1.083847690782972e-05,
+      "loss": 0.8918,
+      "step": 450
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 0.42578125,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 0.8964,
+      "step": 455
+    },
+    {
+      "epoch": 8.846153846153847,
+      "grad_norm": 0.439453125,
+      "learning_rate": 8.002055634117578e-06,
+      "loss": 0.9012,
+      "step": 460
+    },
+    {
+      "epoch": 8.942307692307692,
+      "grad_norm": 0.40625,
+      "learning_rate": 6.738519948473976e-06,
+      "loss": 0.9005,
+      "step": 465
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.5352470874786377,
+      "eval_runtime": 0.2402,
+      "eval_samples_per_second": 41.631,
+      "eval_steps_per_second": 4.163,
+      "step": 468
+    },
+    {
+      "epoch": 9.038461538461538,
+      "grad_norm": 0.3984375,
+      "learning_rate": 5.580037533961546e-06,
+      "loss": 0.9032,
+      "step": 470
+    },
+    {
+      "epoch": 9.134615384615385,
+      "grad_norm": 0.4140625,
+      "learning_rate": 4.527913349145441e-06,
+      "loss": 0.8882,
+      "step": 475
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 0.4140625,
+      "learning_rate": 3.5833325466437694e-06,
+      "loss": 0.8951,
+      "step": 480
+    },
+    {
+      "epoch": 9.326923076923077,
+      "grad_norm": 0.41015625,
+      "learning_rate": 2.7473591381266708e-06,
+      "loss": 0.8969,
+      "step": 485
+    },
+    {
+      "epoch": 9.423076923076923,
+      "grad_norm": 0.494140625,
+      "learning_rate": 2.0209347957732328e-06,
+      "loss": 0.893,
+      "step": 490
+    },
+    {
+      "epoch": 9.51923076923077,
+      "grad_norm": 0.453125,
+      "learning_rate": 1.404877791536141e-06,
+      "loss": 0.9007,
+      "step": 495
+    },
+    {
+      "epoch": 9.615384615384615,
+      "grad_norm": 0.431640625,
+      "learning_rate": 8.998820754091531e-07,
+      "loss": 0.8921,
+      "step": 500
+    },
+    {
+      "epoch": 9.711538461538462,
+      "grad_norm": 0.41015625,
+      "learning_rate": 5.065164937354428e-07,
+      "loss": 0.895,
+      "step": 505
+    },
+    {
+      "epoch": 9.807692307692308,
+      "grad_norm": 0.412109375,
+      "learning_rate": 2.2522414843748618e-07,
+      "loss": 0.9003,
+      "step": 510
+    },
+    {
+      "epoch": 9.903846153846153,
+      "grad_norm": 0.416015625,
+      "learning_rate": 5.632189789027687e-08,
+      "loss": 0.8975,
+      "step": 515
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.0,
+      "loss": 0.8909,
+      "step": 520
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.5407798290252686,
+      "eval_runtime": 0.2364,
+      "eval_samples_per_second": 42.307,
+      "eval_steps_per_second": 4.231,
+      "step": 520
+    },
+    {
+      "epoch": 10.0,
+      "step": 520,
+      "total_flos": 1.586229114665173e+18,
+      "train_loss": 3.2695524289057807,
+      "train_runtime": 1270.6632,
+      "train_samples_per_second": 26.183,
+      "train_steps_per_second": 0.409
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 520,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.586229114665173e+18,
+  "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:ddbcec7504f4d43203690f7bb5a7c7bd59e765b356fba6ac0a0fbabfeeeff186
+size 5176