Upload folder using huggingface_hub

.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

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: other
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: reasoning-multilingual-R1-Llama-70B-train
+  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. -->
+
+# reasoning-multilingual-R1-Llama-70B-train
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on the reasoning-multilingual-R1-Llama-70B-train dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9008
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9946        | 0.1020 | 10   | 0.9808          |
+| 1.042         | 0.2041 | 20   | 0.9511          |
+| 1.1236        | 0.3061 | 30   | 0.9309          |
+| 1.238         | 0.4082 | 40   | 0.9211          |
+| 0.8178        | 0.5102 | 50   | 0.9119          |
+| 0.951         | 0.6122 | 60   | 0.9066          |
+| 0.7869        | 0.7143 | 70   | 0.9032          |
+| 1.2626        | 0.8163 | 80   | 0.9012          |
+| 1.2385        | 0.9184 | 90   | 0.9009          |
+
+
+### Framework versions
+
+- Transformers 4.48.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9007720947265625,
+    "eval_runtime": 0.2597,
+    "eval_samples_per_second": 30.809,
+    "eval_steps_per_second": 3.851,
+    "total_flos": 3.270639151271117e+16,
+    "train_loss": 1.0707874030483013,
+    "train_runtime": 199.5779,
+    "train_samples_per_second": 3.908,
+    "train_steps_per_second": 0.491
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9007720947265625,
+    "eval_runtime": 0.2597,
+    "eval_samples_per_second": 30.809,
+    "eval_steps_per_second": 3.851
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.48.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9435a1147f867736d4fe643968003aa7901bea2c8ac0f3a2163bc38cddb115cc
+size 3554214752

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02643f00207dfc5ed248992486bde04314c21dca556bf65ce520690962b8db63
+size 11422965

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ],
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4500,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 3.270639151271117e+16,
+    "train_loss": 1.0707874030483013,
+    "train_runtime": 199.5779,
+    "train_samples_per_second": 3.908,
+    "train_steps_per_second": 0.491
+}

trainer_log.jsonl

@@ -0,0 +1,108 @@
+{"current_steps": 1, "total_steps": 98, "loss": 1.1572, "lr": 1e-05, "epoch": 0.01020408163265306, "percentage": 1.02, "elapsed_time": "0:00:02", "remaining_time": "0:03:26"}
+{"current_steps": 2, "total_steps": 98, "loss": 1.3198, "lr": 9.997377845227577e-06, "epoch": 0.02040816326530612, "percentage": 2.04, "elapsed_time": "0:00:04", "remaining_time": "0:03:12"}
+{"current_steps": 3, "total_steps": 98, "loss": 1.0636, "lr": 9.98951413118856e-06, "epoch": 0.030612244897959183, "percentage": 3.06, "elapsed_time": "0:00:05", "remaining_time": "0:03:06"}
+{"current_steps": 4, "total_steps": 98, "loss": 1.2853, "lr": 9.97641710583307e-06, "epoch": 0.04081632653061224, "percentage": 4.08, "elapsed_time": "0:00:07", "remaining_time": "0:03:02"}
+{"current_steps": 5, "total_steps": 98, "loss": 1.0573, "lr": 9.958100506132127e-06, "epoch": 0.05102040816326531, "percentage": 5.1, "elapsed_time": "0:00:09", "remaining_time": "0:02:59"}
+{"current_steps": 6, "total_steps": 98, "loss": 1.5486, "lr": 9.934583543669454e-06, "epoch": 0.061224489795918366, "percentage": 6.12, "elapsed_time": "0:00:11", "remaining_time": "0:02:56"}
+{"current_steps": 7, "total_steps": 98, "loss": 0.8672, "lr": 9.905890884491196e-06, "epoch": 0.07142857142857142, "percentage": 7.14, "elapsed_time": "0:00:13", "remaining_time": "0:02:53"}
+{"current_steps": 8, "total_steps": 98, "loss": 1.132, "lr": 9.872052623234632e-06, "epoch": 0.08163265306122448, "percentage": 8.16, "elapsed_time": "0:00:15", "remaining_time": "0:02:51"}
+{"current_steps": 9, "total_steps": 98, "loss": 1.2419, "lr": 9.833104251563058e-06, "epoch": 0.09183673469387756, "percentage": 9.18, "elapsed_time": "0:00:17", "remaining_time": "0:02:49"}
+{"current_steps": 10, "total_steps": 98, "loss": 0.9946, "lr": 9.789086620939936e-06, "epoch": 0.10204081632653061, "percentage": 10.2, "elapsed_time": "0:00:18", "remaining_time": "0:02:47"}
+{"current_steps": 10, "total_steps": 98, "eval_loss": 0.9807827472686768, "epoch": 0.10204081632653061, "percentage": 10.2, "elapsed_time": "0:00:19", "remaining_time": "0:02:49"}
+{"current_steps": 11, "total_steps": 98, "loss": 1.3435, "lr": 9.740045899781353e-06, "epoch": 0.11224489795918367, "percentage": 11.22, "elapsed_time": "0:00:21", "remaining_time": "0:02:47"}
+{"current_steps": 12, "total_steps": 98, "loss": 0.7463, "lr": 9.68603352503172e-06, "epoch": 0.12244897959183673, "percentage": 12.24, "elapsed_time": "0:00:23", "remaining_time": "0:02:44"}
+{"current_steps": 13, "total_steps": 98, "loss": 1.329, "lr": 9.627106148213521e-06, "epoch": 0.1326530612244898, "percentage": 13.27, "elapsed_time": "0:00:24", "remaining_time": "0:02:42"}
+{"current_steps": 14, "total_steps": 98, "loss": 1.3815, "lr": 9.563325576007702e-06, "epoch": 0.14285714285714285, "percentage": 14.29, "elapsed_time": "0:00:26", "remaining_time": "0:02:40"}
+{"current_steps": 15, "total_steps": 98, "loss": 1.0305, "lr": 9.494758705426978e-06, "epoch": 0.15306122448979592, "percentage": 15.31, "elapsed_time": "0:00:28", "remaining_time": "0:02:38"}
+{"current_steps": 16, "total_steps": 98, "loss": 1.3317, "lr": 9.421477453650118e-06, "epoch": 0.16326530612244897, "percentage": 16.33, "elapsed_time": "0:00:30", "remaining_time": "0:02:36"}
+{"current_steps": 17, "total_steps": 98, "loss": 1.323, "lr": 9.343558682590757e-06, "epoch": 0.17346938775510204, "percentage": 17.35, "elapsed_time": "0:00:32", "remaining_time": "0:02:34"}
+{"current_steps": 18, "total_steps": 98, "loss": 1.5154, "lr": 9.261084118279846e-06, "epoch": 0.1836734693877551, "percentage": 18.37, "elapsed_time": "0:00:34", "remaining_time": "0:02:32"}
+{"current_steps": 19, "total_steps": 98, "loss": 1.2371, "lr": 9.174140265146356e-06, "epoch": 0.19387755102040816, "percentage": 19.39, "elapsed_time": "0:00:36", "remaining_time": "0:02:30"}
+{"current_steps": 20, "total_steps": 98, "loss": 1.042, "lr": 9.082818315286054e-06, "epoch": 0.20408163265306123, "percentage": 20.41, "elapsed_time": "0:00:38", "remaining_time": "0:02:28"}
+{"current_steps": 20, "total_steps": 98, "eval_loss": 0.9510844945907593, "epoch": 0.20408163265306123, "percentage": 20.41, "elapsed_time": "0:00:38", "remaining_time": "0:02:29"}
+{"current_steps": 21, "total_steps": 98, "loss": 1.07, "lr": 8.987214052813605e-06, "epoch": 0.21428571428571427, "percentage": 21.43, "elapsed_time": "0:00:40", "remaining_time": "0:02:27"}
+{"current_steps": 22, "total_steps": 98, "loss": 1.2102, "lr": 8.887427753398249e-06, "epoch": 0.22448979591836735, "percentage": 22.45, "elapsed_time": "0:00:42", "remaining_time": "0:02:25"}
+{"current_steps": 23, "total_steps": 98, "loss": 1.0913, "lr": 8.783564079088478e-06, "epoch": 0.23469387755102042, "percentage": 23.47, "elapsed_time": "0:00:43", "remaining_time": "0:02:23"}
+{"current_steps": 24, "total_steps": 98, "loss": 0.8923, "lr": 8.675731968536004e-06, "epoch": 0.24489795918367346, "percentage": 24.49, "elapsed_time": "0:00:45", "remaining_time": "0:02:21"}
+{"current_steps": 25, "total_steps": 98, "loss": 1.1723, "lr": 8.564044522734147e-06, "epoch": 0.25510204081632654, "percentage": 25.51, "elapsed_time": "0:00:47", "remaining_time": "0:02:19"}
+{"current_steps": 26, "total_steps": 98, "loss": 1.1206, "lr": 8.448618886390523e-06, "epoch": 0.2653061224489796, "percentage": 26.53, "elapsed_time": "0:00:49", "remaining_time": "0:02:17"}
+{"current_steps": 27, "total_steps": 98, "loss": 1.1261, "lr": 8.329576125058406e-06, "epoch": 0.2755102040816326, "percentage": 27.55, "elapsed_time": "0:00:51", "remaining_time": "0:02:15"}
+{"current_steps": 28, "total_steps": 98, "loss": 1.2727, "lr": 8.207041098155701e-06, "epoch": 0.2857142857142857, "percentage": 28.57, "elapsed_time": "0:00:53", "remaining_time": "0:02:13"}
+{"current_steps": 29, "total_steps": 98, "loss": 1.2197, "lr": 8.081142328004638e-06, "epoch": 0.29591836734693877, "percentage": 29.59, "elapsed_time": "0:00:55", "remaining_time": "0:02:11"}
+{"current_steps": 30, "total_steps": 98, "loss": 1.1236, "lr": 7.952011865029614e-06, "epoch": 0.30612244897959184, "percentage": 30.61, "elapsed_time": "0:00:57", "remaining_time": "0:02:09"}
+{"current_steps": 30, "total_steps": 98, "eval_loss": 0.9308969974517822, "epoch": 0.30612244897959184, "percentage": 30.61, "elapsed_time": "0:00:57", "remaining_time": "0:02:09"}
+{"current_steps": 31, "total_steps": 98, "loss": 0.9098, "lr": 7.819785149254534e-06, "epoch": 0.3163265306122449, "percentage": 31.63, "elapsed_time": "0:00:59", "remaining_time": "0:02:07"}
+{"current_steps": 32, "total_steps": 98, "loss": 1.0564, "lr": 7.68460086824492e-06, "epoch": 0.32653061224489793, "percentage": 32.65, "elapsed_time": "0:01:01", "remaining_time": "0:02:05"}
+{"current_steps": 33, "total_steps": 98, "loss": 1.0174, "lr": 7.546600811643816e-06, "epoch": 0.336734693877551, "percentage": 33.67, "elapsed_time": "0:01:02", "remaining_time": "0:02:03"}
+{"current_steps": 34, "total_steps": 98, "loss": 1.1875, "lr": 7.405929722454026e-06, "epoch": 0.3469387755102041, "percentage": 34.69, "elapsed_time": "0:01:04", "remaining_time": "0:02:01"}
+{"current_steps": 35, "total_steps": 98, "loss": 0.9453, "lr": 7.262735145222696e-06, "epoch": 0.35714285714285715, "percentage": 35.71, "elapsed_time": "0:01:06", "remaining_time": "0:01:59"}
+{"current_steps": 36, "total_steps": 98, "loss": 1.0147, "lr": 7.117167271287453e-06, "epoch": 0.3673469387755102, "percentage": 36.73, "elapsed_time": "0:01:08", "remaining_time": "0:01:57"}
+{"current_steps": 37, "total_steps": 98, "loss": 0.995, "lr": 6.969378781246436e-06, "epoch": 0.37755102040816324, "percentage": 37.76, "elapsed_time": "0:01:10", "remaining_time": "0:01:56"}
+{"current_steps": 38, "total_steps": 98, "loss": 0.9636, "lr": 6.819524684817439e-06, "epoch": 0.3877551020408163, "percentage": 38.78, "elapsed_time": "0:01:12", "remaining_time": "0:01:54"}
+{"current_steps": 39, "total_steps": 98, "loss": 1.1511, "lr": 6.667762158254104e-06, "epoch": 0.3979591836734694, "percentage": 39.8, "elapsed_time": "0:01:14", "remaining_time": "0:01:52"}
+{"current_steps": 40, "total_steps": 98, "loss": 1.238, "lr": 6.514250379489754e-06, "epoch": 0.40816326530612246, "percentage": 40.82, "elapsed_time": "0:01:16", "remaining_time": "0:01:50"}
+{"current_steps": 40, "total_steps": 98, "eval_loss": 0.9210565090179443, "epoch": 0.40816326530612246, "percentage": 40.82, "elapsed_time": "0:01:16", "remaining_time": "0:01:50"}
+{"current_steps": 41, "total_steps": 98, "loss": 0.927, "lr": 6.3591503611817155e-06, "epoch": 0.41836734693877553, "percentage": 41.84, "elapsed_time": "0:01:18", "remaining_time": "0:01:48"}
+{"current_steps": 42, "total_steps": 98, "loss": 1.1018, "lr": 6.202624781831269e-06, "epoch": 0.42857142857142855, "percentage": 42.86, "elapsed_time": "0:01:20", "remaining_time": "0:01:46"}
+{"current_steps": 43, "total_steps": 98, "loss": 0.938, "lr": 6.044837815156377e-06, "epoch": 0.4387755102040816, "percentage": 43.88, "elapsed_time": "0:01:21", "remaining_time": "0:01:44"}
+{"current_steps": 44, "total_steps": 98, "loss": 1.0764, "lr": 5.885954957896115e-06, "epoch": 0.4489795918367347, "percentage": 44.9, "elapsed_time": "0:01:23", "remaining_time": "0:01:42"}
+{"current_steps": 45, "total_steps": 98, "loss": 1.2437, "lr": 5.726142856227453e-06, "epoch": 0.45918367346938777, "percentage": 45.92, "elapsed_time": "0:01:25", "remaining_time": "0:01:40"}
+{"current_steps": 46, "total_steps": 98, "loss": 1.0162, "lr": 5.5655691309764225e-06, "epoch": 0.46938775510204084, "percentage": 46.94, "elapsed_time": "0:01:27", "remaining_time": "0:01:38"}
+{"current_steps": 47, "total_steps": 98, "loss": 1.1398, "lr": 5.404402201807022e-06, "epoch": 0.47959183673469385, "percentage": 47.96, "elapsed_time": "0:01:29", "remaining_time": "0:01:36"}
+{"current_steps": 48, "total_steps": 98, "loss": 0.8257, "lr": 5.242811110572243e-06, "epoch": 0.4897959183673469, "percentage": 48.98, "elapsed_time": "0:01:31", "remaining_time": "0:01:35"}
+{"current_steps": 49, "total_steps": 98, "loss": 0.9318, "lr": 5.080965344012509e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:01:33", "remaining_time": "0:01:33"}
+{"current_steps": 50, "total_steps": 98, "loss": 0.8178, "lr": 4.919034655987493e-06, "epoch": 0.5102040816326531, "percentage": 51.02, "elapsed_time": "0:01:35", "remaining_time": "0:01:31"}
+{"current_steps": 50, "total_steps": 98, "eval_loss": 0.9119246006011963, "epoch": 0.5102040816326531, "percentage": 51.02, "elapsed_time": "0:01:35", "remaining_time": "0:01:31"}
+{"current_steps": 51, "total_steps": 98, "loss": 1.0659, "lr": 4.757188889427761e-06, "epoch": 0.5204081632653061, "percentage": 52.04, "elapsed_time": "0:01:37", "remaining_time": "0:01:29"}
+{"current_steps": 52, "total_steps": 98, "loss": 1.0016, "lr": 4.59559779819298e-06, "epoch": 0.5306122448979592, "percentage": 53.06, "elapsed_time": "0:01:39", "remaining_time": "0:01:27"}
+{"current_steps": 53, "total_steps": 98, "loss": 1.0541, "lr": 4.434430869023579e-06, "epoch": 0.5408163265306123, "percentage": 54.08, "elapsed_time": "0:01:40", "remaining_time": "0:01:25"}
+{"current_steps": 54, "total_steps": 98, "loss": 0.8034, "lr": 4.27385714377255e-06, "epoch": 0.5510204081632653, "percentage": 55.1, "elapsed_time": "0:01:42", "remaining_time": "0:01:23"}
+{"current_steps": 55, "total_steps": 98, "loss": 0.8833, "lr": 4.1140450421038865e-06, "epoch": 0.5612244897959183, "percentage": 56.12, "elapsed_time": "0:01:44", "remaining_time": "0:01:21"}
+{"current_steps": 56, "total_steps": 98, "loss": 0.8837, "lr": 3.955162184843625e-06, "epoch": 0.5714285714285714, "percentage": 57.14, "elapsed_time": "0:01:46", "remaining_time": "0:01:19"}
+{"current_steps": 57, "total_steps": 98, "loss": 1.0044, "lr": 3.7973752181687336e-06, "epoch": 0.5816326530612245, "percentage": 58.16, "elapsed_time": "0:01:48", "remaining_time": "0:01:17"}
+{"current_steps": 58, "total_steps": 98, "loss": 0.9338, "lr": 3.6408496388182857e-06, "epoch": 0.5918367346938775, "percentage": 59.18, "elapsed_time": "0:01:50", "remaining_time": "0:01:16"}
+{"current_steps": 59, "total_steps": 98, "loss": 1.1868, "lr": 3.4857496205102475e-06, "epoch": 0.6020408163265306, "percentage": 60.2, "elapsed_time": "0:01:52", "remaining_time": "0:01:14"}
+{"current_steps": 60, "total_steps": 98, "loss": 0.951, "lr": 3.3322378417458985e-06, "epoch": 0.6122448979591837, "percentage": 61.22, "elapsed_time": "0:01:54", "remaining_time": "0:01:12"}
+{"current_steps": 60, "total_steps": 98, "eval_loss": 0.9065544605255127, "epoch": 0.6122448979591837, "percentage": 61.22, "elapsed_time": "0:01:54", "remaining_time": "0:01:12"}
+{"current_steps": 61, "total_steps": 98, "loss": 1.2871, "lr": 3.180475315182563e-06, "epoch": 0.6224489795918368, "percentage": 62.24, "elapsed_time": "0:01:56", "remaining_time": "0:01:10"}
+{"current_steps": 62, "total_steps": 98, "loss": 0.9965, "lr": 3.0306212187535653e-06, "epoch": 0.6326530612244898, "percentage": 63.27, "elapsed_time": "0:01:58", "remaining_time": "0:01:08"}
+{"current_steps": 63, "total_steps": 98, "loss": 0.8174, "lr": 2.882832728712551e-06, "epoch": 0.6428571428571429, "percentage": 64.29, "elapsed_time": "0:01:59", "remaining_time": "0:01:06"}
+{"current_steps": 64, "total_steps": 98, "loss": 0.9641, "lr": 2.7372648547773063e-06, "epoch": 0.6530612244897959, "percentage": 65.31, "elapsed_time": "0:02:01", "remaining_time": "0:01:04"}
+{"current_steps": 65, "total_steps": 98, "loss": 0.8579, "lr": 2.594070277545975e-06, "epoch": 0.6632653061224489, "percentage": 66.33, "elapsed_time": "0:02:03", "remaining_time": "0:01:02"}
+{"current_steps": 66, "total_steps": 98, "loss": 0.872, "lr": 2.4533991883561868e-06, "epoch": 0.673469387755102, "percentage": 67.35, "elapsed_time": "0:02:05", "remaining_time": "0:01:00"}
+{"current_steps": 67, "total_steps": 98, "loss": 1.1029, "lr": 2.315399131755081e-06, "epoch": 0.6836734693877551, "percentage": 68.37, "elapsed_time": "0:02:07", "remaining_time": "0:00:58"}
+{"current_steps": 68, "total_steps": 98, "loss": 0.8727, "lr": 2.1802148507454675e-06, "epoch": 0.6938775510204082, "percentage": 69.39, "elapsed_time": "0:02:09", "remaining_time": "0:00:57"}
+{"current_steps": 69, "total_steps": 98, "loss": 0.9211, "lr": 2.0479881349703885e-06, "epoch": 0.7040816326530612, "percentage": 70.41, "elapsed_time": "0:02:11", "remaining_time": "0:00:55"}
+{"current_steps": 70, "total_steps": 98, "loss": 0.7869, "lr": 1.9188576719953635e-06, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:02:13", "remaining_time": "0:00:53"}
+{"current_steps": 70, "total_steps": 98, "eval_loss": 0.9032285809516907, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:02:13", "remaining_time": "0:00:53"}
+{"current_steps": 71, "total_steps": 98, "loss": 1.1762, "lr": 1.7929589018443016e-06, "epoch": 0.7244897959183674, "percentage": 72.45, "elapsed_time": "0:02:15", "remaining_time": "0:00:51"}
+{"current_steps": 72, "total_steps": 98, "loss": 1.0489, "lr": 1.6704238749415958e-06, "epoch": 0.7346938775510204, "percentage": 73.47, "elapsed_time": "0:02:17", "remaining_time": "0:00:49"}
+{"current_steps": 73, "total_steps": 98, "loss": 0.8249, "lr": 1.5513811136094786e-06, "epoch": 0.7448979591836735, "percentage": 74.49, "elapsed_time": "0:02:18", "remaining_time": "0:00:47"}
+{"current_steps": 74, "total_steps": 98, "loss": 1.0011, "lr": 1.4359554772658551e-06, "epoch": 0.7551020408163265, "percentage": 75.51, "elapsed_time": "0:02:20", "remaining_time": "0:00:45"}
+{"current_steps": 75, "total_steps": 98, "loss": 1.0774, "lr": 1.3242680314639995e-06, "epoch": 0.7653061224489796, "percentage": 76.53, "elapsed_time": "0:02:22", "remaining_time": "0:00:43"}
+{"current_steps": 76, "total_steps": 98, "loss": 1.1492, "lr": 1.2164359209115235e-06, "epoch": 0.7755102040816326, "percentage": 77.55, "elapsed_time": "0:02:24", "remaining_time": "0:00:41"}
+{"current_steps": 77, "total_steps": 98, "loss": 1.1329, "lr": 1.1125722466017547e-06, "epoch": 0.7857142857142857, "percentage": 78.57, "elapsed_time": "0:02:26", "remaining_time": "0:00:39"}
+{"current_steps": 78, "total_steps": 98, "loss": 0.9375, "lr": 1.012785947186397e-06, "epoch": 0.7959183673469388, "percentage": 79.59, "elapsed_time": "0:02:28", "remaining_time": "0:00:38"}
+{"current_steps": 79, "total_steps": 98, "loss": 1.0936, "lr": 9.171816847139447e-07, "epoch": 0.8061224489795918, "percentage": 80.61, "elapsed_time": "0:02:30", "remaining_time": "0:00:36"}
+{"current_steps": 80, "total_steps": 98, "loss": 1.2626, "lr": 8.258597348536452e-07, "epoch": 0.8163265306122449, "percentage": 81.63, "elapsed_time": "0:02:32", "remaining_time": "0:00:34"}
+{"current_steps": 80, "total_steps": 98, "eval_loss": 0.9012266397476196, "epoch": 0.8163265306122449, "percentage": 81.63, "elapsed_time": "0:02:32", "remaining_time": "0:00:34"}
+{"current_steps": 81, "total_steps": 98, "loss": 1.3479, "lr": 7.389158817201541e-07, "epoch": 0.826530612244898, "percentage": 82.65, "elapsed_time": "0:02:34", "remaining_time": "0:00:32"}
+{"current_steps": 82, "total_steps": 98, "loss": 0.9699, "lr": 6.564413174092443e-07, "epoch": 0.8367346938775511, "percentage": 83.67, "elapsed_time": "0:02:36", "remaining_time": "0:00:30"}
+{"current_steps": 83, "total_steps": 98, "loss": 1.1757, "lr": 5.785225463498828e-07, "epoch": 0.8469387755102041, "percentage": 84.69, "elapsed_time": "0:02:37", "remaining_time": "0:00:28"}
+{"current_steps": 84, "total_steps": 98, "loss": 1.1877, "lr": 5.05241294573024e-07, "epoch": 0.8571428571428571, "percentage": 85.71, "elapsed_time": "0:02:39", "remaining_time": "0:00:26"}
+{"current_steps": 85, "total_steps": 98, "loss": 0.9878, "lr": 4.3667442399229985e-07, "epoch": 0.8673469387755102, "percentage": 86.73, "elapsed_time": "0:02:41", "remaining_time": "0:00:24"}
+{"current_steps": 86, "total_steps": 98, "loss": 1.145, "lr": 3.728938517864794e-07, "epoch": 0.8775510204081632, "percentage": 87.76, "elapsed_time": "0:02:43", "remaining_time": "0:00:22"}
+{"current_steps": 87, "total_steps": 98, "loss": 1.128, "lr": 3.1396647496828245e-07, "epoch": 0.8877551020408163, "percentage": 88.78, "elapsed_time": "0:02:45", "remaining_time": "0:00:20"}
+{"current_steps": 88, "total_steps": 98, "loss": 0.9712, "lr": 2.599541002186479e-07, "epoch": 0.8979591836734694, "percentage": 89.8, "elapsed_time": "0:02:47", "remaining_time": "0:00:19"}
+{"current_steps": 89, "total_steps": 98, "loss": 0.9278, "lr": 2.109133790600648e-07, "epoch": 0.9081632653061225, "percentage": 90.82, "elapsed_time": "0:02:49", "remaining_time": "0:00:17"}
+{"current_steps": 90, "total_steps": 98, "loss": 1.2385, "lr": 1.6689574843694433e-07, "epoch": 0.9183673469387755, "percentage": 91.84, "elapsed_time": "0:02:51", "remaining_time": "0:00:15"}
+{"current_steps": 90, "total_steps": 98, "eval_loss": 0.9008685350418091, "epoch": 0.9183673469387755, "percentage": 91.84, "elapsed_time": "0:02:51", "remaining_time": "0:00:15"}
+{"current_steps": 91, "total_steps": 98, "loss": 1.0866, "lr": 1.2794737676536993e-07, "epoch": 0.9285714285714286, "percentage": 92.86, "elapsed_time": "0:02:53", "remaining_time": "0:00:13"}
+{"current_steps": 92, "total_steps": 98, "loss": 1.0466, "lr": 9.410911550880474e-08, "epoch": 0.9387755102040817, "percentage": 93.88, "elapsed_time": "0:02:55", "remaining_time": "0:00:11"}
+{"current_steps": 93, "total_steps": 98, "loss": 0.8466, "lr": 6.54164563305465e-08, "epoch": 0.9489795918367347, "percentage": 94.9, "elapsed_time": "0:02:56", "remaining_time": "0:00:09"}
+{"current_steps": 94, "total_steps": 98, "loss": 1.1521, "lr": 4.189949386787462e-08, "epoch": 0.9591836734693877, "percentage": 95.92, "elapsed_time": "0:02:58", "remaining_time": "0:00:07"}
+{"current_steps": 95, "total_steps": 98, "loss": 1.1505, "lr": 2.358289416693027e-08, "epoch": 0.9693877551020408, "percentage": 96.94, "elapsed_time": "0:03:00", "remaining_time": "0:00:05"}
+{"current_steps": 96, "total_steps": 98, "loss": 0.9055, "lr": 1.0485868811441757e-08, "epoch": 0.9795918367346939, "percentage": 97.96, "elapsed_time": "0:03:02", "remaining_time": "0:00:03"}
+{"current_steps": 97, "total_steps": 98, "loss": 1.0224, "lr": 2.6221547724253337e-09, "epoch": 0.9897959183673469, "percentage": 98.98, "elapsed_time": "0:03:04", "remaining_time": "0:00:01"}
+{"current_steps": 98, "total_steps": 98, "loss": 0.9534, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:06", "remaining_time": "0:00:00"}
+{"current_steps": 98, "total_steps": 98, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:18", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,800 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 10,
+  "global_step": 98,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01020408163265306,
+      "grad_norm": 1.5935372114181519,
+      "learning_rate": 1e-05,
+      "loss": 1.1572,
+      "step": 1
+    },
+    {
+      "epoch": 0.02040816326530612,
+      "grad_norm": 1.8600682020187378,
+      "learning_rate": 9.997377845227577e-06,
+      "loss": 1.3198,
+      "step": 2
+    },
+    {
+      "epoch": 0.030612244897959183,
+      "grad_norm": 1.662075400352478,
+      "learning_rate": 9.98951413118856e-06,
+      "loss": 1.0636,
+      "step": 3
+    },
+    {
+      "epoch": 0.04081632653061224,
+      "grad_norm": 1.6947352886199951,
+      "learning_rate": 9.97641710583307e-06,
+      "loss": 1.2853,
+      "step": 4
+    },
+    {
+      "epoch": 0.05102040816326531,
+      "grad_norm": 1.231564998626709,
+      "learning_rate": 9.958100506132127e-06,
+      "loss": 1.0573,
+      "step": 5
+    },
+    {
+      "epoch": 0.061224489795918366,
+      "grad_norm": 1.550899863243103,
+      "learning_rate": 9.934583543669454e-06,
+      "loss": 1.5486,
+      "step": 6
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 1.017148733139038,
+      "learning_rate": 9.905890884491196e-06,
+      "loss": 0.8672,
+      "step": 7
+    },
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 1.2291380167007446,
+      "learning_rate": 9.872052623234632e-06,
+      "loss": 1.132,
+      "step": 8
+    },
+    {
+      "epoch": 0.09183673469387756,
+      "grad_norm": 1.1650055646896362,
+      "learning_rate": 9.833104251563058e-06,
+      "loss": 1.2419,
+      "step": 9
+    },
+    {
+      "epoch": 0.10204081632653061,
+      "grad_norm": 0.9753865003585815,
+      "learning_rate": 9.789086620939936e-06,
+      "loss": 0.9946,
+      "step": 10
+    },
+    {
+      "epoch": 0.10204081632653061,
+      "eval_loss": 0.9807827472686768,
+      "eval_runtime": 0.2604,
+      "eval_samples_per_second": 30.717,
+      "eval_steps_per_second": 3.84,
+      "step": 10
+    },
+    {
+      "epoch": 0.11224489795918367,
+      "grad_norm": 1.191615343093872,
+      "learning_rate": 9.740045899781353e-06,
+      "loss": 1.3435,
+      "step": 11
+    },
+    {
+      "epoch": 0.12244897959183673,
+      "grad_norm": 0.9799769520759583,
+      "learning_rate": 9.68603352503172e-06,
+      "loss": 0.7463,
+      "step": 12
+    },
+    {
+      "epoch": 0.1326530612244898,
+      "grad_norm": 1.0710457563400269,
+      "learning_rate": 9.627106148213521e-06,
+      "loss": 1.329,
+      "step": 13
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 1.071432113647461,
+      "learning_rate": 9.563325576007702e-06,
+      "loss": 1.3815,
+      "step": 14
+    },
+    {
+      "epoch": 0.15306122448979592,
+      "grad_norm": 0.9442039132118225,
+      "learning_rate": 9.494758705426978e-06,
+      "loss": 1.0305,
+      "step": 15
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 1.022035837173462,
+      "learning_rate": 9.421477453650118e-06,
+      "loss": 1.3317,
+      "step": 16
+    },
+    {
+      "epoch": 0.17346938775510204,
+      "grad_norm": 1.0751738548278809,
+      "learning_rate": 9.343558682590757e-06,
+      "loss": 1.323,
+      "step": 17
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": 1.0566898584365845,
+      "learning_rate": 9.261084118279846e-06,
+      "loss": 1.5154,
+      "step": 18
+    },
+    {
+      "epoch": 0.19387755102040816,
+      "grad_norm": 1.0009628534317017,
+      "learning_rate": 9.174140265146356e-06,
+      "loss": 1.2371,
+      "step": 19
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 0.9259373545646667,
+      "learning_rate": 9.082818315286054e-06,
+      "loss": 1.042,
+      "step": 20
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "eval_loss": 0.9510844945907593,
+      "eval_runtime": 0.2601,
+      "eval_samples_per_second": 30.76,
+      "eval_steps_per_second": 3.845,
+      "step": 20
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.9078995585441589,
+      "learning_rate": 8.987214052813605e-06,
+      "loss": 1.07,
+      "step": 21
+    },
+    {
+      "epoch": 0.22448979591836735,
+      "grad_norm": 0.9820942282676697,
+      "learning_rate": 8.887427753398249e-06,
+      "loss": 1.2102,
+      "step": 22
+    },
+    {
+      "epoch": 0.23469387755102042,
+      "grad_norm": 1.0587691068649292,
+      "learning_rate": 8.783564079088478e-06,
+      "loss": 1.0913,
+      "step": 23
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 0.8137860894203186,
+      "learning_rate": 8.675731968536004e-06,
+      "loss": 0.8923,
+      "step": 24
+    },
+    {
+      "epoch": 0.25510204081632654,
+      "grad_norm": 0.9471170902252197,
+      "learning_rate": 8.564044522734147e-06,
+      "loss": 1.1723,
+      "step": 25
+    },
+    {
+      "epoch": 0.2653061224489796,
+      "grad_norm": 0.8885685205459595,
+      "learning_rate": 8.448618886390523e-06,
+      "loss": 1.1206,
+      "step": 26
+    },
+    {
+      "epoch": 0.2755102040816326,
+      "grad_norm": 0.8613781332969666,
+      "learning_rate": 8.329576125058406e-06,
+      "loss": 1.1261,
+      "step": 27
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.9407626986503601,
+      "learning_rate": 8.207041098155701e-06,
+      "loss": 1.2727,
+      "step": 28
+    },
+    {
+      "epoch": 0.29591836734693877,
+      "grad_norm": 0.8954651951789856,
+      "learning_rate": 8.081142328004638e-06,
+      "loss": 1.2197,
+      "step": 29
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 0.8864608407020569,
+      "learning_rate": 7.952011865029614e-06,
+      "loss": 1.1236,
+      "step": 30
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "eval_loss": 0.9308969974517822,
+      "eval_runtime": 0.2599,
+      "eval_samples_per_second": 30.775,
+      "eval_steps_per_second": 3.847,
+      "step": 30
+    },
+    {
+      "epoch": 0.3163265306122449,
+      "grad_norm": 0.8076571226119995,
+      "learning_rate": 7.819785149254534e-06,
+      "loss": 0.9098,
+      "step": 31
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.8902921080589294,
+      "learning_rate": 7.68460086824492e-06,
+      "loss": 1.0564,
+      "step": 32
+    },
+    {
+      "epoch": 0.336734693877551,
+      "grad_norm": 0.9010928273200989,
+      "learning_rate": 7.546600811643816e-06,
+      "loss": 1.0174,
+      "step": 33
+    },
+    {
+      "epoch": 0.3469387755102041,
+      "grad_norm": 0.8672641515731812,
+      "learning_rate": 7.405929722454026e-06,
+      "loss": 1.1875,
+      "step": 34
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.7878830432891846,
+      "learning_rate": 7.262735145222696e-06,
+      "loss": 0.9453,
+      "step": 35
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 0.85221266746521,
+      "learning_rate": 7.117167271287453e-06,
+      "loss": 1.0147,
+      "step": 36
+    },
+    {
+      "epoch": 0.37755102040816324,
+      "grad_norm": 0.8591777682304382,
+      "learning_rate": 6.969378781246436e-06,
+      "loss": 0.995,
+      "step": 37
+    },
+    {
+      "epoch": 0.3877551020408163,
+      "grad_norm": 0.9585978388786316,
+      "learning_rate": 6.819524684817439e-06,
+      "loss": 0.9636,
+      "step": 38
+    },
+    {
+      "epoch": 0.3979591836734694,
+      "grad_norm": 0.9561256170272827,
+      "learning_rate": 6.667762158254104e-06,
+      "loss": 1.1511,
+      "step": 39
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.9076462388038635,
+      "learning_rate": 6.514250379489754e-06,
+      "loss": 1.238,
+      "step": 40
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "eval_loss": 0.9210565090179443,
+      "eval_runtime": 0.26,
+      "eval_samples_per_second": 30.764,
+      "eval_steps_per_second": 3.846,
+      "step": 40
+    },
+    {
+      "epoch": 0.41836734693877553,
+      "grad_norm": 0.779888391494751,
+      "learning_rate": 6.3591503611817155e-06,
+      "loss": 0.927,
+      "step": 41
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.826004147529602,
+      "learning_rate": 6.202624781831269e-06,
+      "loss": 1.1018,
+      "step": 42
+    },
+    {
+      "epoch": 0.4387755102040816,
+      "grad_norm": 0.8641281127929688,
+      "learning_rate": 6.044837815156377e-06,
+      "loss": 0.938,
+      "step": 43
+    },
+    {
+      "epoch": 0.4489795918367347,
+      "grad_norm": 0.896023154258728,
+      "learning_rate": 5.885954957896115e-06,
+      "loss": 1.0764,
+      "step": 44
+    },
+    {
+      "epoch": 0.45918367346938777,
+      "grad_norm": 0.9072222709655762,
+      "learning_rate": 5.726142856227453e-06,
+      "loss": 1.2437,
+      "step": 45
+    },
+    {
+      "epoch": 0.46938775510204084,
+      "grad_norm": 0.7771997451782227,
+      "learning_rate": 5.5655691309764225e-06,
+      "loss": 1.0162,
+      "step": 46
+    },
+    {
+      "epoch": 0.47959183673469385,
+      "grad_norm": 0.8864902853965759,
+      "learning_rate": 5.404402201807022e-06,
+      "loss": 1.1398,
+      "step": 47
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.702143669128418,
+      "learning_rate": 5.242811110572243e-06,
+      "loss": 0.8257,
+      "step": 48
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.7524011731147766,
+      "learning_rate": 5.080965344012509e-06,
+      "loss": 0.9318,
+      "step": 49
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "grad_norm": 0.7233298420906067,
+      "learning_rate": 4.919034655987493e-06,
+      "loss": 0.8178,
+      "step": 50
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "eval_loss": 0.9119246006011963,
+      "eval_runtime": 0.2595,
+      "eval_samples_per_second": 30.823,
+      "eval_steps_per_second": 3.853,
+      "step": 50
+    },
+    {
+      "epoch": 0.5204081632653061,
+      "grad_norm": 0.8432551622390747,
+      "learning_rate": 4.757188889427761e-06,
+      "loss": 1.0659,
+      "step": 51
+    },
+    {
+      "epoch": 0.5306122448979592,
+      "grad_norm": 0.772146999835968,
+      "learning_rate": 4.59559779819298e-06,
+      "loss": 1.0016,
+      "step": 52
+    },
+    {
+      "epoch": 0.5408163265306123,
+      "grad_norm": 0.8176573514938354,
+      "learning_rate": 4.434430869023579e-06,
+      "loss": 1.0541,
+      "step": 53
+    },
+    {
+      "epoch": 0.5510204081632653,
+      "grad_norm": 0.730097770690918,
+      "learning_rate": 4.27385714377255e-06,
+      "loss": 0.8034,
+      "step": 54
+    },
+    {
+      "epoch": 0.5612244897959183,
+      "grad_norm": 0.7190036177635193,
+      "learning_rate": 4.1140450421038865e-06,
+      "loss": 0.8833,
+      "step": 55
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.732845664024353,
+      "learning_rate": 3.955162184843625e-06,
+      "loss": 0.8837,
+      "step": 56
+    },
+    {
+      "epoch": 0.5816326530612245,
+      "grad_norm": 0.770910918712616,
+      "learning_rate": 3.7973752181687336e-06,
+      "loss": 1.0044,
+      "step": 57
+    },
+    {
+      "epoch": 0.5918367346938775,
+      "grad_norm": 0.7635073065757751,
+      "learning_rate": 3.6408496388182857e-06,
+      "loss": 0.9338,
+      "step": 58
+    },
+    {
+      "epoch": 0.6020408163265306,
+      "grad_norm": 0.8665493130683899,
+      "learning_rate": 3.4857496205102475e-06,
+      "loss": 1.1868,
+      "step": 59
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.7718795537948608,
+      "learning_rate": 3.3322378417458985e-06,
+      "loss": 0.951,
+      "step": 60
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "eval_loss": 0.9065544605255127,
+      "eval_runtime": 0.2595,
+      "eval_samples_per_second": 30.831,
+      "eval_steps_per_second": 3.854,
+      "step": 60
+    },
+    {
+      "epoch": 0.6224489795918368,
+      "grad_norm": 0.932878851890564,
+      "learning_rate": 3.180475315182563e-06,
+      "loss": 1.2871,
+      "step": 61
+    },
+    {
+      "epoch": 0.6326530612244898,
+      "grad_norm": 0.8946093320846558,
+      "learning_rate": 3.0306212187535653e-06,
+      "loss": 0.9965,
+      "step": 62
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.7468050718307495,
+      "learning_rate": 2.882832728712551e-06,
+      "loss": 0.8174,
+      "step": 63
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.7200383543968201,
+      "learning_rate": 2.7372648547773063e-06,
+      "loss": 0.9641,
+      "step": 64
+    },
+    {
+      "epoch": 0.6632653061224489,
+      "grad_norm": 0.7331112623214722,
+      "learning_rate": 2.594070277545975e-06,
+      "loss": 0.8579,
+      "step": 65
+    },
+    {
+      "epoch": 0.673469387755102,
+      "grad_norm": 0.713594377040863,
+      "learning_rate": 2.4533991883561868e-06,
+      "loss": 0.872,
+      "step": 66
+    },
+    {
+      "epoch": 0.6836734693877551,
+      "grad_norm": 0.8468301296234131,
+      "learning_rate": 2.315399131755081e-06,
+      "loss": 1.1029,
+      "step": 67
+    },
+    {
+      "epoch": 0.6938775510204082,
+      "grad_norm": 0.7141689658164978,
+      "learning_rate": 2.1802148507454675e-06,
+      "loss": 0.8727,
+      "step": 68
+    },
+    {
+      "epoch": 0.7040816326530612,
+      "grad_norm": 0.7567382454872131,
+      "learning_rate": 2.0479881349703885e-06,
+      "loss": 0.9211,
+      "step": 69
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.7020692825317383,
+      "learning_rate": 1.9188576719953635e-06,
+      "loss": 0.7869,
+      "step": 70
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "eval_loss": 0.9032285809516907,
+      "eval_runtime": 0.2594,
+      "eval_samples_per_second": 30.835,
+      "eval_steps_per_second": 3.854,
+      "step": 70
+    },
+    {
+      "epoch": 0.7244897959183674,
+      "grad_norm": 0.853243350982666,
+      "learning_rate": 1.7929589018443016e-06,
+      "loss": 1.1762,
+      "step": 71
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 0.8287662267684937,
+      "learning_rate": 1.6704238749415958e-06,
+      "loss": 1.0489,
+      "step": 72
+    },
+    {
+      "epoch": 0.7448979591836735,
+      "grad_norm": 0.6973975300788879,
+      "learning_rate": 1.5513811136094786e-06,
+      "loss": 0.8249,
+      "step": 73
+    },
+    {
+      "epoch": 0.7551020408163265,
+      "grad_norm": 0.8150553703308105,
+      "learning_rate": 1.4359554772658551e-06,
+      "loss": 1.0011,
+      "step": 74
+    },
+    {
+      "epoch": 0.7653061224489796,
+      "grad_norm": 0.7974684238433838,
+      "learning_rate": 1.3242680314639995e-06,
+      "loss": 1.0774,
+      "step": 75
+    },
+    {
+      "epoch": 0.7755102040816326,
+      "grad_norm": 0.8233014941215515,
+      "learning_rate": 1.2164359209115235e-06,
+      "loss": 1.1492,
+      "step": 76
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.8305495977401733,
+      "learning_rate": 1.1125722466017547e-06,
+      "loss": 1.1329,
+      "step": 77
+    },
+    {
+      "epoch": 0.7959183673469388,
+      "grad_norm": 0.7523290514945984,
+      "learning_rate": 1.012785947186397e-06,
+      "loss": 0.9375,
+      "step": 78
+    },
+    {
+      "epoch": 0.8061224489795918,
+      "grad_norm": 0.8073377013206482,
+      "learning_rate": 9.171816847139447e-07,
+      "loss": 1.0936,
+      "step": 79
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.8685086965560913,
+      "learning_rate": 8.258597348536452e-07,
+      "loss": 1.2626,
+      "step": 80
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "eval_loss": 0.9012266397476196,
+      "eval_runtime": 0.2595,
+      "eval_samples_per_second": 30.833,
+      "eval_steps_per_second": 3.854,
+      "step": 80
+    },
+    {
+      "epoch": 0.826530612244898,
+      "grad_norm": 0.877649188041687,
+      "learning_rate": 7.389158817201541e-07,
+      "loss": 1.3479,
+      "step": 81
+    },
+    {
+      "epoch": 0.8367346938775511,
+      "grad_norm": 0.7652468085289001,
+      "learning_rate": 6.564413174092443e-07,
+      "loss": 0.9699,
+      "step": 82
+    },
+    {
+      "epoch": 0.8469387755102041,
+      "grad_norm": 0.8436093926429749,
+      "learning_rate": 5.785225463498828e-07,
+      "loss": 1.1757,
+      "step": 83
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.8732744455337524,
+      "learning_rate": 5.05241294573024e-07,
+      "loss": 1.1877,
+      "step": 84
+    },
+    {
+      "epoch": 0.8673469387755102,
+      "grad_norm": 0.7433239221572876,
+      "learning_rate": 4.3667442399229985e-07,
+      "loss": 0.9878,
+      "step": 85
+    },
+    {
+      "epoch": 0.8775510204081632,
+      "grad_norm": 0.8225981593132019,
+      "learning_rate": 3.728938517864794e-07,
+      "loss": 1.145,
+      "step": 86
+    },
+    {
+      "epoch": 0.8877551020408163,
+      "grad_norm": 0.8591734170913696,
+      "learning_rate": 3.1396647496828245e-07,
+      "loss": 1.128,
+      "step": 87
+    },
+    {
+      "epoch": 0.8979591836734694,
+      "grad_norm": 0.7502849102020264,
+      "learning_rate": 2.599541002186479e-07,
+      "loss": 0.9712,
+      "step": 88
+    },
+    {
+      "epoch": 0.9081632653061225,
+      "grad_norm": 0.7429087162017822,
+      "learning_rate": 2.109133790600648e-07,
+      "loss": 0.9278,
+      "step": 89
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "grad_norm": 0.8890379667282104,
+      "learning_rate": 1.6689574843694433e-07,
+      "loss": 1.2385,
+      "step": 90
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "eval_loss": 0.9008685350418091,
+      "eval_runtime": 0.2594,
+      "eval_samples_per_second": 30.837,
+      "eval_steps_per_second": 3.855,
+      "step": 90
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.9237527251243591,
+      "learning_rate": 1.2794737676536993e-07,
+      "loss": 1.0866,
+      "step": 91
+    },
+    {
+      "epoch": 0.9387755102040817,
+      "grad_norm": 0.8110918402671814,
+      "learning_rate": 9.410911550880474e-08,
+      "loss": 1.0466,
+      "step": 92
+    },
+    {
+      "epoch": 0.9489795918367347,
+      "grad_norm": 0.7134807109832764,
+      "learning_rate": 6.54164563305465e-08,
+      "loss": 0.8466,
+      "step": 93
+    },
+    {
+      "epoch": 0.9591836734693877,
+      "grad_norm": 0.8616638779640198,
+      "learning_rate": 4.189949386787462e-08,
+      "loss": 1.1521,
+      "step": 94
+    },
+    {
+      "epoch": 0.9693877551020408,
+      "grad_norm": 0.9501765966415405,
+      "learning_rate": 2.358289416693027e-08,
+      "loss": 1.1505,
+      "step": 95
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.7652553915977478,
+      "learning_rate": 1.0485868811441757e-08,
+      "loss": 0.9055,
+      "step": 96
+    },
+    {
+      "epoch": 0.9897959183673469,
+      "grad_norm": 0.862601637840271,
+      "learning_rate": 2.6221547724253337e-09,
+      "loss": 1.0224,
+      "step": 97
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.712780773639679,
+      "learning_rate": 0.0,
+      "loss": 0.9534,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "step": 98,
+      "total_flos": 3.270639151271117e+16,
+      "train_loss": 1.0707874030483013,
+      "train_runtime": 199.5779,
+      "train_samples_per_second": 3.908,
+      "train_steps_per_second": 0.491
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 98,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 98,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.270639151271117e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ff4a2daceec38620085408ea7ead1959ffc0205553c71886db48306f253159
+size 7416