superklein18/test

README.md

@@ -1,10 +1,11 @@
 ---
-base_model: microsoft/Phi-3.5-mini-instruct
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 library_name: peft
 license: mit
 tags:
 - trl
 - sft
+- finetuned
 - generated_from_trainer
 model-index:
 - name: outputs
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
+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 an unknown dataset.
 
 ## Model description
 
@@ -36,7 +37,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 1
+- train_batch_size: 4
 - eval_batch_size: 16
 - seed: 3407
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

adapter_config.json

@@ -1,10 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "Phi3ForCausalLM",
-    "parent_library": "transformers_modules.microsoft.Phi-3.5-mini-instruct.3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca.modeling_phi3"
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2"
   },
-  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -24,12 +24,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
+    "gate_proj",
     "down_proj",
+    "o_proj",
     "up_proj",
-    "v_proj",
     "q_proj",
-    "gate_proj",
-    "o_proj"
+    "v_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a815b75fe028f594998833ba1dc590089bfe3694cbea3ae4b8d8fd388c4a7a6
-size 35668592
+oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
+size 40

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 0.0,
-    "train_loss": 0.5319549602828002,
-    "train_runtime": 55.3499,
-    "train_samples_per_second": 3.668,
-    "train_steps_per_second": 3.668
+    "train_loss": 0.1567674662395578,
+    "train_runtime": 349.2812,
+    "train_samples_per_second": 4.272,
+    "train_steps_per_second": 1.068
 }

config.json

@@ -0,0 +1,29 @@
+{
+  "_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_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

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": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52685fab0e3fe31ab3d22be9347155dc8a4164ca4ea95785a467cf7549976873
+size 3554214752

special_tokens_map.json

@@ -1,24 +1,17 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<｜begin▁of▁sentence｜>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<｜end▁of▁sentence｜>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<｜end▁of▁sentence｜>"
 }

tokenizer_config.json

@@ -1,132 +1,194 @@
 {
-  "add_bos_token": false,
+  "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "151644": {
+      "content": "<｜User｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "2": {
-      "content": "</s>",
+    "151645": {
+      "content": "<｜Assistant｜>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32000": {
-      "content": "<|endoftext|>",
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32001": {
-      "content": "<|assistant|>",
+    "151647": {
+      "content": "<|EOT|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32002": {
-      "content": "<|placeholder1|>",
+    "151648": {
+      "content": "<think>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32003": {
-      "content": "<|placeholder2|>",
+    "151649": {
+      "content": "</think>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32004": {
-      "content": "<|placeholder3|>",
+    "151650": {
+      "content": "<|quad_start|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32005": {
-      "content": "<|placeholder4|>",
+    "151651": {
+      "content": "<|quad_end|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32006": {
-      "content": "<|system|>",
+    "151652": {
+      "content": "<|vision_start|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32007": {
-      "content": "<|end|>",
+    "151653": {
+      "content": "<|vision_end|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32008": {
-      "content": "<|placeholder5|>",
+    "151654": {
+      "content": "<|vision_pad|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32009": {
-      "content": "<|placeholder6|>",
+    "151655": {
+      "content": "<|image_pad|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32010": {
-      "content": "<|user|>",
+    "151656": {
+      "content": "<|video_pad|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "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
     }
   },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "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｜><think>\\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "legacy": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
   "model_max_length": 2048,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
+  "pad_token": "<｜end▁of▁sentence｜>",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
+  "unk_token": null,
   "use_default_system_prompt": false
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 0.0,
-    "train_loss": 0.5319549602828002,
-    "train_runtime": 55.3499,
-    "train_samples_per_second": 3.668,
-    "train_steps_per_second": 3.668
+    "train_loss": 0.1567674662395578,
+    "train_runtime": 349.2812,
+    "train_samples_per_second": 4.272,
+    "train_steps_per_second": 1.068
 }

trainer_state.json

@@ -3,163 +3,296 @@
   "best_model_checkpoint": null,
   "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 203,
+  "global_step": 373,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.04926108374384237,
-      "grad_norm": 2.7416231632232666,
-      "learning_rate": 9.507389162561576e-05,
-      "loss": 3.0533,
+      "epoch": 0.02680965147453083,
+      "grad_norm": 0.08274202048778534,
+      "learning_rate": 9.731903485254692e-05,
+      "loss": 5.8472,
       "step": 10
     },
     {
-      "epoch": 0.09852216748768473,
-      "grad_norm": 1.8756747245788574,
-      "learning_rate": 9.014778325123154e-05,
-      "loss": 0.4214,
+      "epoch": 0.05361930294906166,
+      "grad_norm": 0.03481147810816765,
+      "learning_rate": 9.463806970509384e-05,
+      "loss": 0.0001,
       "step": 20
     },
     {
-      "epoch": 0.1477832512315271,
-      "grad_norm": 1.4831429719924927,
-      "learning_rate": 8.52216748768473e-05,
-      "loss": 0.4639,
+      "epoch": 0.08042895442359249,
+      "grad_norm": 0.03238165006041527,
+      "learning_rate": 9.195710455764074e-05,
+      "loss": 0.0,
       "step": 30
     },
     {
-      "epoch": 0.19704433497536947,
-      "grad_norm": 1.7727338075637817,
-      "learning_rate": 8.029556650246307e-05,
-      "loss": 0.3722,
+      "epoch": 0.10723860589812333,
+      "grad_norm": 0.030895311385393143,
+      "learning_rate": 8.927613941018768e-05,
+      "loss": 0.0,
       "step": 40
     },
     {
-      "epoch": 0.24630541871921183,
-      "grad_norm": 0.9307169914245605,
-      "learning_rate": 7.536945812807882e-05,
-      "loss": 0.3516,
+      "epoch": 0.13404825737265416,
+      "grad_norm": 0.029906680807471275,
+      "learning_rate": 8.65951742627346e-05,
+      "loss": 0.0,
       "step": 50
     },
     {
-      "epoch": 0.2955665024630542,
-      "grad_norm": 0.7861897349357605,
-      "learning_rate": 7.044334975369458e-05,
-      "loss": 0.3897,
+      "epoch": 0.16085790884718498,
+      "grad_norm": 0.029279008507728577,
+      "learning_rate": 8.391420911528151e-05,
+      "loss": 0.0,
       "step": 60
     },
     {
-      "epoch": 0.3448275862068966,
-      "grad_norm": 1.2244670391082764,
-      "learning_rate": 6.551724137931034e-05,
-      "loss": 0.4396,
+      "epoch": 0.1876675603217158,
+      "grad_norm": 0.028912600129842758,
+      "learning_rate": 8.123324396782842e-05,
+      "loss": 0.0,
       "step": 70
     },
     {
-      "epoch": 0.39408866995073893,
-      "grad_norm": 0.8233121037483215,
-      "learning_rate": 6.0591133004926113e-05,
-      "loss": 0.3135,
+      "epoch": 0.1876675603217158,
+      "eval_runtime": 27.496,
+      "eval_samples_per_second": 13.566,
+      "eval_steps_per_second": 0.873,
+      "step": 70
+    },
+    {
+      "epoch": 0.21447721179624665,
+      "grad_norm": 0.028546025976538658,
+      "learning_rate": 7.855227882037533e-05,
+      "loss": 0.0,
       "step": 80
     },
     {
-      "epoch": 0.4433497536945813,
-      "grad_norm": 3.173562526702881,
-      "learning_rate": 5.566502463054187e-05,
-      "loss": 0.6026,
+      "epoch": 0.24128686327077747,
+      "grad_norm": 0.028238529339432716,
+      "learning_rate": 7.587131367292225e-05,
+      "loss": 0.0,
       "step": 90
     },
     {
-      "epoch": 0.49261083743842365,
-      "grad_norm": 1.5332086086273193,
-      "learning_rate": 5.0738916256157644e-05,
-      "loss": 0.386,
+      "epoch": 0.2680965147453083,
+      "grad_norm": 0.02808106318116188,
+      "learning_rate": 7.319034852546918e-05,
+      "loss": 0.0,
       "step": 100
     },
     {
-      "epoch": 0.541871921182266,
-      "grad_norm": 1.3006514310836792,
-      "learning_rate": 4.58128078817734e-05,
-      "loss": 0.3327,
+      "epoch": 0.2949061662198391,
+      "grad_norm": 0.02785572223365307,
+      "learning_rate": 7.050938337801609e-05,
+      "loss": 0.0,
       "step": 110
     },
     {
-      "epoch": 0.5911330049261084,
-      "grad_norm": 1.4627310037612915,
-      "learning_rate": 4.088669950738917e-05,
-      "loss": 0.329,
+      "epoch": 0.32171581769436997,
+      "grad_norm": 0.027657197788357735,
+      "learning_rate": 6.7828418230563e-05,
+      "loss": 0.0,
       "step": 120
     },
     {
-      "epoch": 0.6403940886699507,
-      "grad_norm": 1.226656198501587,
-      "learning_rate": 3.5960591133004926e-05,
-      "loss": 0.27,
+      "epoch": 0.3485254691689008,
+      "grad_norm": 0.027470039203763008,
+      "learning_rate": 6.514745308310992e-05,
+      "loss": 0.0,
       "step": 130
     },
     {
-      "epoch": 0.6896551724137931,
-      "grad_norm": 1.3999422788619995,
-      "learning_rate": 3.103448275862069e-05,
-      "loss": 0.3287,
+      "epoch": 0.3753351206434316,
+      "grad_norm": 0.027397796511650085,
+      "learning_rate": 6.246648793565684e-05,
+      "loss": 0.0,
       "step": 140
     },
     {
-      "epoch": 0.7389162561576355,
-      "grad_norm": 4.163649082183838,
-      "learning_rate": 2.6108374384236457e-05,
-      "loss": 0.3943,
+      "epoch": 0.40214477211796246,
+      "grad_norm": 0.027218900620937347,
+      "learning_rate": 5.978552278820375e-05,
+      "loss": 0.0,
       "step": 150
     },
     {
-      "epoch": 0.7881773399014779,
-      "grad_norm": 0.8537468314170837,
-      "learning_rate": 2.1182266009852215e-05,
-      "loss": 0.3435,
+      "epoch": 0.4289544235924933,
+      "grad_norm": 0.027058888226747513,
+      "learning_rate": 5.7104557640750675e-05,
+      "loss": 0.0,
       "step": 160
     },
     {
-      "epoch": 0.8374384236453202,
-      "grad_norm": 3.8700287342071533,
-      "learning_rate": 1.625615763546798e-05,
-      "loss": 0.5416,
+      "epoch": 0.45576407506702415,
+      "grad_norm": 0.02702343836426735,
+      "learning_rate": 5.442359249329759e-05,
+      "loss": 0.0,
       "step": 170
     },
     {
-      "epoch": 0.8866995073891626,
-      "grad_norm": 6.436923980712891,
-      "learning_rate": 1.1330049261083744e-05,
-      "loss": 0.3257,
+      "epoch": 0.48257372654155495,
+      "grad_norm": 0.026990406215190887,
+      "learning_rate": 5.174262734584451e-05,
+      "loss": 0.0,
       "step": 180
     },
     {
-      "epoch": 0.9359605911330049,
-      "grad_norm": 1.033650279045105,
-      "learning_rate": 6.403940886699508e-06,
-      "loss": 0.5444,
+      "epoch": 0.5093833780160858,
+      "grad_norm": 0.026836372911930084,
+      "learning_rate": 4.906166219839142e-05,
+      "loss": 0.0,
       "step": 190
     },
     {
-      "epoch": 0.9852216748768473,
-      "grad_norm": 2.5371437072753906,
-      "learning_rate": 1.477832512315271e-06,
-      "loss": 0.5019,
+      "epoch": 0.5361930294906166,
+      "grad_norm": 0.026813047006726265,
+      "learning_rate": 4.638069705093834e-05,
+      "loss": 0.0,
       "step": 200
     },
+    {
+      "epoch": 0.5630026809651475,
+      "grad_norm": 0.02667263336479664,
+      "learning_rate": 4.3699731903485256e-05,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.5898123324396782,
+      "grad_norm": 0.026654915884137154,
+      "learning_rate": 4.1018766756032174e-05,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.6166219839142091,
+      "grad_norm": 0.02663583494722843,
+      "learning_rate": 3.8337801608579085e-05,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.6434316353887399,
+      "grad_norm": 0.02650284953415394,
+      "learning_rate": 3.565683646112601e-05,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 0.026488320901989937,
+      "learning_rate": 3.297587131367292e-05,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.6970509383378016,
+      "grad_norm": 0.02647605538368225,
+      "learning_rate": 3.0294906166219838e-05,
+      "loss": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.7238605898123325,
+      "grad_norm": 0.026349999010562897,
+      "learning_rate": 2.761394101876676e-05,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.7506702412868632,
+      "grad_norm": 0.026226293295621872,
+      "learning_rate": 2.4932975871313673e-05,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.7774798927613941,
+      "grad_norm": 0.026215018704533577,
+      "learning_rate": 2.225201072386059e-05,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.8042895442359249,
+      "grad_norm": 0.02620949037373066,
+      "learning_rate": 1.9571045576407505e-05,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.8310991957104558,
+      "grad_norm": 0.02621125429868698,
+      "learning_rate": 1.6890080428954423e-05,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.8579088471849866,
+      "grad_norm": 0.026199743151664734,
+      "learning_rate": 1.4209115281501343e-05,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.8847184986595175,
+      "grad_norm": 0.026200657710433006,
+      "learning_rate": 1.1528150134048257e-05,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.9115281501340483,
+      "grad_norm": 0.02620103396475315,
+      "learning_rate": 8.847184986595175e-06,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.938337801608579,
+      "grad_norm": 0.026197846978902817,
+      "learning_rate": 6.1662198391420915e-06,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.9651474530831099,
+      "grad_norm": 0.026203904300928116,
+      "learning_rate": 3.4852546916890083e-06,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.9919571045576407,
+      "grad_norm": 0.0262033361941576,
+      "learning_rate": 8.04289544235925e-07,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 1.0,
+      "eval_runtime": 26.0963,
+      "eval_samples_per_second": 14.293,
+      "eval_steps_per_second": 0.92,
+      "step": 373
+    },
     {
       "epoch": 1.0,
-      "step": 203,
+      "step": 373,
       "total_flos": 0.0,
-      "train_loss": 0.5319549602828002,
-      "train_runtime": 55.3499,
-      "train_samples_per_second": 3.668,
-      "train_steps_per_second": 3.668
+      "train_loss": 0.1567674662395578,
+      "train_runtime": 349.2812,
+      "train_samples_per_second": 4.272,
+      "train_steps_per_second": 1.068
     }
   ],
   "logging_steps": 10,
-  "max_steps": 203,
+  "max_steps": 373,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -176,7 +309,7 @@
     }
   },
   "total_flos": 0.0,
-  "train_batch_size": 1,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3b9650fc36193ba33029ea31e3820a0bf08dbd41f1bffa00adf86ad61a2e6e
+oid sha256:34c93f8087af42de0f66def80a14024461a78d1da002000e529291da561312d8
 size 5432