初始化项目，由ModelHub XC社区提供模型

Model: israel/AfriqueQwen-14B-multiturn
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+checkpoint-34265/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: McGill-NLP/AfriqueQwen-14B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: AfriqueQwen-14B-multiturn
+  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. -->
+
+# AfriqueQwen-14B-multiturn
+
+This model is a fine-tuned version of [McGill-NLP/AfriqueQwen-14B](https://huggingface.co/McGill-NLP/AfriqueQwen-14B) on the afri_multiturn dataset.
+
+## 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: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.2.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1091733654863872.0,
+    "train_loss": 0.42485430567312915,
+    "train_runtime": 114160.2816,
+    "train_samples_per_second": 2.401,
+    "train_steps_per_second": 0.3
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,75 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "5.2.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00c3e05d9310da4dcdc3b1e919ba7c1a445da8eeff56950f0a74ca8b2306a96
+size 29536666272

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1091733654863872.0,
+    "train_loss": 0.42485430567312915,
+    "train_runtime": 114160.2816,
+    "train_samples_per_second": 2.401,
+    "train_steps_per_second": 0.3
+}

trainer_log.jsonl

@@ -0,0 +1,35 @@
+{"current_steps": 1000, "total_steps": 34265, "loss": 1.091951904296875, "lr": 2.915086081120514e-06, "epoch": 0.1459321415541773, "percentage": 2.92, "elapsed_time": "0:55:22", "remaining_time": "1 day, 6:42:13"}
+{"current_steps": 2000, "total_steps": 34265, "loss": 0.9010311279296875, "lr": 5.833090166326233e-06, "epoch": 0.2918642831083546, "percentage": 5.84, "elapsed_time": "1:50:40", "remaining_time": "1 day, 5:45:32"}
+{"current_steps": 3000, "total_steps": 34265, "loss": 0.8496372680664063, "lr": 8.751094251531953e-06, "epoch": 0.43779642466253194, "percentage": 8.76, "elapsed_time": "2:46:03", "remaining_time": "1 day, 4:50:33"}
+{"current_steps": 4000, "total_steps": 34265, "loss": 0.8293939208984376, "lr": 9.991513345767592e-06, "epoch": 0.5837285662167092, "percentage": 11.67, "elapsed_time": "3:41:25", "remaining_time": "1 day, 3:55:21"}
+{"current_steps": 5000, "total_steps": 34265, "loss": 0.8073157348632812, "lr": 9.936020028278053e-06, "epoch": 0.7296607077708865, "percentage": 14.59, "elapsed_time": "4:36:43", "remaining_time": "1 day, 2:59:41"}
+{"current_steps": 6000, "total_steps": 34265, "loss": 0.7829708251953125, "lr": 9.829343371836088e-06, "epoch": 0.8755928493250639, "percentage": 17.51, "elapsed_time": "5:32:07", "remaining_time": "1 day, 2:04:34"}
+{"current_steps": 7000, "total_steps": 34265, "loss": 0.7496401977539062, "lr": 9.672589544454328e-06, "epoch": 1.021452024808464, "percentage": 20.43, "elapsed_time": "6:27:24", "remaining_time": "1 day, 1:08:55"}
+{"current_steps": 8000, "total_steps": 34265, "loss": 0.6121725463867187, "lr": 9.46738398205746e-06, "epoch": 1.1673841663626414, "percentage": 23.35, "elapsed_time": "7:22:45", "remaining_time": "1 day, 0:13:38"}
+{"current_steps": 9000, "total_steps": 34265, "loss": 0.611597412109375, "lr": 9.215854533761766e-06, "epoch": 1.3133163079168186, "percentage": 26.27, "elapsed_time": "8:18:11", "remaining_time": "23:18:31"}
+{"current_steps": 10000, "total_steps": 34265, "loss": 0.6123408203125, "lr": 8.920609397454381e-06, "epoch": 1.459248449470996, "percentage": 29.18, "elapsed_time": "9:13:31", "remaining_time": "22:23:07"}
+{"current_steps": 11000, "total_steps": 34265, "loss": 0.609525390625, "lr": 8.584710074466158e-06, "epoch": 1.6051805910251733, "percentage": 32.1, "elapsed_time": "10:08:58", "remaining_time": "21:27:58"}
+{"current_steps": 12000, "total_steps": 34265, "loss": 0.6133668823242188, "lr": 8.211639623780629e-06, "epoch": 1.7511127325793505, "percentage": 35.02, "elapsed_time": "11:04:20", "remaining_time": "20:32:37"}
+{"current_steps": 13000, "total_steps": 34265, "loss": 0.615207763671875, "lr": 7.805266544962458e-06, "epoch": 1.897044874133528, "percentage": 37.94, "elapsed_time": "11:59:35", "remaining_time": "19:37:05"}
+{"current_steps": 14000, "total_steps": 34265, "loss": 0.5413321533203125, "lr": 7.3698046643160645e-06, "epoch": 2.042904049616928, "percentage": 40.86, "elapsed_time": "12:54:57", "remaining_time": "18:41:45"}
+{"current_steps": 15000, "total_steps": 34265, "loss": 0.38200238037109374, "lr": 6.909769440229038e-06, "epoch": 2.1888361911711054, "percentage": 43.78, "elapsed_time": "13:50:21", "remaining_time": "17:46:27"}
+{"current_steps": 16000, "total_steps": 34265, "loss": 0.38497344970703123, "lr": 6.4299311407857035e-06, "epoch": 2.334768332725283, "percentage": 46.69, "elapsed_time": "14:45:41", "remaining_time": "16:51:03"}
+{"current_steps": 17000, "total_steps": 34265, "loss": 0.3850032653808594, "lr": 5.935265379168761e-06, "epoch": 2.48070047427946, "percentage": 49.61, "elapsed_time": "15:40:54", "remaining_time": "15:55:34"}
+{"current_steps": 18000, "total_steps": 34265, "loss": 0.38166015625, "lr": 5.430901519764892e-06, "epoch": 2.6266326158336373, "percentage": 52.53, "elapsed_time": "16:36:17", "remaining_time": "15:00:15"}
+{"current_steps": 19000, "total_steps": 34265, "loss": 0.3862608642578125, "lr": 4.9220694899697185e-06, "epoch": 2.7725647573878147, "percentage": 55.45, "elapsed_time": "17:31:33", "remaining_time": "14:04:50"}
+{"current_steps": 20000, "total_steps": 34265, "loss": 0.38137054443359375, "lr": 4.414045549219315e-06, "epoch": 2.918496898941992, "percentage": 58.37, "elapsed_time": "18:26:50", "remaining_time": "13:09:27"}
+{"current_steps": 21000, "total_steps": 34265, "loss": 0.2938824462890625, "lr": 3.912097577588397e-06, "epoch": 3.064356074425392, "percentage": 61.29, "elapsed_time": "19:22:11", "remaining_time": "12:14:06"}
+{"current_steps": 22000, "total_steps": 34265, "loss": 0.19125808715820314, "lr": 3.4214304512770823e-06, "epoch": 3.2102882159795696, "percentage": 64.21, "elapsed_time": "20:17:28", "remaining_time": "11:18:44"}
+{"current_steps": 23000, "total_steps": 34265, "loss": 0.18847378540039061, "lr": 2.9471320714071095e-06, "epoch": 3.356220357533747, "percentage": 67.12, "elapsed_time": "21:12:42", "remaining_time": "10:23:20"}
+{"current_steps": 24000, "total_steps": 34265, "loss": 0.19000143432617186, "lr": 2.4941206057740675e-06, "epoch": 3.502152499087924, "percentage": 70.04, "elapsed_time": "22:08:12", "remaining_time": "9:28:04"}
+{"current_steps": 25000, "total_steps": 34265, "loss": 0.18782159423828124, "lr": 2.06709349062457e-06, "epoch": 3.6480846406421015, "percentage": 72.96, "elapsed_time": "23:03:30", "remaining_time": "8:32:43"}
+{"current_steps": 26000, "total_steps": 34265, "loss": 0.18233416748046874, "lr": 1.6704787212769829e-06, "epoch": 3.7940167821962785, "percentage": 75.88, "elapsed_time": "23:58:48", "remaining_time": "7:37:22"}
+{"current_steps": 27000, "total_steps": 34265, "loss": 0.17911607360839843, "lr": 1.3083889366705216e-06, "epoch": 3.939948923750456, "percentage": 78.8, "elapsed_time": "1 day, 0:54:08", "remaining_time": "6:42:01"}
+{"current_steps": 28000, "total_steps": 34265, "loss": 0.12317549133300781, "lr": 9.845787739562829e-07, "epoch": 4.085808099233856, "percentage": 81.72, "elapsed_time": "1 day, 1:49:35", "remaining_time": "5:46:43"}
+{"current_steps": 29000, "total_steps": 34265, "loss": 0.08010615539550782, "lr": 7.024059353355333e-07, "epoch": 4.231740240788033, "percentage": 84.63, "elapsed_time": "1 day, 2:45:03", "remaining_time": "4:51:24"}
+{"current_steps": 30000, "total_steps": 34265, "loss": 0.08023818969726562, "lr": 4.64796370857008e-07, "epoch": 4.377672382342211, "percentage": 87.55, "elapsed_time": "1 day, 3:40:23", "remaining_time": "3:56:03"}
+{"current_steps": 31000, "total_steps": 34265, "loss": 0.07947054290771484, "lr": 2.7421393820510846e-07, "epoch": 4.523604523896388, "percentage": 90.47, "elapsed_time": "1 day, 4:35:53", "remaining_time": "3:00:43"}
+{"current_steps": 32000, "total_steps": 34265, "loss": 0.07735189056396484, "lr": 1.326348540874095e-07, "epoch": 4.669536665450566, "percentage": 93.39, "elapsed_time": "1 day, 5:31:22", "remaining_time": "2:05:22"}
+{"current_steps": 33000, "total_steps": 34265, "loss": 0.07909833526611328, "lr": 4.152720214406214e-08, "epoch": 4.815468807004743, "percentage": 96.31, "elapsed_time": "1 day, 6:26:45", "remaining_time": "1:10:01"}
+{"current_steps": 34000, "total_steps": 34265, "loss": 0.07906644439697266, "lr": 1.8357098688476238e-09, "epoch": 4.96140094855892, "percentage": 99.23, "elapsed_time": "1 day, 7:22:10", "remaining_time": "0:14:40"}
+{"current_steps": 34265, "total_steps": 34265, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1 day, 7:42:40", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,281 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 34265,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1459321415541773,
+      "grad_norm": 2.2002170436333888,
+      "learning_rate": 2.915086081120514e-06,
+      "loss": 1.091951904296875,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2918642831083546,
+      "grad_norm": 2.3899237660554205,
+      "learning_rate": 5.833090166326233e-06,
+      "loss": 0.9010311279296875,
+      "step": 2000
+    },
+    {
+      "epoch": 0.43779642466253194,
+      "grad_norm": 1.7207455491966865,
+      "learning_rate": 8.751094251531953e-06,
+      "loss": 0.8496372680664063,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5837285662167092,
+      "grad_norm": 1.49997561253202,
+      "learning_rate": 9.991513345767592e-06,
+      "loss": 0.8293939208984376,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7296607077708865,
+      "grad_norm": 1.43919873990257,
+      "learning_rate": 9.936020028278053e-06,
+      "loss": 0.8073157348632812,
+      "step": 5000
+    },
+    {
+      "epoch": 0.8755928493250639,
+      "grad_norm": 1.384519444393501,
+      "learning_rate": 9.829343371836088e-06,
+      "loss": 0.7829708251953125,
+      "step": 6000
+    },
+    {
+      "epoch": 1.021452024808464,
+      "grad_norm": 1.457416645249146,
+      "learning_rate": 9.672589544454328e-06,
+      "loss": 0.7496401977539062,
+      "step": 7000
+    },
+    {
+      "epoch": 1.1673841663626414,
+      "grad_norm": 1.5133027310610572,
+      "learning_rate": 9.46738398205746e-06,
+      "loss": 0.6121725463867187,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3133163079168186,
+      "grad_norm": 1.3855612557611925,
+      "learning_rate": 9.215854533761766e-06,
+      "loss": 0.611597412109375,
+      "step": 9000
+    },
+    {
+      "epoch": 1.459248449470996,
+      "grad_norm": 1.5802706606106216,
+      "learning_rate": 8.920609397454381e-06,
+      "loss": 0.6123408203125,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6051805910251733,
+      "grad_norm": 1.4685873474216664,
+      "learning_rate": 8.584710074466158e-06,
+      "loss": 0.609525390625,
+      "step": 11000
+    },
+    {
+      "epoch": 1.7511127325793505,
+      "grad_norm": 1.219859265372452,
+      "learning_rate": 8.211639623780629e-06,
+      "loss": 0.6133668823242188,
+      "step": 12000
+    },
+    {
+      "epoch": 1.897044874133528,
+      "grad_norm": 1.2535196330309815,
+      "learning_rate": 7.805266544962458e-06,
+      "loss": 0.615207763671875,
+      "step": 13000
+    },
+    {
+      "epoch": 2.042904049616928,
+      "grad_norm": 1.5681754211680612,
+      "learning_rate": 7.3698046643160645e-06,
+      "loss": 0.5413321533203125,
+      "step": 14000
+    },
+    {
+      "epoch": 2.1888361911711054,
+      "grad_norm": 1.2447962924993787,
+      "learning_rate": 6.909769440229038e-06,
+      "loss": 0.38200238037109374,
+      "step": 15000
+    },
+    {
+      "epoch": 2.334768332725283,
+      "grad_norm": 1.4067667074111327,
+      "learning_rate": 6.4299311407857035e-06,
+      "loss": 0.38497344970703123,
+      "step": 16000
+    },
+    {
+      "epoch": 2.48070047427946,
+      "grad_norm": 1.326059120500027,
+      "learning_rate": 5.935265379168761e-06,
+      "loss": 0.3850032653808594,
+      "step": 17000
+    },
+    {
+      "epoch": 2.6266326158336373,
+      "grad_norm": 1.6923974019115828,
+      "learning_rate": 5.430901519764892e-06,
+      "loss": 0.38166015625,
+      "step": 18000
+    },
+    {
+      "epoch": 2.7725647573878147,
+      "grad_norm": 1.5367782861850559,
+      "learning_rate": 4.9220694899697185e-06,
+      "loss": 0.3862608642578125,
+      "step": 19000
+    },
+    {
+      "epoch": 2.918496898941992,
+      "grad_norm": 1.3054321737811847,
+      "learning_rate": 4.414045549219315e-06,
+      "loss": 0.38137054443359375,
+      "step": 20000
+    },
+    {
+      "epoch": 3.064356074425392,
+      "grad_norm": 1.69275953279231,
+      "learning_rate": 3.912097577588397e-06,
+      "loss": 0.2938824462890625,
+      "step": 21000
+    },
+    {
+      "epoch": 3.2102882159795696,
+      "grad_norm": 1.5240170572509457,
+      "learning_rate": 3.4214304512770823e-06,
+      "loss": 0.19125808715820314,
+      "step": 22000
+    },
+    {
+      "epoch": 3.356220357533747,
+      "grad_norm": 1.5774125509908914,
+      "learning_rate": 2.9471320714071095e-06,
+      "loss": 0.18847378540039061,
+      "step": 23000
+    },
+    {
+      "epoch": 3.502152499087924,
+      "grad_norm": 1.8421166872943977,
+      "learning_rate": 2.4941206057740675e-06,
+      "loss": 0.19000143432617186,
+      "step": 24000
+    },
+    {
+      "epoch": 3.6480846406421015,
+      "grad_norm": 1.5694212047061644,
+      "learning_rate": 2.06709349062457e-06,
+      "loss": 0.18782159423828124,
+      "step": 25000
+    },
+    {
+      "epoch": 3.7940167821962785,
+      "grad_norm": 1.496800606594422,
+      "learning_rate": 1.6704787212769829e-06,
+      "loss": 0.18233416748046874,
+      "step": 26000
+    },
+    {
+      "epoch": 3.939948923750456,
+      "grad_norm": 1.984744582152809,
+      "learning_rate": 1.3083889366705216e-06,
+      "loss": 0.17911607360839843,
+      "step": 27000
+    },
+    {
+      "epoch": 4.085808099233856,
+      "grad_norm": 1.2567953809414274,
+      "learning_rate": 9.845787739562829e-07,
+      "loss": 0.12317549133300781,
+      "step": 28000
+    },
+    {
+      "epoch": 4.231740240788033,
+      "grad_norm": 1.091077915720754,
+      "learning_rate": 7.024059353355333e-07,
+      "loss": 0.08010615539550782,
+      "step": 29000
+    },
+    {
+      "epoch": 4.377672382342211,
+      "grad_norm": 1.2460581955478622,
+      "learning_rate": 4.64796370857008e-07,
+      "loss": 0.08023818969726562,
+      "step": 30000
+    },
+    {
+      "epoch": 4.523604523896388,
+      "grad_norm": 1.7839106451867877,
+      "learning_rate": 2.7421393820510846e-07,
+      "loss": 0.07947054290771484,
+      "step": 31000
+    },
+    {
+      "epoch": 4.669536665450566,
+      "grad_norm": 1.1265268481087043,
+      "learning_rate": 1.326348540874095e-07,
+      "loss": 0.07735189056396484,
+      "step": 32000
+    },
+    {
+      "epoch": 4.815468807004743,
+      "grad_norm": 1.0896372619502366,
+      "learning_rate": 4.152720214406214e-08,
+      "loss": 0.07909833526611328,
+      "step": 33000
+    },
+    {
+      "epoch": 4.96140094855892,
+      "grad_norm": 1.2750658260191035,
+      "learning_rate": 1.8357098688476238e-09,
+      "loss": 0.07906644439697266,
+      "step": 34000
+    },
+    {
+      "epoch": 5.0,
+      "step": 34265,
+      "total_flos": 1091733654863872.0,
+      "train_loss": 0.42485430567312915,
+      "train_runtime": 114160.2816,
+      "train_samples_per_second": 2.401,
+      "train_steps_per_second": 0.3
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 34265,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1091733654863872.0,
+  "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 sha256:7a4cc99de1a10fd6c19d45d4b68f0e6d1e0fb1309394ed1c123226c8b71056c8
+size 7377