commit aaf1107285d85732a8bb6609dad5843dbd5a1642
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Thu Aug 20 14:15:17 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: oodgnas/Qwen3-1.7B-SFT-100k
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000..db2e8c8
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 145115603533824.0,
+    "train_loss": 0.698847218818268,
+    "train_runtime": 3222.3497,
+    "train_samples_per_second": 29.579,
+    "train_steps_per_second": 0.463
+}
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..01be9b3
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- 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 message.content is string 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.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.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' }}
+        {{- 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 %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..7146857
--- /dev/null
+++ b/config.json
@@ -0,0 +1,63 @@
+{
+  "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": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "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": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..1701c94
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.2.0"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..3f40933
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eed34c0bc3b02529b0e2e56e2a6ba3d43559c749947815a1c9ccd73a39f7eec
+size 4063515640
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..c7afbed
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..271320b
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000..db2e8c8
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 145115603533824.0,
+    "train_loss": 0.698847218818268,
+    "train_runtime": 3222.3497,
+    "train_samples_per_second": 29.579,
+    "train_steps_per_second": 0.463
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000..72b5aae
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,150 @@
+{"current_steps": 10, "total_steps": 1491, "loss": 3.073244094848633, "lr": 4.000000000000001e-06, "epoch": 0.02014098690835851, "percentage": 0.67, "elapsed_time": "0:00:26", "remaining_time": "1:04:24"}
+{"current_steps": 20, "total_steps": 1491, "loss": 2.2913312911987305, "lr": 8.444444444444446e-06, "epoch": 0.04028197381671702, "percentage": 1.34, "elapsed_time": "0:00:47", "remaining_time": "0:58:05"}
+{"current_steps": 30, "total_steps": 1491, "loss": 1.5302621841430664, "lr": 1.288888888888889e-05, "epoch": 0.06042296072507553, "percentage": 2.01, "elapsed_time": "0:01:08", "remaining_time": "0:55:45"}
+{"current_steps": 40, "total_steps": 1491, "loss": 1.0828689575195312, "lr": 1.7333333333333336e-05, "epoch": 0.08056394763343404, "percentage": 2.68, "elapsed_time": "0:01:30", "remaining_time": "0:54:31"}
+{"current_steps": 50, "total_steps": 1491, "loss": 0.8968555450439453, "lr": 1.9999622383977725e-05, "epoch": 0.10070493454179255, "percentage": 3.35, "elapsed_time": "0:01:51", "remaining_time": "0:53:38"}
+{"current_steps": 60, "total_steps": 1491, "loss": 0.8666976928710938, "lr": 1.999537453124055e-05, "epoch": 0.12084592145015106, "percentage": 4.02, "elapsed_time": "0:02:13", "remaining_time": "0:52:55"}
+{"current_steps": 70, "total_steps": 1491, "loss": 0.8250602722167969, "lr": 1.998640881742778e-05, "epoch": 0.14098690835850958, "percentage": 4.69, "elapsed_time": "0:02:34", "remaining_time": "0:52:18"}
+{"current_steps": 80, "total_steps": 1491, "loss": 0.8222087860107422, "lr": 1.997272947439608e-05, "epoch": 0.16112789526686808, "percentage": 5.37, "elapsed_time": "0:02:56", "remaining_time": "0:51:45"}
+{"current_steps": 90, "total_steps": 1491, "loss": 0.7954679489135742, "lr": 1.995434295885598e-05, "epoch": 0.18126888217522658, "percentage": 6.04, "elapsed_time": "0:03:17", "remaining_time": "0:51:12"}
+{"current_steps": 100, "total_steps": 1491, "loss": 0.8072474479675293, "lr": 1.993125794932429e-05, "epoch": 0.2014098690835851, "percentage": 6.71, "elapsed_time": "0:03:38", "remaining_time": "0:50:43"}
+{"current_steps": 110, "total_steps": 1491, "loss": 0.8378339767456054, "lr": 1.9903485342027827e-05, "epoch": 0.2215508559919436, "percentage": 7.38, "elapsed_time": "0:04:00", "remaining_time": "0:50:14"}
+{"current_steps": 120, "total_steps": 1491, "loss": 0.7969758987426758, "lr": 1.9871038245760305e-05, "epoch": 0.24169184290030213, "percentage": 8.05, "elapsed_time": "0:04:21", "remaining_time": "0:49:46"}
+{"current_steps": 130, "total_steps": 1491, "loss": 0.837348747253418, "lr": 1.983393197569497e-05, "epoch": 0.2618328298086606, "percentage": 8.72, "elapsed_time": "0:04:42", "remaining_time": "0:49:19"}
+{"current_steps": 140, "total_steps": 1491, "loss": 0.7704894065856933, "lr": 1.9792184046155733e-05, "epoch": 0.28197381671701915, "percentage": 9.39, "elapsed_time": "0:05:04", "remaining_time": "0:48:53"}
+{"current_steps": 150, "total_steps": 1491, "loss": 0.7638654708862305, "lr": 1.974581416235035e-05, "epoch": 0.3021148036253776, "percentage": 10.06, "elapsed_time": "0:05:25", "remaining_time": "0:48:28"}
+{"current_steps": 160, "total_steps": 1491, "loss": 0.7630445480346679, "lr": 1.9694844211069477e-05, "epoch": 0.32225579053373615, "percentage": 10.73, "elapsed_time": "0:05:46", "remaining_time": "0:48:03"}
+{"current_steps": 170, "total_steps": 1491, "loss": 0.79698166847229, "lr": 1.963929825035601e-05, "epoch": 0.3423967774420947, "percentage": 11.4, "elapsed_time": "0:06:07", "remaining_time": "0:47:39"}
+{"current_steps": 180, "total_steps": 1491, "loss": 0.7727674961090087, "lr": 1.9579202498149562e-05, "epoch": 0.36253776435045315, "percentage": 12.07, "elapsed_time": "0:06:29", "remaining_time": "0:47:14"}
+{"current_steps": 190, "total_steps": 1491, "loss": 0.7765314102172851, "lr": 1.951458531991151e-05, "epoch": 0.3826787512588117, "percentage": 12.74, "elapsed_time": "0:06:50", "remaining_time": "0:46:51"}
+{"current_steps": 200, "total_steps": 1491, "loss": 0.7855539321899414, "lr": 1.9445477215236343e-05, "epoch": 0.4028197381671702, "percentage": 13.41, "elapsed_time": "0:07:11", "remaining_time": "0:46:27"}
+{"current_steps": 210, "total_steps": 1491, "loss": 0.7797715187072753, "lr": 1.937191080345574e-05, "epoch": 0.4229607250755287, "percentage": 14.08, "elapsed_time": "0:07:33", "remaining_time": "0:46:03"}
+{"current_steps": 220, "total_steps": 1491, "loss": 0.7819314956665039, "lr": 1.9293920808242084e-05, "epoch": 0.4431017119838872, "percentage": 14.76, "elapsed_time": "0:07:54", "remaining_time": "0:45:40"}
+{"current_steps": 230, "total_steps": 1491, "loss": 0.7715907096862793, "lr": 1.9211544041218752e-05, "epoch": 0.46324269889224573, "percentage": 15.43, "elapsed_time": "0:08:15", "remaining_time": "0:45:16"}
+{"current_steps": 240, "total_steps": 1491, "loss": 0.7307522296905518, "lr": 1.912481938458485e-05, "epoch": 0.48338368580060426, "percentage": 16.1, "elapsed_time": "0:08:36", "remaining_time": "0:44:53"}
+{"current_steps": 250, "total_steps": 1491, "loss": 0.7505370616912842, "lr": 1.9033787772762647e-05, "epoch": 0.5035246727089627, "percentage": 16.77, "elapsed_time": "0:08:58", "remaining_time": "0:44:30"}
+{"current_steps": 260, "total_steps": 1491, "loss": 0.7448963165283203, "lr": 1.893849217307635e-05, "epoch": 0.5236656596173213, "percentage": 17.44, "elapsed_time": "0:09:19", "remaining_time": "0:44:08"}
+{"current_steps": 270, "total_steps": 1491, "loss": 0.7512392044067383, "lr": 1.8838977565471343e-05, "epoch": 0.5438066465256798, "percentage": 18.11, "elapsed_time": "0:09:40", "remaining_time": "0:43:46"}
+{"current_steps": 280, "total_steps": 1491, "loss": 0.7734776496887207, "lr": 1.873529092128343e-05, "epoch": 0.5639476334340383, "percentage": 18.78, "elapsed_time": "0:10:02", "remaining_time": "0:43:24"}
+{"current_steps": 290, "total_steps": 1491, "loss": 0.7516597747802735, "lr": 1.8627481181068185e-05, "epoch": 0.5840886203423967, "percentage": 19.45, "elapsed_time": "0:10:23", "remaining_time": "0:43:01"}
+{"current_steps": 300, "total_steps": 1491, "loss": 0.7655241966247559, "lr": 1.851559923150077e-05, "epoch": 0.6042296072507553, "percentage": 20.12, "elapsed_time": "0:10:44", "remaining_time": "0:42:38"}
+{"current_steps": 310, "total_steps": 1491, "loss": 0.7743952751159668, "lr": 1.8399697881357214e-05, "epoch": 0.6243705941591138, "percentage": 20.79, "elapsed_time": "0:11:24", "remaining_time": "0:43:27"}
+{"current_steps": 320, "total_steps": 1491, "loss": 0.7196044445037841, "lr": 1.8279831836588427e-05, "epoch": 0.6445115810674723, "percentage": 21.46, "elapsed_time": "0:11:46", "remaining_time": "0:43:04"}
+{"current_steps": 330, "total_steps": 1491, "loss": 0.7735816955566406, "lr": 1.8156057674498756e-05, "epoch": 0.6646525679758308, "percentage": 22.13, "elapsed_time": "0:12:07", "remaining_time": "0:42:39"}
+{"current_steps": 340, "total_steps": 1491, "loss": 0.7698081970214844, "lr": 1.8028433817041237e-05, "epoch": 0.6847935548841894, "percentage": 22.8, "elapsed_time": "0:12:28", "remaining_time": "0:42:14"}
+{"current_steps": 350, "total_steps": 1491, "loss": 0.7545667171478272, "lr": 1.7897020503242192e-05, "epoch": 0.7049345417925479, "percentage": 23.47, "elapsed_time": "0:12:50", "remaining_time": "0:41:50"}
+{"current_steps": 360, "total_steps": 1491, "loss": 0.7272197723388671, "lr": 1.7761879760768123e-05, "epoch": 0.7250755287009063, "percentage": 24.14, "elapsed_time": "0:13:11", "remaining_time": "0:41:26"}
+{"current_steps": 370, "total_steps": 1491, "loss": 0.735597801208496, "lr": 1.7623075376648374e-05, "epoch": 0.7452165156092648, "percentage": 24.82, "elapsed_time": "0:13:32", "remaining_time": "0:41:02"}
+{"current_steps": 380, "total_steps": 1491, "loss": 0.7506361484527588, "lr": 1.748067286716741e-05, "epoch": 0.7653575025176234, "percentage": 25.49, "elapsed_time": "0:13:54", "remaining_time": "0:40:38"}
+{"current_steps": 390, "total_steps": 1491, "loss": 0.7382652282714843, "lr": 1.7334739446940785e-05, "epoch": 0.7854984894259819, "percentage": 26.16, "elapsed_time": "0:14:15", "remaining_time": "0:40:14"}
+{"current_steps": 400, "total_steps": 1491, "loss": 0.7026462554931641, "lr": 1.718534399718959e-05, "epoch": 0.8056394763343404, "percentage": 26.83, "elapsed_time": "0:14:36", "remaining_time": "0:39:50"}
+{"current_steps": 410, "total_steps": 1491, "loss": 0.7259914398193359, "lr": 1.7032557033228184e-05, "epoch": 0.8257804632426989, "percentage": 27.5, "elapsed_time": "0:14:57", "remaining_time": "0:39:26"}
+{"current_steps": 420, "total_steps": 1491, "loss": 0.7931873798370361, "lr": 1.6876450671180667e-05, "epoch": 0.8459214501510574, "percentage": 28.17, "elapsed_time": "0:15:19", "remaining_time": "0:39:03"}
+{"current_steps": 430, "total_steps": 1491, "loss": 0.726997709274292, "lr": 1.6717098593941753e-05, "epoch": 0.8660624370594159, "percentage": 28.84, "elapsed_time": "0:15:40", "remaining_time": "0:38:40"}
+{"current_steps": 440, "total_steps": 1491, "loss": 0.7656588554382324, "lr": 1.65545760163981e-05, "epoch": 0.8862034239677744, "percentage": 29.51, "elapsed_time": "0:16:01", "remaining_time": "0:38:17"}
+{"current_steps": 450, "total_steps": 1491, "loss": 0.7257630348205566, "lr": 1.6388959649926567e-05, "epoch": 0.9063444108761329, "percentage": 30.18, "elapsed_time": "0:16:23", "remaining_time": "0:37:54"}
+{"current_steps": 460, "total_steps": 1491, "loss": 0.7346350669860839, "lr": 1.62203276661861e-05, "epoch": 0.9264853977844915, "percentage": 30.85, "elapsed_time": "0:16:44", "remaining_time": "0:37:31"}
+{"current_steps": 470, "total_steps": 1491, "loss": 0.7640430450439453, "lr": 1.604875966022035e-05, "epoch": 0.94662638469285, "percentage": 31.52, "elapsed_time": "0:17:05", "remaining_time": "0:37:08"}
+{"current_steps": 480, "total_steps": 1491, "loss": 0.718746280670166, "lr": 1.5874336612888487e-05, "epoch": 0.9667673716012085, "percentage": 32.19, "elapsed_time": "0:17:26", "remaining_time": "0:36:45"}
+{"current_steps": 490, "total_steps": 1491, "loss": 0.7472597122192383, "lr": 1.5697140852641835e-05, "epoch": 0.9869083585095669, "percentage": 32.86, "elapsed_time": "0:17:48", "remaining_time": "0:36:22"}
+{"current_steps": 500, "total_steps": 1491, "loss": 0.7291147232055664, "lr": 1.5517256016664524e-05, "epoch": 1.0060422960725075, "percentage": 33.53, "elapsed_time": "0:18:08", "remaining_time": "0:35:58"}
+{"current_steps": 510, "total_steps": 1491, "loss": 0.6633618354797364, "lr": 1.533476701139633e-05, "epoch": 1.0261832829808661, "percentage": 34.21, "elapsed_time": "0:18:30", "remaining_time": "0:35:35"}
+{"current_steps": 520, "total_steps": 1491, "loss": 0.6561120033264161, "lr": 1.514975997245649e-05, "epoch": 1.0463242698892246, "percentage": 34.88, "elapsed_time": "0:18:51", "remaining_time": "0:35:13"}
+{"current_steps": 530, "total_steps": 1491, "loss": 0.651552963256836, "lr": 1.4962322223987284e-05, "epoch": 1.0664652567975832, "percentage": 35.55, "elapsed_time": "0:19:13", "remaining_time": "0:34:50"}
+{"current_steps": 540, "total_steps": 1491, "loss": 0.6309733867645264, "lr": 1.477254223743666e-05, "epoch": 1.0866062437059416, "percentage": 36.22, "elapsed_time": "0:19:34", "remaining_time": "0:34:28"}
+{"current_steps": 550, "total_steps": 1491, "loss": 0.6375226974487305, "lr": 1.458050958979933e-05, "epoch": 1.1067472306143, "percentage": 36.89, "elapsed_time": "0:19:55", "remaining_time": "0:34:06"}
+{"current_steps": 560, "total_steps": 1491, "loss": 0.6501843929290771, "lr": 1.438631492133601e-05, "epoch": 1.1268882175226587, "percentage": 37.56, "elapsed_time": "0:20:17", "remaining_time": "0:33:43"}
+{"current_steps": 570, "total_steps": 1491, "loss": 0.6371057510375977, "lr": 1.4190049892790838e-05, "epoch": 1.147029204431017, "percentage": 38.23, "elapsed_time": "0:20:38", "remaining_time": "0:33:21"}
+{"current_steps": 580, "total_steps": 1491, "loss": 0.6492814540863037, "lr": 1.3991807142127082e-05, "epoch": 1.1671701913393757, "percentage": 38.9, "elapsed_time": "0:21:00", "remaining_time": "0:32:59"}
+{"current_steps": 590, "total_steps": 1491, "loss": 0.6572648048400879, "lr": 1.3791680240801608e-05, "epoch": 1.1873111782477341, "percentage": 39.57, "elapsed_time": "0:21:21", "remaining_time": "0:32:37"}
+{"current_steps": 600, "total_steps": 1491, "loss": 0.6534214496612549, "lr": 1.358976364959876e-05, "epoch": 1.2074521651560928, "percentage": 40.24, "elapsed_time": "0:21:42", "remaining_time": "0:32:14"}
+{"current_steps": 610, "total_steps": 1491, "loss": 0.6604917526245118, "lr": 1.3386152674044421e-05, "epoch": 1.2275931520644512, "percentage": 40.91, "elapsed_time": "0:22:19", "remaining_time": "0:32:14"}
+{"current_steps": 620, "total_steps": 1491, "loss": 0.6616671085357666, "lr": 1.3180943419421409e-05, "epoch": 1.2477341389728096, "percentage": 41.58, "elapsed_time": "0:22:40", "remaining_time": "0:31:51"}
+{"current_steps": 630, "total_steps": 1491, "loss": 0.6450593948364258, "lr": 1.2974232745407326e-05, "epoch": 1.2678751258811682, "percentage": 42.25, "elapsed_time": "0:23:03", "remaining_time": "0:31:30"}
+{"current_steps": 640, "total_steps": 1491, "loss": 0.6392330169677735, "lr": 1.276611822035641e-05, "epoch": 1.2880161127895267, "percentage": 42.92, "elapsed_time": "0:23:26", "remaining_time": "0:31:09"}
+{"current_steps": 650, "total_steps": 1491, "loss": 0.6576297283172607, "lr": 1.2556698075246776e-05, "epoch": 1.308157099697885, "percentage": 43.59, "elapsed_time": "0:23:47", "remaining_time": "0:30:46"}
+{"current_steps": 660, "total_steps": 1491, "loss": 0.6367029666900634, "lr": 1.2346071157315026e-05, "epoch": 1.3282980866062437, "percentage": 44.27, "elapsed_time": "0:24:08", "remaining_time": "0:30:23"}
+{"current_steps": 670, "total_steps": 1491, "loss": 0.6807767868041992, "lr": 1.2134336883399855e-05, "epoch": 1.3484390735146023, "percentage": 44.94, "elapsed_time": "0:24:28", "remaining_time": "0:29:59"}
+{"current_steps": 680, "total_steps": 1491, "loss": 0.6392487525939942, "lr": 1.1921595193016905e-05, "epoch": 1.3685800604229608, "percentage": 45.61, "elapsed_time": "0:24:49", "remaining_time": "0:29:36"}
+{"current_steps": 690, "total_steps": 1491, "loss": 0.6165999889373779, "lr": 1.1707946501186853e-05, "epoch": 1.3887210473313192, "percentage": 46.28, "elapsed_time": "0:25:10", "remaining_time": "0:29:13"}
+{"current_steps": 700, "total_steps": 1491, "loss": 0.6656947135925293, "lr": 1.1493491651039077e-05, "epoch": 1.4088620342396778, "percentage": 46.95, "elapsed_time": "0:25:31", "remaining_time": "0:28:50"}
+{"current_steps": 710, "total_steps": 1491, "loss": 0.6254322528839111, "lr": 1.1278331866213253e-05, "epoch": 1.4290030211480362, "percentage": 47.62, "elapsed_time": "0:25:52", "remaining_time": "0:28:27"}
+{"current_steps": 720, "total_steps": 1491, "loss": 0.6936765670776367, "lr": 1.1062568703081345e-05, "epoch": 1.4491440080563947, "percentage": 48.29, "elapsed_time": "0:26:13", "remaining_time": "0:28:04"}
+{"current_steps": 730, "total_steps": 1491, "loss": 0.6438858032226562, "lr": 1.0846304002812564e-05, "epoch": 1.4692849949647533, "percentage": 48.96, "elapsed_time": "0:26:34", "remaining_time": "0:27:41"}
+{"current_steps": 740, "total_steps": 1491, "loss": 0.6418643951416015, "lr": 1.0629639843303857e-05, "epoch": 1.4894259818731117, "percentage": 49.63, "elapsed_time": "0:26:54", "remaining_time": "0:27:18"}
+{"current_steps": 750, "total_steps": 1491, "loss": 0.6461330413818359, "lr": 1.0412678490998717e-05, "epoch": 1.5095669687814703, "percentage": 50.3, "elapsed_time": "0:27:15", "remaining_time": "0:26:55"}
+{"current_steps": 760, "total_steps": 1491, "loss": 0.6453229904174804, "lr": 1.0195522352616942e-05, "epoch": 1.5297079556898288, "percentage": 50.97, "elapsed_time": "0:27:36", "remaining_time": "0:26:33"}
+{"current_steps": 770, "total_steps": 1491, "loss": 0.6503273010253906, "lr": 9.978273926818233e-06, "epoch": 1.5498489425981874, "percentage": 51.64, "elapsed_time": "0:27:57", "remaining_time": "0:26:10"}
+{"current_steps": 780, "total_steps": 1491, "loss": 0.6495280265808105, "lr": 9.761035755822347e-06, "epoch": 1.5699899295065458, "percentage": 52.31, "elapsed_time": "0:28:18", "remaining_time": "0:25:47"}
+{"current_steps": 790, "total_steps": 1491, "loss": 0.6502289772033691, "lr": 9.543910377008741e-06, "epoch": 1.5901309164149042, "percentage": 52.98, "elapsed_time": "0:28:38", "remaining_time": "0:25:25"}
+{"current_steps": 800, "total_steps": 1491, "loss": 0.657621192932129, "lr": 9.327000274518453e-06, "epoch": 1.6102719033232629, "percentage": 53.66, "elapsed_time": "0:28:59", "remaining_time": "0:25:02"}
+{"current_steps": 810, "total_steps": 1491, "loss": 0.6535334587097168, "lr": 9.110407830881146e-06, "epoch": 1.6304128902316215, "percentage": 54.33, "elapsed_time": "0:29:20", "remaining_time": "0:24:40"}
+{"current_steps": 820, "total_steps": 1491, "loss": 0.6586101531982422, "lr": 8.894235278690104e-06, "epoch": 1.6505538771399797, "percentage": 55.0, "elapsed_time": "0:29:41", "remaining_time": "0:24:17"}
+{"current_steps": 830, "total_steps": 1491, "loss": 0.6694258689880371, "lr": 8.678584652347974e-06, "epoch": 1.6706948640483383, "percentage": 55.67, "elapsed_time": "0:30:02", "remaining_time": "0:23:55"}
+{"current_steps": 840, "total_steps": 1491, "loss": 0.6554967403411865, "lr": 8.463557739906094e-06, "epoch": 1.690835850956697, "percentage": 56.34, "elapsed_time": "0:30:23", "remaining_time": "0:23:33"}
+{"current_steps": 850, "total_steps": 1491, "loss": 0.6524125099182129, "lr": 8.249256035020086e-06, "epoch": 1.7109768378650554, "percentage": 57.01, "elapsed_time": "0:30:44", "remaining_time": "0:23:10"}
+{"current_steps": 860, "total_steps": 1491, "loss": 0.6640297889709472, "lr": 8.035780689044381e-06, "epoch": 1.7311178247734138, "percentage": 57.68, "elapsed_time": "0:31:05", "remaining_time": "0:22:48"}
+{"current_steps": 870, "total_steps": 1491, "loss": 0.6420666694641113, "lr": 7.823232463288344e-06, "epoch": 1.7512588116817724, "percentage": 58.35, "elapsed_time": "0:31:26", "remaining_time": "0:22:26"}
+{"current_steps": 880, "total_steps": 1491, "loss": 0.6338119506835938, "lr": 7.611711681456493e-06, "epoch": 1.771399798590131, "percentage": 59.02, "elapsed_time": "0:31:47", "remaining_time": "0:22:04"}
+{"current_steps": 890, "total_steps": 1491, "loss": 0.6390099048614502, "lr": 7.4013181822952484e-06, "epoch": 1.7915407854984893, "percentage": 59.69, "elapsed_time": "0:32:07", "remaining_time": "0:21:41"}
+{"current_steps": 900, "total_steps": 1491, "loss": 0.6316941261291504, "lr": 7.19215127246863e-06, "epoch": 1.811681772406848, "percentage": 60.36, "elapsed_time": "0:32:28", "remaining_time": "0:21:19"}
+{"current_steps": 910, "total_steps": 1491, "loss": 0.6456757068634034, "lr": 6.984309679685049e-06, "epoch": 1.8318227593152066, "percentage": 61.03, "elapsed_time": "0:33:03", "remaining_time": "0:21:06"}
+{"current_steps": 920, "total_steps": 1491, "loss": 0.6603025436401367, "lr": 6.777891506097394e-06, "epoch": 1.851963746223565, "percentage": 61.7, "elapsed_time": "0:33:25", "remaining_time": "0:20:44"}
+{"current_steps": 930, "total_steps": 1491, "loss": 0.6764796257019043, "lr": 6.572994181998385e-06, "epoch": 1.8721047331319234, "percentage": 62.37, "elapsed_time": "0:33:45", "remaining_time": "0:20:22"}
+{"current_steps": 940, "total_steps": 1491, "loss": 0.632731819152832, "lr": 6.369714419833056e-06, "epoch": 1.892245720040282, "percentage": 63.04, "elapsed_time": "0:34:06", "remaining_time": "0:19:59"}
+{"current_steps": 950, "total_steps": 1491, "loss": 0.6480500221252441, "lr": 6.168148168550029e-06, "epoch": 1.9123867069486404, "percentage": 63.72, "elapsed_time": "0:34:27", "remaining_time": "0:19:37"}
+{"current_steps": 960, "total_steps": 1491, "loss": 0.6275962352752685, "lr": 5.968390568313194e-06, "epoch": 1.9325276938569989, "percentage": 64.39, "elapsed_time": "0:34:50", "remaining_time": "0:19:16"}
+{"current_steps": 970, "total_steps": 1491, "loss": 0.6480206489562989, "lr": 5.770535905595138e-06, "epoch": 1.9526686807653575, "percentage": 65.06, "elapsed_time": "0:35:11", "remaining_time": "0:18:53"}
+{"current_steps": 980, "total_steps": 1491, "loss": 0.6083292007446289, "lr": 5.574677568673499e-06, "epoch": 1.9728096676737161, "percentage": 65.73, "elapsed_time": "0:35:31", "remaining_time": "0:18:31"}
+{"current_steps": 990, "total_steps": 1491, "loss": 0.6685420989990234, "lr": 5.3809080035513e-06, "epoch": 1.9929506545820745, "percentage": 66.4, "elapsed_time": "0:35:52", "remaining_time": "0:18:09"}
+{"current_steps": 1000, "total_steps": 1491, "loss": 0.6245943069458008, "lr": 5.189318670322016e-06, "epoch": 2.012084592145015, "percentage": 67.07, "elapsed_time": "0:36:12", "remaining_time": "0:17:46"}
+{"current_steps": 1010, "total_steps": 1491, "loss": 0.5742752552032471, "lr": 5.000000000000003e-06, "epoch": 2.0322255790533736, "percentage": 67.74, "elapsed_time": "0:36:33", "remaining_time": "0:17:24"}
+{"current_steps": 1020, "total_steps": 1491, "loss": 0.6170816421508789, "lr": 4.813041351836657e-06, "epoch": 2.0523665659617323, "percentage": 68.41, "elapsed_time": "0:36:54", "remaining_time": "0:17:02"}
+{"current_steps": 1030, "total_steps": 1491, "loss": 0.5987297058105469, "lr": 4.6285309711424706e-06, "epoch": 2.0725075528700905, "percentage": 69.08, "elapsed_time": "0:37:15", "remaining_time": "0:16:40"}
+{"current_steps": 1040, "total_steps": 1491, "loss": 0.6134644508361816, "lr": 4.446555947634825e-06, "epoch": 2.092648539778449, "percentage": 69.75, "elapsed_time": "0:37:35", "remaining_time": "0:16:18"}
+{"current_steps": 1050, "total_steps": 1491, "loss": 0.5931161403656006, "lr": 4.267202174331288e-06, "epoch": 2.1127895266868078, "percentage": 70.42, "elapsed_time": "0:37:56", "remaining_time": "0:15:56"}
+{"current_steps": 1060, "total_steps": 1491, "loss": 0.5778852939605713, "lr": 4.0905543070077036e-06, "epoch": 2.1329305135951664, "percentage": 71.09, "elapsed_time": "0:38:17", "remaining_time": "0:15:34"}
+{"current_steps": 1070, "total_steps": 1491, "loss": 0.5790260791778564, "lr": 3.916695724240302e-06, "epoch": 2.1530715005035246, "percentage": 71.76, "elapsed_time": "0:38:38", "remaining_time": "0:15:12"}
+{"current_steps": 1080, "total_steps": 1491, "loss": 0.5704402446746826, "lr": 3.7457084880506465e-06, "epoch": 2.173212487411883, "percentage": 72.43, "elapsed_time": "0:38:58", "remaining_time": "0:14:50"}
+{"current_steps": 1090, "total_steps": 1491, "loss": 0.5825461864471435, "lr": 3.5776733051719935e-06, "epoch": 2.193353474320242, "percentage": 73.11, "elapsed_time": "0:39:19", "remaining_time": "0:14:28"}
+{"current_steps": 1100, "total_steps": 1491, "loss": 0.5475648880004883, "lr": 3.412669488955346e-06, "epoch": 2.2134944612286, "percentage": 73.78, "elapsed_time": "0:39:40", "remaining_time": "0:14:06"}
+{"current_steps": 1110, "total_steps": 1491, "loss": 0.5859562873840332, "lr": 3.2507749219332065e-06, "epoch": 2.2336354481369587, "percentage": 74.45, "elapsed_time": "0:40:01", "remaining_time": "0:13:44"}
+{"current_steps": 1120, "total_steps": 1491, "loss": 0.5725872039794921, "lr": 3.0920660190586893e-06, "epoch": 2.2537764350453173, "percentage": 75.12, "elapsed_time": "0:40:21", "remaining_time": "0:13:22"}
+{"current_steps": 1130, "total_steps": 1491, "loss": 0.5810467720031738, "lr": 2.9366176916373024e-06, "epoch": 2.2739174219536755, "percentage": 75.79, "elapsed_time": "0:40:42", "remaining_time": "0:13:00"}
+{"current_steps": 1140, "total_steps": 1491, "loss": 0.5589536666870117, "lr": 2.7845033119684996e-06, "epoch": 2.294058408862034, "percentage": 76.46, "elapsed_time": "0:41:03", "remaining_time": "0:12:38"}
+{"current_steps": 1150, "total_steps": 1491, "loss": 0.5693657875061036, "lr": 2.635794678713611e-06, "epoch": 2.314199395770393, "percentage": 77.13, "elapsed_time": "0:41:24", "remaining_time": "0:12:16"}
+{"current_steps": 1160, "total_steps": 1491, "loss": 0.5591839790344239, "lr": 2.4905619830065685e-06, "epoch": 2.3343403826787514, "percentage": 77.8, "elapsed_time": "0:41:45", "remaining_time": "0:11:54"}
+{"current_steps": 1170, "total_steps": 1491, "loss": 0.5525025367736817, "lr": 2.3488737753233827e-06, "epoch": 2.3544813695871096, "percentage": 78.47, "elapsed_time": "0:42:06", "remaining_time": "0:11:33"}
+{"current_steps": 1180, "total_steps": 1491, "loss": 0.5566308498382568, "lr": 2.210796933126005e-06, "epoch": 2.3746223564954683, "percentage": 79.14, "elapsed_time": "0:42:26", "remaining_time": "0:11:11"}
+{"current_steps": 1190, "total_steps": 1491, "loss": 0.5564406394958497, "lr": 2.0763966292958704e-06, "epoch": 2.394763343403827, "percentage": 79.81, "elapsed_time": "0:42:47", "remaining_time": "0:10:49"}
+{"current_steps": 1200, "total_steps": 1491, "loss": 0.5888455390930176, "lr": 1.94573630137201e-06, "epoch": 2.4149043303121855, "percentage": 80.48, "elapsed_time": "0:43:08", "remaining_time": "0:10:27"}
+{"current_steps": 1210, "total_steps": 1491, "loss": 0.5436674594879151, "lr": 1.8188776216082604e-06, "epoch": 2.4350453172205437, "percentage": 81.15, "elapsed_time": "0:43:43", "remaining_time": "0:10:09"}
+{"current_steps": 1220, "total_steps": 1491, "loss": 0.5791024208068848, "lr": 1.6958804678636743e-06, "epoch": 2.4551863041289024, "percentage": 81.82, "elapsed_time": "0:44:04", "remaining_time": "0:09:47"}
+{"current_steps": 1230, "total_steps": 1491, "loss": 0.5947460174560547, "lr": 1.5768028953399083e-06, "epoch": 2.475327291037261, "percentage": 82.49, "elapsed_time": "0:44:25", "remaining_time": "0:09:25"}
+{"current_steps": 1240, "total_steps": 1491, "loss": 0.6078821659088135, "lr": 1.4617011091789135e-06, "epoch": 2.495468277945619, "percentage": 83.17, "elapsed_time": "0:44:46", "remaining_time": "0:09:03"}
+{"current_steps": 1250, "total_steps": 1491, "loss": 0.576723861694336, "lr": 1.3506294379338557e-06, "epoch": 2.515609264853978, "percentage": 83.84, "elapsed_time": "0:45:06", "remaining_time": "0:08:41"}
+{"current_steps": 1260, "total_steps": 1491, "loss": 0.5891146659851074, "lr": 1.2436403079258064e-06, "epoch": 2.5357502517623365, "percentage": 84.51, "elapsed_time": "0:45:27", "remaining_time": "0:08:20"}
+{"current_steps": 1270, "total_steps": 1491, "loss": 0.5659162044525147, "lr": 1.1407842184982786e-06, "epoch": 2.5558912386706947, "percentage": 85.18, "elapsed_time": "0:45:48", "remaining_time": "0:07:58"}
+{"current_steps": 1280, "total_steps": 1491, "loss": 0.5638632774353027, "lr": 1.04210971818131e-06, "epoch": 2.5760322255790533, "percentage": 85.85, "elapsed_time": "0:46:11", "remaining_time": "0:07:36"}
+{"current_steps": 1290, "total_steps": 1491, "loss": 0.556513786315918, "lr": 9.476633817763481e-07, "epoch": 2.596173212487412, "percentage": 86.52, "elapsed_time": "0:46:32", "remaining_time": "0:07:15"}
+{"current_steps": 1300, "total_steps": 1491, "loss": 0.5709822654724122, "lr": 8.574897883727384e-07, "epoch": 2.61631419939577, "percentage": 87.19, "elapsed_time": "0:46:53", "remaining_time": "0:06:53"}
+{"current_steps": 1310, "total_steps": 1491, "loss": 0.602019214630127, "lr": 7.716315003061948e-07, "epoch": 2.636455186304129, "percentage": 87.86, "elapsed_time": "0:47:14", "remaining_time": "0:06:31"}
+{"current_steps": 1320, "total_steps": 1491, "loss": 0.5823301315307617, "lr": 6.901290430691842e-07, "epoch": 2.6565961732124874, "percentage": 88.53, "elapsed_time": "0:47:35", "remaining_time": "0:06:09"}
+{"current_steps": 1330, "total_steps": 1491, "loss": 0.571865463256836, "lr": 6.130208861827203e-07, "epoch": 2.676737160120846, "percentage": 89.2, "elapsed_time": "0:47:56", "remaining_time": "0:05:48"}
+{"current_steps": 1340, "total_steps": 1491, "loss": 0.5906769752502441, "lr": 5.40343425038573e-07, "epoch": 2.6968781470292047, "percentage": 89.87, "elapsed_time": "0:48:17", "remaining_time": "0:05:26"}
+{"current_steps": 1350, "total_steps": 1491, "loss": 0.5911761283874511, "lr": 4.7213096372049404e-07, "epoch": 2.717019133937563, "percentage": 90.54, "elapsed_time": "0:48:37", "remaining_time": "0:05:04"}
+{"current_steps": 1360, "total_steps": 1491, "loss": 0.5763310432434082, "lr": 4.084156988125232e-07, "epoch": 2.7371601208459215, "percentage": 91.21, "elapsed_time": "0:48:58", "remaining_time": "0:04:43"}
+{"current_steps": 1370, "total_steps": 1491, "loss": 0.5731249332427979, "lr": 3.4922770420206754e-07, "epoch": 2.75730110775428, "percentage": 91.88, "elapsed_time": "0:49:19", "remaining_time": "0:04:21"}
+{"current_steps": 1380, "total_steps": 1491, "loss": 0.5795963764190674, "lr": 2.9459491688488604e-07, "epoch": 2.7774420946626384, "percentage": 92.56, "elapsed_time": "0:49:40", "remaining_time": "0:03:59"}
+{"current_steps": 1390, "total_steps": 1491, "loss": 0.580109691619873, "lr": 2.4454312377871105e-07, "epoch": 2.797583081570997, "percentage": 93.23, "elapsed_time": "0:50:00", "remaining_time": "0:03:38"}
+{"current_steps": 1400, "total_steps": 1491, "loss": 0.6225358009338379, "lr": 1.9909594955170752e-07, "epoch": 2.8177240684793556, "percentage": 93.9, "elapsed_time": "0:50:21", "remaining_time": "0:03:16"}
+{"current_steps": 1410, "total_steps": 1491, "loss": 0.5751284599304199, "lr": 1.5827484547151772e-07, "epoch": 2.837865055387714, "percentage": 94.57, "elapsed_time": "0:50:42", "remaining_time": "0:02:54"}
+{"current_steps": 1420, "total_steps": 1491, "loss": 0.6069238662719727, "lr": 1.2209907928017794e-07, "epoch": 2.8580060422960725, "percentage": 95.24, "elapsed_time": "0:51:03", "remaining_time": "0:02:33"}
+{"current_steps": 1430, "total_steps": 1491, "loss": 0.5654289245605468, "lr": 9.058572609964788e-08, "epoch": 2.878147029204431, "percentage": 95.91, "elapsed_time": "0:51:23", "remaining_time": "0:02:11"}
+{"current_steps": 1440, "total_steps": 1491, "loss": 0.5597522735595704, "lr": 6.374966037229202e-08, "epoch": 2.8982880161127893, "percentage": 96.58, "elapsed_time": "0:51:44", "remaining_time": "0:01:49"}
+{"current_steps": 1450, "total_steps": 1491, "loss": 0.5661287784576416, "lr": 4.1603548840062344e-08, "epoch": 2.918429003021148, "percentage": 97.25, "elapsed_time": "0:52:05", "remaining_time": "0:01:28"}
+{"current_steps": 1460, "total_steps": 1491, "loss": 0.5586350440979004, "lr": 2.4157844565747546e-08, "epoch": 2.9385699899295066, "percentage": 97.92, "elapsed_time": "0:52:25", "remaining_time": "0:01:06"}
+{"current_steps": 1470, "total_steps": 1491, "loss": 0.5903618335723877, "lr": 1.14207819990797e-08, "epoch": 2.958710976837865, "percentage": 98.59, "elapsed_time": "0:52:46", "remaining_time": "0:00:45"}
+{"current_steps": 1480, "total_steps": 1491, "loss": 0.5927345275878906, "lr": 3.3983730900377654e-09, "epoch": 2.9788519637462234, "percentage": 99.26, "elapsed_time": "0:53:07", "remaining_time": "0:00:23"}
+{"current_steps": 1490, "total_steps": 1491, "loss": 0.571845006942749, "lr": 9.44044511796971e-11, "epoch": 2.998992950654582, "percentage": 99.93, "elapsed_time": "0:53:28", "remaining_time": "0:00:02"}
+{"current_steps": 1491, "total_steps": 1491, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:53:42", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..e2ad092
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,1086 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1491,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02014098690835851,
+      "grad_norm": 17.982622939860434,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.073244094848633,
+      "step": 10
+    },
+    {
+      "epoch": 0.04028197381671702,
+      "grad_norm": 4.416304162538307,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 2.2913312911987305,
+      "step": 20
+    },
+    {
+      "epoch": 0.06042296072507553,
+      "grad_norm": 2.3255969684771034,
+      "learning_rate": 1.288888888888889e-05,
+      "loss": 1.5302621841430664,
+      "step": 30
+    },
+    {
+      "epoch": 0.08056394763343404,
+      "grad_norm": 3.3171831937075003,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 1.0828689575195312,
+      "step": 40
+    },
+    {
+      "epoch": 0.10070493454179255,
+      "grad_norm": 0.8556098890983025,
+      "learning_rate": 1.9999622383977725e-05,
+      "loss": 0.8968555450439453,
+      "step": 50
+    },
+    {
+      "epoch": 0.12084592145015106,
+      "grad_norm": 0.8935143428003198,
+      "learning_rate": 1.999537453124055e-05,
+      "loss": 0.8666976928710938,
+      "step": 60
+    },
+    {
+      "epoch": 0.14098690835850958,
+      "grad_norm": 0.9119446875586649,
+      "learning_rate": 1.998640881742778e-05,
+      "loss": 0.8250602722167969,
+      "step": 70
+    },
+    {
+      "epoch": 0.16112789526686808,
+      "grad_norm": 0.7723616857133194,
+      "learning_rate": 1.997272947439608e-05,
+      "loss": 0.8222087860107422,
+      "step": 80
+    },
+    {
+      "epoch": 0.18126888217522658,
+      "grad_norm": 0.7086293310893315,
+      "learning_rate": 1.995434295885598e-05,
+      "loss": 0.7954679489135742,
+      "step": 90
+    },
+    {
+      "epoch": 0.2014098690835851,
+      "grad_norm": 0.8182937768539513,
+      "learning_rate": 1.993125794932429e-05,
+      "loss": 0.8072474479675293,
+      "step": 100
+    },
+    {
+      "epoch": 0.2215508559919436,
+      "grad_norm": 0.7354938507346823,
+      "learning_rate": 1.9903485342027827e-05,
+      "loss": 0.8378339767456054,
+      "step": 110
+    },
+    {
+      "epoch": 0.24169184290030213,
+      "grad_norm": 0.7384628140878121,
+      "learning_rate": 1.9871038245760305e-05,
+      "loss": 0.7969758987426758,
+      "step": 120
+    },
+    {
+      "epoch": 0.2618328298086606,
+      "grad_norm": 0.7270112546895067,
+      "learning_rate": 1.983393197569497e-05,
+      "loss": 0.837348747253418,
+      "step": 130
+    },
+    {
+      "epoch": 0.28197381671701915,
+      "grad_norm": 1.152458861127753,
+      "learning_rate": 1.9792184046155733e-05,
+      "loss": 0.7704894065856933,
+      "step": 140
+    },
+    {
+      "epoch": 0.3021148036253776,
+      "grad_norm": 0.7830669702448827,
+      "learning_rate": 1.974581416235035e-05,
+      "loss": 0.7638654708862305,
+      "step": 150
+    },
+    {
+      "epoch": 0.32225579053373615,
+      "grad_norm": 0.662909194939404,
+      "learning_rate": 1.9694844211069477e-05,
+      "loss": 0.7630445480346679,
+      "step": 160
+    },
+    {
+      "epoch": 0.3423967774420947,
+      "grad_norm": 0.6068166763286809,
+      "learning_rate": 1.963929825035601e-05,
+      "loss": 0.79698166847229,
+      "step": 170
+    },
+    {
+      "epoch": 0.36253776435045315,
+      "grad_norm": 0.7231230225443792,
+      "learning_rate": 1.9579202498149562e-05,
+      "loss": 0.7727674961090087,
+      "step": 180
+    },
+    {
+      "epoch": 0.3826787512588117,
+      "grad_norm": 0.6798705825407562,
+      "learning_rate": 1.951458531991151e-05,
+      "loss": 0.7765314102172851,
+      "step": 190
+    },
+    {
+      "epoch": 0.4028197381671702,
+      "grad_norm": 0.601709580862295,
+      "learning_rate": 1.9445477215236343e-05,
+      "loss": 0.7855539321899414,
+      "step": 200
+    },
+    {
+      "epoch": 0.4229607250755287,
+      "grad_norm": 0.7559675683509207,
+      "learning_rate": 1.937191080345574e-05,
+      "loss": 0.7797715187072753,
+      "step": 210
+    },
+    {
+      "epoch": 0.4431017119838872,
+      "grad_norm": 0.6437182934735217,
+      "learning_rate": 1.9293920808242084e-05,
+      "loss": 0.7819314956665039,
+      "step": 220
+    },
+    {
+      "epoch": 0.46324269889224573,
+      "grad_norm": 0.6520667495447376,
+      "learning_rate": 1.9211544041218752e-05,
+      "loss": 0.7715907096862793,
+      "step": 230
+    },
+    {
+      "epoch": 0.48338368580060426,
+      "grad_norm": 0.6479556212268033,
+      "learning_rate": 1.912481938458485e-05,
+      "loss": 0.7307522296905518,
+      "step": 240
+    },
+    {
+      "epoch": 0.5035246727089627,
+      "grad_norm": 0.6205427420369014,
+      "learning_rate": 1.9033787772762647e-05,
+      "loss": 0.7505370616912842,
+      "step": 250
+    },
+    {
+      "epoch": 0.5236656596173213,
+      "grad_norm": 0.6301103631446919,
+      "learning_rate": 1.893849217307635e-05,
+      "loss": 0.7448963165283203,
+      "step": 260
+    },
+    {
+      "epoch": 0.5438066465256798,
+      "grad_norm": 0.6054604049411163,
+      "learning_rate": 1.8838977565471343e-05,
+      "loss": 0.7512392044067383,
+      "step": 270
+    },
+    {
+      "epoch": 0.5639476334340383,
+      "grad_norm": 0.6641842324027172,
+      "learning_rate": 1.873529092128343e-05,
+      "loss": 0.7734776496887207,
+      "step": 280
+    },
+    {
+      "epoch": 0.5840886203423967,
+      "grad_norm": 0.6881766972436127,
+      "learning_rate": 1.8627481181068185e-05,
+      "loss": 0.7516597747802735,
+      "step": 290
+    },
+    {
+      "epoch": 0.6042296072507553,
+      "grad_norm": 0.7114932246416025,
+      "learning_rate": 1.851559923150077e-05,
+      "loss": 0.7655241966247559,
+      "step": 300
+    },
+    {
+      "epoch": 0.6243705941591138,
+      "grad_norm": 0.6808053148104048,
+      "learning_rate": 1.8399697881357214e-05,
+      "loss": 0.7743952751159668,
+      "step": 310
+    },
+    {
+      "epoch": 0.6445115810674723,
+      "grad_norm": 0.633401029258308,
+      "learning_rate": 1.8279831836588427e-05,
+      "loss": 0.7196044445037841,
+      "step": 320
+    },
+    {
+      "epoch": 0.6646525679758308,
+      "grad_norm": 0.635189452406444,
+      "learning_rate": 1.8156057674498756e-05,
+      "loss": 0.7735816955566406,
+      "step": 330
+    },
+    {
+      "epoch": 0.6847935548841894,
+      "grad_norm": 0.6079022064378636,
+      "learning_rate": 1.8028433817041237e-05,
+      "loss": 0.7698081970214844,
+      "step": 340
+    },
+    {
+      "epoch": 0.7049345417925479,
+      "grad_norm": 0.6691748614288394,
+      "learning_rate": 1.7897020503242192e-05,
+      "loss": 0.7545667171478272,
+      "step": 350
+    },
+    {
+      "epoch": 0.7250755287009063,
+      "grad_norm": 0.6704403785715234,
+      "learning_rate": 1.7761879760768123e-05,
+      "loss": 0.7272197723388671,
+      "step": 360
+    },
+    {
+      "epoch": 0.7452165156092648,
+      "grad_norm": 0.6248181535199508,
+      "learning_rate": 1.7623075376648374e-05,
+      "loss": 0.735597801208496,
+      "step": 370
+    },
+    {
+      "epoch": 0.7653575025176234,
+      "grad_norm": 0.6691162481904424,
+      "learning_rate": 1.748067286716741e-05,
+      "loss": 0.7506361484527588,
+      "step": 380
+    },
+    {
+      "epoch": 0.7854984894259819,
+      "grad_norm": 0.5985017428584295,
+      "learning_rate": 1.7334739446940785e-05,
+      "loss": 0.7382652282714843,
+      "step": 390
+    },
+    {
+      "epoch": 0.8056394763343404,
+      "grad_norm": 0.674850678027072,
+      "learning_rate": 1.718534399718959e-05,
+      "loss": 0.7026462554931641,
+      "step": 400
+    },
+    {
+      "epoch": 0.8257804632426989,
+      "grad_norm": 0.575762458028171,
+      "learning_rate": 1.7032557033228184e-05,
+      "loss": 0.7259914398193359,
+      "step": 410
+    },
+    {
+      "epoch": 0.8459214501510574,
+      "grad_norm": 0.6224947992992479,
+      "learning_rate": 1.6876450671180667e-05,
+      "loss": 0.7931873798370361,
+      "step": 420
+    },
+    {
+      "epoch": 0.8660624370594159,
+      "grad_norm": 0.6047243356309274,
+      "learning_rate": 1.6717098593941753e-05,
+      "loss": 0.726997709274292,
+      "step": 430
+    },
+    {
+      "epoch": 0.8862034239677744,
+      "grad_norm": 0.618674243738717,
+      "learning_rate": 1.65545760163981e-05,
+      "loss": 0.7656588554382324,
+      "step": 440
+    },
+    {
+      "epoch": 0.9063444108761329,
+      "grad_norm": 0.6135808451328559,
+      "learning_rate": 1.6388959649926567e-05,
+      "loss": 0.7257630348205566,
+      "step": 450
+    },
+    {
+      "epoch": 0.9264853977844915,
+      "grad_norm": 0.5903369684800459,
+      "learning_rate": 1.62203276661861e-05,
+      "loss": 0.7346350669860839,
+      "step": 460
+    },
+    {
+      "epoch": 0.94662638469285,
+      "grad_norm": 0.6976504986685628,
+      "learning_rate": 1.604875966022035e-05,
+      "loss": 0.7640430450439453,
+      "step": 470
+    },
+    {
+      "epoch": 0.9667673716012085,
+      "grad_norm": 0.6035606483951823,
+      "learning_rate": 1.5874336612888487e-05,
+      "loss": 0.718746280670166,
+      "step": 480
+    },
+    {
+      "epoch": 0.9869083585095669,
+      "grad_norm": 0.6717571495166765,
+      "learning_rate": 1.5697140852641835e-05,
+      "loss": 0.7472597122192383,
+      "step": 490
+    },
+    {
+      "epoch": 1.0060422960725075,
+      "grad_norm": 0.7203444401990272,
+      "learning_rate": 1.5517256016664524e-05,
+      "loss": 0.7291147232055664,
+      "step": 500
+    },
+    {
+      "epoch": 1.0261832829808661,
+      "grad_norm": 0.6921694505639285,
+      "learning_rate": 1.533476701139633e-05,
+      "loss": 0.6633618354797364,
+      "step": 510
+    },
+    {
+      "epoch": 1.0463242698892246,
+      "grad_norm": 0.6349522071558343,
+      "learning_rate": 1.514975997245649e-05,
+      "loss": 0.6561120033264161,
+      "step": 520
+    },
+    {
+      "epoch": 1.0664652567975832,
+      "grad_norm": 0.6428241160936208,
+      "learning_rate": 1.4962322223987284e-05,
+      "loss": 0.651552963256836,
+      "step": 530
+    },
+    {
+      "epoch": 1.0866062437059416,
+      "grad_norm": 0.5614783554365259,
+      "learning_rate": 1.477254223743666e-05,
+      "loss": 0.6309733867645264,
+      "step": 540
+    },
+    {
+      "epoch": 1.1067472306143,
+      "grad_norm": 0.6136450539009461,
+      "learning_rate": 1.458050958979933e-05,
+      "loss": 0.6375226974487305,
+      "step": 550
+    },
+    {
+      "epoch": 1.1268882175226587,
+      "grad_norm": 0.5738680488992384,
+      "learning_rate": 1.438631492133601e-05,
+      "loss": 0.6501843929290771,
+      "step": 560
+    },
+    {
+      "epoch": 1.147029204431017,
+      "grad_norm": 0.6256698406539856,
+      "learning_rate": 1.4190049892790838e-05,
+      "loss": 0.6371057510375977,
+      "step": 570
+    },
+    {
+      "epoch": 1.1671701913393757,
+      "grad_norm": 0.5679189425501606,
+      "learning_rate": 1.3991807142127082e-05,
+      "loss": 0.6492814540863037,
+      "step": 580
+    },
+    {
+      "epoch": 1.1873111782477341,
+      "grad_norm": 0.6065846599142134,
+      "learning_rate": 1.3791680240801608e-05,
+      "loss": 0.6572648048400879,
+      "step": 590
+    },
+    {
+      "epoch": 1.2074521651560928,
+      "grad_norm": 0.6331239898292791,
+      "learning_rate": 1.358976364959876e-05,
+      "loss": 0.6534214496612549,
+      "step": 600
+    },
+    {
+      "epoch": 1.2275931520644512,
+      "grad_norm": 0.621707193585302,
+      "learning_rate": 1.3386152674044421e-05,
+      "loss": 0.6604917526245118,
+      "step": 610
+    },
+    {
+      "epoch": 1.2477341389728096,
+      "grad_norm": 0.6302732699277002,
+      "learning_rate": 1.3180943419421409e-05,
+      "loss": 0.6616671085357666,
+      "step": 620
+    },
+    {
+      "epoch": 1.2678751258811682,
+      "grad_norm": 0.6372781840535979,
+      "learning_rate": 1.2974232745407326e-05,
+      "loss": 0.6450593948364258,
+      "step": 630
+    },
+    {
+      "epoch": 1.2880161127895267,
+      "grad_norm": 0.5889507844368161,
+      "learning_rate": 1.276611822035641e-05,
+      "loss": 0.6392330169677735,
+      "step": 640
+    },
+    {
+      "epoch": 1.308157099697885,
+      "grad_norm": 0.6057569389599446,
+      "learning_rate": 1.2556698075246776e-05,
+      "loss": 0.6576297283172607,
+      "step": 650
+    },
+    {
+      "epoch": 1.3282980866062437,
+      "grad_norm": 0.9487405810829506,
+      "learning_rate": 1.2346071157315026e-05,
+      "loss": 0.6367029666900634,
+      "step": 660
+    },
+    {
+      "epoch": 1.3484390735146023,
+      "grad_norm": 0.5458544429535442,
+      "learning_rate": 1.2134336883399855e-05,
+      "loss": 0.6807767868041992,
+      "step": 670
+    },
+    {
+      "epoch": 1.3685800604229608,
+      "grad_norm": 0.5893035791406586,
+      "learning_rate": 1.1921595193016905e-05,
+      "loss": 0.6392487525939942,
+      "step": 680
+    },
+    {
+      "epoch": 1.3887210473313192,
+      "grad_norm": 0.6010604306346117,
+      "learning_rate": 1.1707946501186853e-05,
+      "loss": 0.6165999889373779,
+      "step": 690
+    },
+    {
+      "epoch": 1.4088620342396778,
+      "grad_norm": 0.6063068167039452,
+      "learning_rate": 1.1493491651039077e-05,
+      "loss": 0.6656947135925293,
+      "step": 700
+    },
+    {
+      "epoch": 1.4290030211480362,
+      "grad_norm": 0.6077129163598095,
+      "learning_rate": 1.1278331866213253e-05,
+      "loss": 0.6254322528839111,
+      "step": 710
+    },
+    {
+      "epoch": 1.4491440080563947,
+      "grad_norm": 0.5864287567502068,
+      "learning_rate": 1.1062568703081345e-05,
+      "loss": 0.6936765670776367,
+      "step": 720
+    },
+    {
+      "epoch": 1.4692849949647533,
+      "grad_norm": 0.6089793392201761,
+      "learning_rate": 1.0846304002812564e-05,
+      "loss": 0.6438858032226562,
+      "step": 730
+    },
+    {
+      "epoch": 1.4894259818731117,
+      "grad_norm": 0.6317374637004732,
+      "learning_rate": 1.0629639843303857e-05,
+      "loss": 0.6418643951416015,
+      "step": 740
+    },
+    {
+      "epoch": 1.5095669687814703,
+      "grad_norm": 0.6018478874762406,
+      "learning_rate": 1.0412678490998717e-05,
+      "loss": 0.6461330413818359,
+      "step": 750
+    },
+    {
+      "epoch": 1.5297079556898288,
+      "grad_norm": 0.5345160985133722,
+      "learning_rate": 1.0195522352616942e-05,
+      "loss": 0.6453229904174804,
+      "step": 760
+    },
+    {
+      "epoch": 1.5498489425981874,
+      "grad_norm": 0.6430235560122531,
+      "learning_rate": 9.978273926818233e-06,
+      "loss": 0.6503273010253906,
+      "step": 770
+    },
+    {
+      "epoch": 1.5699899295065458,
+      "grad_norm": 0.5938734205039293,
+      "learning_rate": 9.761035755822347e-06,
+      "loss": 0.6495280265808105,
+      "step": 780
+    },
+    {
+      "epoch": 1.5901309164149042,
+      "grad_norm": 0.5742568159918696,
+      "learning_rate": 9.543910377008741e-06,
+      "loss": 0.6502289772033691,
+      "step": 790
+    },
+    {
+      "epoch": 1.6102719033232629,
+      "grad_norm": 0.6183799064495971,
+      "learning_rate": 9.327000274518453e-06,
+      "loss": 0.657621192932129,
+      "step": 800
+    },
+    {
+      "epoch": 1.6304128902316215,
+      "grad_norm": 0.5746676315893429,
+      "learning_rate": 9.110407830881146e-06,
+      "loss": 0.6535334587097168,
+      "step": 810
+    },
+    {
+      "epoch": 1.6505538771399797,
+      "grad_norm": 0.6152747581447773,
+      "learning_rate": 8.894235278690104e-06,
+      "loss": 0.6586101531982422,
+      "step": 820
+    },
+    {
+      "epoch": 1.6706948640483383,
+      "grad_norm": 0.6175070299910487,
+      "learning_rate": 8.678584652347974e-06,
+      "loss": 0.6694258689880371,
+      "step": 830
+    },
+    {
+      "epoch": 1.690835850956697,
+      "grad_norm": 0.6490996006457843,
+      "learning_rate": 8.463557739906094e-06,
+      "loss": 0.6554967403411865,
+      "step": 840
+    },
+    {
+      "epoch": 1.7109768378650554,
+      "grad_norm": 0.6057747265761942,
+      "learning_rate": 8.249256035020086e-06,
+      "loss": 0.6524125099182129,
+      "step": 850
+    },
+    {
+      "epoch": 1.7311178247734138,
+      "grad_norm": 0.5781069954757457,
+      "learning_rate": 8.035780689044381e-06,
+      "loss": 0.6640297889709472,
+      "step": 860
+    },
+    {
+      "epoch": 1.7512588116817724,
+      "grad_norm": 0.5907306482202962,
+      "learning_rate": 7.823232463288344e-06,
+      "loss": 0.6420666694641113,
+      "step": 870
+    },
+    {
+      "epoch": 1.771399798590131,
+      "grad_norm": 0.6381794417859438,
+      "learning_rate": 7.611711681456493e-06,
+      "loss": 0.6338119506835938,
+      "step": 880
+    },
+    {
+      "epoch": 1.7915407854984893,
+      "grad_norm": 0.5790935289783766,
+      "learning_rate": 7.4013181822952484e-06,
+      "loss": 0.6390099048614502,
+      "step": 890
+    },
+    {
+      "epoch": 1.811681772406848,
+      "grad_norm": 0.5964904558967495,
+      "learning_rate": 7.19215127246863e-06,
+      "loss": 0.6316941261291504,
+      "step": 900
+    },
+    {
+      "epoch": 1.8318227593152066,
+      "grad_norm": 0.5909905502502826,
+      "learning_rate": 6.984309679685049e-06,
+      "loss": 0.6456757068634034,
+      "step": 910
+    },
+    {
+      "epoch": 1.851963746223565,
+      "grad_norm": 0.633551186863175,
+      "learning_rate": 6.777891506097394e-06,
+      "loss": 0.6603025436401367,
+      "step": 920
+    },
+    {
+      "epoch": 1.8721047331319234,
+      "grad_norm": 0.6405284882539302,
+      "learning_rate": 6.572994181998385e-06,
+      "loss": 0.6764796257019043,
+      "step": 930
+    },
+    {
+      "epoch": 1.892245720040282,
+      "grad_norm": 0.6414528571522098,
+      "learning_rate": 6.369714419833056e-06,
+      "loss": 0.632731819152832,
+      "step": 940
+    },
+    {
+      "epoch": 1.9123867069486404,
+      "grad_norm": 0.6234333012608522,
+      "learning_rate": 6.168148168550029e-06,
+      "loss": 0.6480500221252441,
+      "step": 950
+    },
+    {
+      "epoch": 1.9325276938569989,
+      "grad_norm": 0.6320726033761638,
+      "learning_rate": 5.968390568313194e-06,
+      "loss": 0.6275962352752685,
+      "step": 960
+    },
+    {
+      "epoch": 1.9526686807653575,
+      "grad_norm": 0.5637434358543838,
+      "learning_rate": 5.770535905595138e-06,
+      "loss": 0.6480206489562989,
+      "step": 970
+    },
+    {
+      "epoch": 1.9728096676737161,
+      "grad_norm": 0.5952218778997469,
+      "learning_rate": 5.574677568673499e-06,
+      "loss": 0.6083292007446289,
+      "step": 980
+    },
+    {
+      "epoch": 1.9929506545820745,
+      "grad_norm": 0.5734556241430626,
+      "learning_rate": 5.3809080035513e-06,
+      "loss": 0.6685420989990234,
+      "step": 990
+    },
+    {
+      "epoch": 2.012084592145015,
+      "grad_norm": 0.6523020868209938,
+      "learning_rate": 5.189318670322016e-06,
+      "loss": 0.6245943069458008,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0322255790533736,
+      "grad_norm": 0.6468582760996592,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.5742752552032471,
+      "step": 1010
+    },
+    {
+      "epoch": 2.0523665659617323,
+      "grad_norm": 0.6165364026803251,
+      "learning_rate": 4.813041351836657e-06,
+      "loss": 0.6170816421508789,
+      "step": 1020
+    },
+    {
+      "epoch": 2.0725075528700905,
+      "grad_norm": 0.649862444578371,
+      "learning_rate": 4.6285309711424706e-06,
+      "loss": 0.5987297058105469,
+      "step": 1030
+    },
+    {
+      "epoch": 2.092648539778449,
+      "grad_norm": 0.6632354933054281,
+      "learning_rate": 4.446555947634825e-06,
+      "loss": 0.6134644508361816,
+      "step": 1040
+    },
+    {
+      "epoch": 2.1127895266868078,
+      "grad_norm": 0.6292999693586733,
+      "learning_rate": 4.267202174331288e-06,
+      "loss": 0.5931161403656006,
+      "step": 1050
+    },
+    {
+      "epoch": 2.1329305135951664,
+      "grad_norm": 0.6886779328643787,
+      "learning_rate": 4.0905543070077036e-06,
+      "loss": 0.5778852939605713,
+      "step": 1060
+    },
+    {
+      "epoch": 2.1530715005035246,
+      "grad_norm": 0.6379340378669663,
+      "learning_rate": 3.916695724240302e-06,
+      "loss": 0.5790260791778564,
+      "step": 1070
+    },
+    {
+      "epoch": 2.173212487411883,
+      "grad_norm": 0.587608625604733,
+      "learning_rate": 3.7457084880506465e-06,
+      "loss": 0.5704402446746826,
+      "step": 1080
+    },
+    {
+      "epoch": 2.193353474320242,
+      "grad_norm": 0.578613328498253,
+      "learning_rate": 3.5776733051719935e-06,
+      "loss": 0.5825461864471435,
+      "step": 1090
+    },
+    {
+      "epoch": 2.2134944612286,
+      "grad_norm": 0.5893218858500716,
+      "learning_rate": 3.412669488955346e-06,
+      "loss": 0.5475648880004883,
+      "step": 1100
+    },
+    {
+      "epoch": 2.2336354481369587,
+      "grad_norm": 0.5728337624083586,
+      "learning_rate": 3.2507749219332065e-06,
+      "loss": 0.5859562873840332,
+      "step": 1110
+    },
+    {
+      "epoch": 2.2537764350453173,
+      "grad_norm": 0.5865892490266207,
+      "learning_rate": 3.0920660190586893e-06,
+      "loss": 0.5725872039794921,
+      "step": 1120
+    },
+    {
+      "epoch": 2.2739174219536755,
+      "grad_norm": 0.6813688024576977,
+      "learning_rate": 2.9366176916373024e-06,
+      "loss": 0.5810467720031738,
+      "step": 1130
+    },
+    {
+      "epoch": 2.294058408862034,
+      "grad_norm": 0.5564488853837758,
+      "learning_rate": 2.7845033119684996e-06,
+      "loss": 0.5589536666870117,
+      "step": 1140
+    },
+    {
+      "epoch": 2.314199395770393,
+      "grad_norm": 0.6221441575834261,
+      "learning_rate": 2.635794678713611e-06,
+      "loss": 0.5693657875061036,
+      "step": 1150
+    },
+    {
+      "epoch": 2.3343403826787514,
+      "grad_norm": 0.6142938109628727,
+      "learning_rate": 2.4905619830065685e-06,
+      "loss": 0.5591839790344239,
+      "step": 1160
+    },
+    {
+      "epoch": 2.3544813695871096,
+      "grad_norm": 0.6040241814867302,
+      "learning_rate": 2.3488737753233827e-06,
+      "loss": 0.5525025367736817,
+      "step": 1170
+    },
+    {
+      "epoch": 2.3746223564954683,
+      "grad_norm": 0.5485294568778827,
+      "learning_rate": 2.210796933126005e-06,
+      "loss": 0.5566308498382568,
+      "step": 1180
+    },
+    {
+      "epoch": 2.394763343403827,
+      "grad_norm": 0.5991094942819453,
+      "learning_rate": 2.0763966292958704e-06,
+      "loss": 0.5564406394958497,
+      "step": 1190
+    },
+    {
+      "epoch": 2.4149043303121855,
+      "grad_norm": 0.5790075897305983,
+      "learning_rate": 1.94573630137201e-06,
+      "loss": 0.5888455390930176,
+      "step": 1200
+    },
+    {
+      "epoch": 2.4350453172205437,
+      "grad_norm": 0.5831452304720957,
+      "learning_rate": 1.8188776216082604e-06,
+      "loss": 0.5436674594879151,
+      "step": 1210
+    },
+    {
+      "epoch": 2.4551863041289024,
+      "grad_norm": 0.5538350696710048,
+      "learning_rate": 1.6958804678636743e-06,
+      "loss": 0.5791024208068848,
+      "step": 1220
+    },
+    {
+      "epoch": 2.475327291037261,
+      "grad_norm": 0.6004824349649384,
+      "learning_rate": 1.5768028953399083e-06,
+      "loss": 0.5947460174560547,
+      "step": 1230
+    },
+    {
+      "epoch": 2.495468277945619,
+      "grad_norm": 0.6013072332149644,
+      "learning_rate": 1.4617011091789135e-06,
+      "loss": 0.6078821659088135,
+      "step": 1240
+    },
+    {
+      "epoch": 2.515609264853978,
+      "grad_norm": 0.5770517074629651,
+      "learning_rate": 1.3506294379338557e-06,
+      "loss": 0.576723861694336,
+      "step": 1250
+    },
+    {
+      "epoch": 2.5357502517623365,
+      "grad_norm": 0.6118862530109742,
+      "learning_rate": 1.2436403079258064e-06,
+      "loss": 0.5891146659851074,
+      "step": 1260
+    },
+    {
+      "epoch": 2.5558912386706947,
+      "grad_norm": 0.6128217947924604,
+      "learning_rate": 1.1407842184982786e-06,
+      "loss": 0.5659162044525147,
+      "step": 1270
+    },
+    {
+      "epoch": 2.5760322255790533,
+      "grad_norm": 0.6192024814414648,
+      "learning_rate": 1.04210971818131e-06,
+      "loss": 0.5638632774353027,
+      "step": 1280
+    },
+    {
+      "epoch": 2.596173212487412,
+      "grad_norm": 0.5898775110317098,
+      "learning_rate": 9.476633817763481e-07,
+      "loss": 0.556513786315918,
+      "step": 1290
+    },
+    {
+      "epoch": 2.61631419939577,
+      "grad_norm": 0.6039004982453571,
+      "learning_rate": 8.574897883727384e-07,
+      "loss": 0.5709822654724122,
+      "step": 1300
+    },
+    {
+      "epoch": 2.636455186304129,
+      "grad_norm": 0.6240148606283491,
+      "learning_rate": 7.716315003061948e-07,
+      "loss": 0.602019214630127,
+      "step": 1310
+    },
+    {
+      "epoch": 2.6565961732124874,
+      "grad_norm": 0.6274955798619531,
+      "learning_rate": 6.901290430691842e-07,
+      "loss": 0.5823301315307617,
+      "step": 1320
+    },
+    {
+      "epoch": 2.676737160120846,
+      "grad_norm": 0.6252907977807435,
+      "learning_rate": 6.130208861827203e-07,
+      "loss": 0.571865463256836,
+      "step": 1330
+    },
+    {
+      "epoch": 2.6968781470292047,
+      "grad_norm": 0.6144848901151767,
+      "learning_rate": 5.40343425038573e-07,
+      "loss": 0.5906769752502441,
+      "step": 1340
+    },
+    {
+      "epoch": 2.717019133937563,
+      "grad_norm": 0.7200971287683633,
+      "learning_rate": 4.7213096372049404e-07,
+      "loss": 0.5911761283874511,
+      "step": 1350
+    },
+    {
+      "epoch": 2.7371601208459215,
+      "grad_norm": 0.6104854405112541,
+      "learning_rate": 4.084156988125232e-07,
+      "loss": 0.5763310432434082,
+      "step": 1360
+    },
+    {
+      "epoch": 2.75730110775428,
+      "grad_norm": 0.5464330677309381,
+      "learning_rate": 3.4922770420206754e-07,
+      "loss": 0.5731249332427979,
+      "step": 1370
+    },
+    {
+      "epoch": 2.7774420946626384,
+      "grad_norm": 0.6216489629404571,
+      "learning_rate": 2.9459491688488604e-07,
+      "loss": 0.5795963764190674,
+      "step": 1380
+    },
+    {
+      "epoch": 2.797583081570997,
+      "grad_norm": 0.62677128317226,
+      "learning_rate": 2.4454312377871105e-07,
+      "loss": 0.580109691619873,
+      "step": 1390
+    },
+    {
+      "epoch": 2.8177240684793556,
+      "grad_norm": 0.5976820703242487,
+      "learning_rate": 1.9909594955170752e-07,
+      "loss": 0.6225358009338379,
+      "step": 1400
+    },
+    {
+      "epoch": 2.837865055387714,
+      "grad_norm": 0.633710024857856,
+      "learning_rate": 1.5827484547151772e-07,
+      "loss": 0.5751284599304199,
+      "step": 1410
+    },
+    {
+      "epoch": 2.8580060422960725,
+      "grad_norm": 0.606609361073119,
+      "learning_rate": 1.2209907928017794e-07,
+      "loss": 0.6069238662719727,
+      "step": 1420
+    },
+    {
+      "epoch": 2.878147029204431,
+      "grad_norm": 0.6047426574267594,
+      "learning_rate": 9.058572609964788e-08,
+      "loss": 0.5654289245605468,
+      "step": 1430
+    },
+    {
+      "epoch": 2.8982880161127893,
+      "grad_norm": 0.6131232265425541,
+      "learning_rate": 6.374966037229202e-08,
+      "loss": 0.5597522735595704,
+      "step": 1440
+    },
+    {
+      "epoch": 2.918429003021148,
+      "grad_norm": 0.5824519340175841,
+      "learning_rate": 4.1603548840062344e-08,
+      "loss": 0.5661287784576416,
+      "step": 1450
+    },
+    {
+      "epoch": 2.9385699899295066,
+      "grad_norm": 0.5758313584108831,
+      "learning_rate": 2.4157844565747546e-08,
+      "loss": 0.5586350440979004,
+      "step": 1460
+    },
+    {
+      "epoch": 2.958710976837865,
+      "grad_norm": 0.6676715022794658,
+      "learning_rate": 1.14207819990797e-08,
+      "loss": 0.5903618335723877,
+      "step": 1470
+    },
+    {
+      "epoch": 2.9788519637462234,
+      "grad_norm": 0.6109078286891169,
+      "learning_rate": 3.3983730900377654e-09,
+      "loss": 0.5927345275878906,
+      "step": 1480
+    },
+    {
+      "epoch": 2.998992950654582,
+      "grad_norm": 0.569947241319677,
+      "learning_rate": 9.44044511796971e-11,
+      "loss": 0.571845006942749,
+      "step": 1490
+    },
+    {
+      "epoch": 3.0,
+      "step": 1491,
+      "total_flos": 145115603533824.0,
+      "train_loss": 0.698847218818268,
+      "train_runtime": 3222.3497,
+      "train_samples_per_second": 29.579,
+      "train_steps_per_second": 0.463
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1491,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 145115603533824.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_loss.png b/training_loss.png
new file mode 100644
index 0000000..3d893f6
Binary files /dev/null and b/training_loss.png differ