Upload folder using huggingface_hub

config.json

@@ -31,7 +31,7 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.52.0.dev0",
+  "transformers_version": "4.51.3",
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -2,5 +2,5 @@
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "max_new_tokens": 2048,
-  "transformers_version": "4.52.0.dev0"
+  "transformers_version": "4.51.3"
 }

model-00001-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9b2c12f4a823681fc7f310cd9e7d1858e1837c8f481e9dcd12eace93cf359a
+oid sha256:57a85535223cebac3dd0e72fbf05fe4b603448d7ebcf7e9188ff95434dd33275
 size 4997184968

model-00002-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61ce446fb5f531228ce12a40630dfcdfdec2dd922bedb6a3260a4d1c7bc40b8
+oid sha256:88b91999246cf00df72bb6aa9e3310f11543d4e9e8309083fcea7ac44e494e1e
 size 4997741608

model-00003-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f76b7b918c9237282a23ede0c5a0d71446af268c51a0dbc7ac551c083e2c992d
+oid sha256:9b7425331578264124afcf5e1833e363c0cdb4a6d99ddc5bd807065fe93dd375
 size 4997742208

model-00004-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3ac5da17858f468ba8f3d58198749475b57fcdfd0dd4726224ee2399a0f5563
+oid sha256:a7316764385fa4671f37ab5b5f76f92e904447a0eaa32cefc84cecd85d6208f5
 size 4997743184

model-00005-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11d79ac0ccfc09ed6f196a2534f5bcd9918311debc454677d49c5ebd2a4a48d1
+oid sha256:427108e6b1255a7a010b94923eef9ccc546e89a73cdbb81eee2c6fe0aa437bfc
 size 4997743184

model-00006-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901908dff02b9d781658e0927c4f4ce2a5dda97a1bf03c7ab53a6d97d3618f96
+oid sha256:348500d6adac68c5092ea88ec3ac831d5125a43e42230b15fa9b61728ee0e673
 size 4997743184

model-00007-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eff26f0bc7baca9d4c3ca570cd63ef3fe4ef36dffa97cdd61785dafd6320f60
+oid sha256:0841c5c324a96fa6c383872fb5401a4a5bdae3d83fcb8ede42ad301c36095618
 size 4997743184

model-00008-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a1283220f145deabf1acf2547012a120ed2ec5dd586635d8d85829654b53168
+oid sha256:37f54ad4f0f4128bbb156a4a07e91f35c4b2db410da3e1e98e7efda7f42a1a08
 size 4997743184

model-00009-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797f4a59966d4bdd65b32b12fa1fd004a03c13597984796b9140fb15e2f6dec6
+oid sha256:6ac266032d3a00504046cd79a5c493dfc66553f1714518683fb13555498de82a
 size 4997743184

model-00010-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8683679160d54cd4a07164d76aa0a2ce7ad71e1716147e80d7ed636fe589c33c
+oid sha256:ef686890e2a45882cf1ffc55cecdf2d173938de71d7e2fffa0cef56e0b45cbe3
 size 4997743184

model-00011-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b42071ed192ee4a5cebacede2084ffffaadbac6cf7f257dc046efd4f469c65
+oid sha256:f7a6c0e2c90ae7bed9f62b605700c77460c6cc35a1f42dc291084b0298d1503f
 size 4997743184

model-00012-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d985bd6981301dd6fb56cd7ad93fcfbefe563b16b848fde9445676a10bd27cb
+oid sha256:b917879e7198cdb7ef34ce981822dbe46fb678c77d02fc2b0add720ffa5a25ea
 size 4997743184

model-00013-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3877faca6e27120ba2f73085eabd9a0f9c8cc7bcdd3d06d54d4b578b80e0a07
+oid sha256:20b0e265aa4505aba6147edaac0b4148f92e84bb4fdd311cc5051f76d8ef3236
 size 1094220288

tokenizer_config.json

@@ -227,6 +227,7 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",

trainer_state.json

@@ -11,1402 +11,1402 @@
   "log_history": [
     {
       "epoch": 0.0018066847335140017,
-      "grad_norm": 2.8330458831358536,
+      "grad_norm": 2.6597820350894357,
       "learning_rate": 0.0,
       "loss": 0.8251,
       "step": 1
     },
     {
       "epoch": 0.0036133694670280035,
-      "grad_norm": 2.881506507345633,
+      "grad_norm": 2.7266510344811494,
       "learning_rate": 1.0714285714285714e-06,
       "loss": 0.8284,
       "step": 2
     },
     {
       "epoch": 0.005420054200542005,
-      "grad_norm": 2.864957143736817,
+      "grad_norm": 2.7200407943823968,
       "learning_rate": 2.1428571428571427e-06,
-      "loss": 0.8427,
+      "loss": 0.8429,
       "step": 3
     },
     {
       "epoch": 0.007226738934056007,
-      "grad_norm": 2.789658157036283,
+      "grad_norm": 2.6398267415203076,
       "learning_rate": 3.2142857142857143e-06,
-      "loss": 0.8378,
+      "loss": 0.8381,
       "step": 4
     },
     {
       "epoch": 0.009033423667570008,
-      "grad_norm": 2.5748296264473147,
+      "grad_norm": 2.450058379558589,
       "learning_rate": 4.2857142857142855e-06,
-      "loss": 0.8226,
+      "loss": 0.8245,
       "step": 5
     },
     {
       "epoch": 0.01084010840108401,
-      "grad_norm": 2.1226324001162262,
+      "grad_norm": 1.9536840033460428,
       "learning_rate": 5.357142857142857e-06,
-      "loss": 0.8096,
+      "loss": 0.814,
       "step": 6
     },
     {
       "epoch": 0.012646793134598013,
-      "grad_norm": 1.4591614339485137,
+      "grad_norm": 1.2180340367347295,
       "learning_rate": 6.428571428571429e-06,
-      "loss": 0.7738,
+      "loss": 0.7845,
       "step": 7
     },
     {
       "epoch": 0.014453477868112014,
-      "grad_norm": 1.3910404074529026,
+      "grad_norm": 1.1514973199014618,
       "learning_rate": 7.5e-06,
-      "loss": 0.7731,
+      "loss": 0.7874,
       "step": 8
     },
     {
       "epoch": 0.016260162601626018,
-      "grad_norm": 1.2975941991178286,
+      "grad_norm": 1.1427251731602237,
       "learning_rate": 8.571428571428571e-06,
-      "loss": 0.7653,
+      "loss": 0.7793,
       "step": 9
     },
     {
       "epoch": 0.018066847335140017,
-      "grad_norm": 2.39949931335525,
+      "grad_norm": 2.4537001853666673,
       "learning_rate": 9.642857142857144e-06,
-      "loss": 0.7503,
+      "loss": 0.7624,
       "step": 10
     },
     {
       "epoch": 0.01987353206865402,
-      "grad_norm": 2.339166039208163,
+      "grad_norm": 2.474412722550665,
       "learning_rate": 1.0714285714285714e-05,
-      "loss": 0.7353,
+      "loss": 0.7491,
       "step": 11
     },
     {
       "epoch": 0.02168021680216802,
-      "grad_norm": 2.2235135720121253,
+      "grad_norm": 2.333456673377541,
       "learning_rate": 1.1785714285714286e-05,
-      "loss": 0.7488,
+      "loss": 0.762,
       "step": 12
     },
     {
       "epoch": 0.023486901535682024,
-      "grad_norm": 1.8641369164869521,
+      "grad_norm": 1.6274020508818596,
       "learning_rate": 1.2857142857142857e-05,
-      "loss": 0.7252,
+      "loss": 0.7368,
       "step": 13
     },
     {
       "epoch": 0.025293586269196026,
-      "grad_norm": 1.7375311366152815,
+      "grad_norm": 1.563869927563279,
       "learning_rate": 1.3928571428571429e-05,
-      "loss": 0.7282,
+      "loss": 0.7378,
       "step": 14
     },
     {
       "epoch": 0.02710027100271003,
-      "grad_norm": 1.4297603171733615,
+      "grad_norm": 1.253626680340628,
       "learning_rate": 1.5e-05,
-      "loss": 0.7175,
+      "loss": 0.7271,
       "step": 15
     },
     {
       "epoch": 0.028906955736224028,
-      "grad_norm": 1.1151402205703254,
+      "grad_norm": 0.9176330164857595,
       "learning_rate": 1.6071428571428572e-05,
-      "loss": 0.7016,
+      "loss": 0.7131,
       "step": 16
     },
     {
       "epoch": 0.03071364046973803,
-      "grad_norm": 0.8024202349277224,
+      "grad_norm": 0.7185343991261351,
       "learning_rate": 1.7142857142857142e-05,
-      "loss": 0.6998,
+      "loss": 0.7131,
       "step": 17
     },
     {
       "epoch": 0.032520325203252036,
-      "grad_norm": 0.7606508999595812,
+      "grad_norm": 0.7884609645105337,
       "learning_rate": 1.8214285714285712e-05,
-      "loss": 0.6884,
+      "loss": 0.7045,
       "step": 18
     },
     {
       "epoch": 0.03432700993676603,
-      "grad_norm": 0.7625534222641119,
+      "grad_norm": 0.7399830971167167,
       "learning_rate": 1.928571428571429e-05,
-      "loss": 0.6829,
+      "loss": 0.6995,
       "step": 19
     },
     {
       "epoch": 0.036133694670280034,
-      "grad_norm": 0.6694670087645954,
+      "grad_norm": 0.7376328500886337,
       "learning_rate": 2.0357142857142858e-05,
-      "loss": 0.6597,
+      "loss": 0.6779,
       "step": 20
     },
     {
       "epoch": 0.037940379403794036,
-      "grad_norm": 0.5962751724140051,
+      "grad_norm": 0.6439873145292982,
       "learning_rate": 2.1428571428571428e-05,
-      "loss": 0.6656,
+      "loss": 0.6834,
       "step": 21
     },
     {
       "epoch": 0.03974706413730804,
-      "grad_norm": 0.574939617107255,
+      "grad_norm": 0.5790542088592184,
       "learning_rate": 2.25e-05,
-      "loss": 0.6544,
+      "loss": 0.6721,
       "step": 22
     },
     {
       "epoch": 0.04155374887082204,
-      "grad_norm": 0.5740495615931904,
+      "grad_norm": 0.5191304250088061,
       "learning_rate": 2.357142857142857e-05,
-      "loss": 0.655,
+      "loss": 0.6707,
       "step": 23
     },
     {
       "epoch": 0.04336043360433604,
-      "grad_norm": 0.5401386924725768,
+      "grad_norm": 0.4488946670945292,
       "learning_rate": 2.464285714285714e-05,
-      "loss": 0.6603,
+      "loss": 0.676,
       "step": 24
     },
     {
       "epoch": 0.045167118337850046,
-      "grad_norm": 0.5411734137719719,
+      "grad_norm": 0.4798647764154148,
       "learning_rate": 2.5714285714285714e-05,
-      "loss": 0.6417,
+      "loss": 0.6585,
       "step": 25
     },
     {
       "epoch": 0.04697380307136405,
-      "grad_norm": 0.4707448281296468,
+      "grad_norm": 0.4204330566493729,
       "learning_rate": 2.6785714285714288e-05,
-      "loss": 0.6565,
+      "loss": 0.673,
       "step": 26
     },
     {
       "epoch": 0.04878048780487805,
-      "grad_norm": 0.4601634980551412,
+      "grad_norm": 0.47130112684574876,
       "learning_rate": 2.7857142857142858e-05,
-      "loss": 0.6344,
+      "loss": 0.6516,
       "step": 27
     },
     {
       "epoch": 0.05058717253839205,
-      "grad_norm": 0.4576924664211419,
+      "grad_norm": 0.4362815754533529,
       "learning_rate": 2.892857142857143e-05,
-      "loss": 0.637,
+      "loss": 0.6545,
       "step": 28
     },
     {
       "epoch": 0.052393857271906055,
-      "grad_norm": 0.44420515620753975,
+      "grad_norm": 0.43822648560890193,
       "learning_rate": 3e-05,
-      "loss": 0.6484,
+      "loss": 0.6647,
       "step": 29
     },
     {
       "epoch": 0.05420054200542006,
-      "grad_norm": 0.41258566428029175,
+      "grad_norm": 0.3853311574389301,
       "learning_rate": 2.9999731440137413e-05,
-      "loss": 0.6488,
+      "loss": 0.6644,
       "step": 30
     },
     {
       "epoch": 0.05600722673893405,
-      "grad_norm": 0.3492774187256118,
+      "grad_norm": 0.4221785516753897,
       "learning_rate": 2.9998925770166232e-05,
-      "loss": 0.6377,
+      "loss": 0.6534,
       "step": 31
     },
     {
       "epoch": 0.057813911472448055,
-      "grad_norm": 0.38161813042837406,
+      "grad_norm": 0.3980570059327311,
       "learning_rate": 2.9997583018935875e-05,
-      "loss": 0.6262,
+      "loss": 0.6416,
       "step": 32
     },
     {
       "epoch": 0.05962059620596206,
-      "grad_norm": 0.3667873345432628,
+      "grad_norm": 0.35571676272289743,
       "learning_rate": 2.9995703234527553e-05,
-      "loss": 0.6358,
+      "loss": 0.6513,
       "step": 33
     },
     {
       "epoch": 0.06142728093947606,
-      "grad_norm": 0.3431907596759456,
+      "grad_norm": 0.38024957472516396,
       "learning_rate": 2.999328648425255e-05,
-      "loss": 0.6233,
+      "loss": 0.6385,
       "step": 34
     },
     {
       "epoch": 0.06323396567299007,
-      "grad_norm": 0.36189091112235033,
+      "grad_norm": 0.2924858728569485,
       "learning_rate": 2.999033285464982e-05,
-      "loss": 0.6288,
+      "loss": 0.644,
       "step": 35
     },
     {
       "epoch": 0.06504065040650407,
-      "grad_norm": 0.3804643814225747,
+      "grad_norm": 0.3482798299572746,
       "learning_rate": 2.9986842451482876e-05,
-      "loss": 0.6248,
+      "loss": 0.6387,
       "step": 36
     },
     {
       "epoch": 0.06684733514001806,
-      "grad_norm": 0.35830891965133377,
+      "grad_norm": 0.3705337140725527,
       "learning_rate": 2.9982815399736008e-05,
-      "loss": 0.6297,
+      "loss": 0.6432,
       "step": 37
     },
     {
       "epoch": 0.06865401987353206,
-      "grad_norm": 0.349837532228719,
+      "grad_norm": 0.3364721163164359,
       "learning_rate": 2.9978251843609816e-05,
-      "loss": 0.6219,
+      "loss": 0.6351,
       "step": 38
     },
     {
       "epoch": 0.07046070460704607,
-      "grad_norm": 0.40406566853435366,
+      "grad_norm": 0.3272631660096153,
       "learning_rate": 2.9973151946516027e-05,
-      "loss": 0.6243,
+      "loss": 0.6364,
       "step": 39
     },
     {
       "epoch": 0.07226738934056007,
-      "grad_norm": 0.30908023037541016,
+      "grad_norm": 0.29708127282462954,
       "learning_rate": 2.996751589107167e-05,
-      "loss": 0.6123,
+      "loss": 0.6252,
       "step": 40
     },
     {
       "epoch": 0.07407407407407407,
-      "grad_norm": 0.3499175700089795,
+      "grad_norm": 0.24921077158970448,
       "learning_rate": 2.9961343879092512e-05,
-      "loss": 0.6186,
+      "loss": 0.6308,
       "step": 41
     },
     {
       "epoch": 0.07588075880758807,
-      "grad_norm": 0.29453754657609377,
+      "grad_norm": 0.3479569257927118,
       "learning_rate": 2.9954636131585845e-05,
-      "loss": 0.6117,
+      "loss": 0.6234,
       "step": 42
     },
     {
       "epoch": 0.07768744354110207,
-      "grad_norm": 0.31600841861885537,
+      "grad_norm": 0.28917511643628596,
       "learning_rate": 2.9947392888742566e-05,
-      "loss": 0.6117,
+      "loss": 0.6233,
       "step": 43
     },
     {
       "epoch": 0.07949412827461608,
-      "grad_norm": 0.3022084890043788,
+      "grad_norm": 0.34737822266968965,
       "learning_rate": 2.993961440992859e-05,
-      "loss": 0.6056,
+      "loss": 0.6171,
       "step": 44
     },
     {
       "epoch": 0.08130081300813008,
-      "grad_norm": 0.3192692448247662,
+      "grad_norm": 0.3247689228102166,
       "learning_rate": 2.993130097367553e-05,
-      "loss": 0.613,
+      "loss": 0.6238,
       "step": 45
     },
     {
       "epoch": 0.08310749774164408,
-      "grad_norm": 0.2995609365814746,
+      "grad_norm": 0.30719902123424325,
       "learning_rate": 2.9922452877670775e-05,
-      "loss": 0.6145,
+      "loss": 0.6252,
       "step": 46
     },
     {
       "epoch": 0.08491418247515808,
-      "grad_norm": 0.28359568489888487,
+      "grad_norm": 0.3175141153740525,
       "learning_rate": 2.991307043874677e-05,
-      "loss": 0.6171,
+      "loss": 0.6281,
       "step": 47
     },
     {
       "epoch": 0.08672086720867209,
-      "grad_norm": 0.2763705613050705,
+      "grad_norm": 0.31244488771705314,
       "learning_rate": 2.9903153992869734e-05,
-      "loss": 0.6031,
+      "loss": 0.6148,
       "step": 48
     },
     {
       "epoch": 0.08852755194218609,
-      "grad_norm": 0.3024771650885143,
+      "grad_norm": 0.3429131319420423,
       "learning_rate": 2.989270389512756e-05,
-      "loss": 0.6108,
+      "loss": 0.6211,
       "step": 49
     },
     {
       "epoch": 0.09033423667570009,
-      "grad_norm": 0.2961191333250206,
+      "grad_norm": 0.3104062918234721,
       "learning_rate": 2.988172051971717e-05,
-      "loss": 0.61,
+      "loss": 0.6204,
       "step": 50
     },
     {
       "epoch": 0.0921409214092141,
-      "grad_norm": 0.2832954078297925,
+      "grad_norm": 0.31461103786584654,
       "learning_rate": 2.9870204259931062e-05,
-      "loss": 0.5999,
+      "loss": 0.6097,
       "step": 51
     },
     {
       "epoch": 0.0939476061427281,
-      "grad_norm": 0.28528145590927906,
+      "grad_norm": 0.3151625720082357,
       "learning_rate": 2.9858155528143256e-05,
-      "loss": 0.617,
+      "loss": 0.6268,
       "step": 52
     },
     {
       "epoch": 0.0957542908762421,
-      "grad_norm": 0.31958273903448986,
+      "grad_norm": 0.2860126481493585,
       "learning_rate": 2.9845574755794522e-05,
-      "loss": 0.6027,
+      "loss": 0.6125,
       "step": 53
     },
     {
       "epoch": 0.0975609756097561,
-      "grad_norm": 0.2721806575699711,
+      "grad_norm": 0.28841121592431124,
       "learning_rate": 2.9832462393376926e-05,
-      "loss": 0.5922,
+      "loss": 0.6018,
       "step": 54
     },
     {
       "epoch": 0.0993676603432701,
-      "grad_norm": 0.345845783610871,
+      "grad_norm": 0.23534181927847642,
       "learning_rate": 2.9818818910417706e-05,
-      "loss": 0.6081,
+      "loss": 0.6169,
       "step": 55
     },
     {
       "epoch": 0.1011743450767841,
-      "grad_norm": 0.29580862920928147,
+      "grad_norm": 0.28661471046317555,
       "learning_rate": 2.9804644795462437e-05,
-      "loss": 0.6121,
+      "loss": 0.6212,
       "step": 56
     },
     {
       "epoch": 0.10298102981029811,
-      "grad_norm": 0.3175507142787931,
+      "grad_norm": 0.2443857675436309,
       "learning_rate": 2.9789940556057574e-05,
-      "loss": 0.5976,
+      "loss": 0.6065,
       "step": 57
     },
     {
       "epoch": 0.10478771454381211,
-      "grad_norm": 0.3374272189572956,
+      "grad_norm": 0.292418070185767,
       "learning_rate": 2.9774706718732255e-05,
-      "loss": 0.6061,
+      "loss": 0.6152,
       "step": 58
     },
     {
       "epoch": 0.10659439927732611,
-      "grad_norm": 0.27546053233166856,
+      "grad_norm": 0.24742182455944323,
       "learning_rate": 2.9758943828979444e-05,
-      "loss": 0.5922,
+      "loss": 0.6009,
       "step": 59
     },
     {
       "epoch": 0.10840108401084012,
-      "grad_norm": 0.3657689574287652,
+      "grad_norm": 0.25007211477600044,
       "learning_rate": 2.9742652451236414e-05,
-      "loss": 0.5934,
+      "loss": 0.6023,
       "step": 60
     },
     {
       "epoch": 0.1102077687443541,
-      "grad_norm": 0.2986956716963071,
+      "grad_norm": 0.24539117288225054,
       "learning_rate": 2.972583316886451e-05,
-      "loss": 0.5971,
+      "loss": 0.6059,
       "step": 61
     },
     {
       "epoch": 0.1120144534778681,
-      "grad_norm": 0.3448276185716925,
+      "grad_norm": 0.2544907417129908,
       "learning_rate": 2.9708486584128303e-05,
-      "loss": 0.6017,
+      "loss": 0.6107,
       "step": 62
     },
     {
       "epoch": 0.11382113821138211,
-      "grad_norm": 0.3163562156051723,
+      "grad_norm": 0.25269030392560393,
       "learning_rate": 2.9690613318173966e-05,
-      "loss": 0.6018,
+      "loss": 0.611,
       "step": 63
     },
     {
       "epoch": 0.11562782294489611,
-      "grad_norm": 0.2891799826775374,
+      "grad_norm": 0.20651691272156247,
       "learning_rate": 2.9672214011007087e-05,
-      "loss": 0.6001,
+      "loss": 0.6091,
       "step": 64
     },
     {
       "epoch": 0.11743450767841011,
-      "grad_norm": 0.3052917388689653,
+      "grad_norm": 0.25759031036445135,
       "learning_rate": 2.9653289321469715e-05,
-      "loss": 0.5941,
+      "loss": 0.6031,
       "step": 65
     },
     {
       "epoch": 0.11924119241192412,
-      "grad_norm": 0.27037779234686826,
+      "grad_norm": 0.27004948462624506,
       "learning_rate": 2.9633839927216793e-05,
-      "loss": 0.5971,
+      "loss": 0.6061,
       "step": 66
     },
     {
       "epoch": 0.12104787714543812,
-      "grad_norm": 0.2837154841373324,
+      "grad_norm": 0.23899477664304233,
       "learning_rate": 2.9613866524691867e-05,
-      "loss": 0.5873,
+      "loss": 0.5958,
       "step": 67
     },
     {
       "epoch": 0.12285456187895212,
-      "grad_norm": 0.29318973292150885,
+      "grad_norm": 0.3109356502387666,
       "learning_rate": 2.9593369829102173e-05,
-      "loss": 0.6033,
+      "loss": 0.6119,
       "step": 68
     },
     {
       "epoch": 0.12466124661246612,
-      "grad_norm": 0.27320922800225206,
+      "grad_norm": 0.23973937288759506,
       "learning_rate": 2.957235057439301e-05,
-      "loss": 0.6043,
+      "loss": 0.6135,
       "step": 69
     },
     {
       "epoch": 0.12646793134598014,
-      "grad_norm": 0.2888792462126571,
+      "grad_norm": 0.29402451520285133,
       "learning_rate": 2.955080951322147e-05,
-      "loss": 0.609,
+      "loss": 0.6178,
       "step": 70
     },
     {
       "epoch": 0.12827461607949414,
-      "grad_norm": 0.3010426601423717,
+      "grad_norm": 0.29085498534508775,
       "learning_rate": 2.9528747416929467e-05,
-      "loss": 0.5817,
+      "loss": 0.5907,
       "step": 71
     },
     {
       "epoch": 0.13008130081300814,
-      "grad_norm": 0.29363653670708806,
+      "grad_norm": 0.25477514255751904,
       "learning_rate": 2.9506165075516148e-05,
-      "loss": 0.599,
+      "loss": 0.6073,
       "step": 72
     },
     {
       "epoch": 0.13188798554652212,
-      "grad_norm": 0.3695495205161594,
+      "grad_norm": 0.28366229733780235,
       "learning_rate": 2.9483063297609577e-05,
-      "loss": 0.5979,
+      "loss": 0.6063,
       "step": 73
     },
     {
       "epoch": 0.13369467028003612,
-      "grad_norm": 0.312283280850037,
+      "grad_norm": 0.26317649422081363,
       "learning_rate": 2.9459442910437798e-05,
-      "loss": 0.5894,
+      "loss": 0.598,
       "step": 74
     },
     {
       "epoch": 0.13550135501355012,
-      "grad_norm": 0.34410257132188554,
+      "grad_norm": 0.28039599919104496,
       "learning_rate": 2.94353047597992e-05,
-      "loss": 0.5887,
+      "loss": 0.5971,
       "step": 75
     },
     {
       "epoch": 0.13730803974706413,
-      "grad_norm": 0.2913822090159289,
+      "grad_norm": 0.271745198157929,
       "learning_rate": 2.941064971003224e-05,
-      "loss": 0.5844,
+      "loss": 0.593,
       "step": 76
     },
     {
       "epoch": 0.13911472448057813,
-      "grad_norm": 0.34659905630109983,
+      "grad_norm": 0.24998502389958926,
       "learning_rate": 2.9385478643984484e-05,
-      "loss": 0.5796,
+      "loss": 0.5878,
       "step": 77
     },
     {
       "epoch": 0.14092140921409213,
-      "grad_norm": 0.3690502006189352,
+      "grad_norm": 0.30322559816019845,
       "learning_rate": 2.9359792462981007e-05,
-      "loss": 0.591,
+      "loss": 0.599,
       "step": 78
     },
     {
       "epoch": 0.14272809394760613,
-      "grad_norm": 0.3032664893630925,
+      "grad_norm": 0.29351194680487536,
       "learning_rate": 2.9333592086792113e-05,
-      "loss": 0.5986,
+      "loss": 0.6075,
       "step": 79
     },
     {
       "epoch": 0.14453477868112014,
-      "grad_norm": 0.34886668595229536,
+      "grad_norm": 0.2670107767188747,
       "learning_rate": 2.9306878453600382e-05,
-      "loss": 0.6077,
+      "loss": 0.6161,
       "step": 80
     },
     {
       "epoch": 0.14634146341463414,
-      "grad_norm": 0.3308668167904688,
+      "grad_norm": 0.2927366904918854,
       "learning_rate": 2.9279652519967105e-05,
-      "loss": 0.5927,
+      "loss": 0.6004,
       "step": 81
     },
     {
       "epoch": 0.14814814814814814,
-      "grad_norm": 0.34561229364377843,
+      "grad_norm": 0.28777141201555767,
       "learning_rate": 2.9251915260798024e-05,
-      "loss": 0.585,
+      "loss": 0.593,
       "step": 82
     },
     {
       "epoch": 0.14995483288166214,
-      "grad_norm": 0.3315517031152509,
+      "grad_norm": 0.282262421377073,
       "learning_rate": 2.9223667669308395e-05,
-      "loss": 0.5951,
+      "loss": 0.6038,
       "step": 83
     },
     {
       "epoch": 0.15176151761517614,
-      "grad_norm": 0.26853290095208654,
+      "grad_norm": 0.24811154699761442,
       "learning_rate": 2.9194910756987464e-05,
-      "loss": 0.5885,
+      "loss": 0.5976,
       "step": 84
     },
     {
       "epoch": 0.15356820234869015,
-      "grad_norm": 0.29448765107140906,
+      "grad_norm": 0.27670190484589513,
       "learning_rate": 2.9165645553562215e-05,
-      "loss": 0.5914,
+      "loss": 0.5997,
       "step": 85
     },
     {
       "epoch": 0.15537488708220415,
-      "grad_norm": 0.2806586567612587,
+      "grad_norm": 0.24338487756299684,
       "learning_rate": 2.9135873106960525e-05,
-      "loss": 0.5905,
+      "loss": 0.5994,
       "step": 86
     },
     {
       "epoch": 0.15718157181571815,
-      "grad_norm": 0.3083804198003563,
+      "grad_norm": 0.3040191021283788,
       "learning_rate": 2.9105594483273603e-05,
-      "loss": 0.5933,
+      "loss": 0.6012,
       "step": 87
     },
     {
       "epoch": 0.15898825654923215,
-      "grad_norm": 0.29100169406971965,
+      "grad_norm": 0.26703924304748566,
       "learning_rate": 2.9074810766717865e-05,
-      "loss": 0.5971,
+      "loss": 0.6058,
       "step": 88
     },
     {
       "epoch": 0.16079494128274616,
-      "grad_norm": 0.3123482151135741,
+      "grad_norm": 0.2694312104706441,
       "learning_rate": 2.904352305959606e-05,
-      "loss": 0.594,
+      "loss": 0.602,
       "step": 89
     },
     {
       "epoch": 0.16260162601626016,
-      "grad_norm": 0.29086528776110065,
+      "grad_norm": 0.29517928394037635,
       "learning_rate": 2.9011732482257835e-05,
-      "loss": 0.5858,
+      "loss": 0.5944,
       "step": 90
     },
     {
       "epoch": 0.16440831074977416,
-      "grad_norm": 0.32777518300425235,
+      "grad_norm": 0.25118801401605734,
       "learning_rate": 2.89794401730596e-05,
-      "loss": 0.5838,
+      "loss": 0.5923,
       "step": 91
     },
     {
       "epoch": 0.16621499548328816,
-      "grad_norm": 0.31282829577117277,
+      "grad_norm": 0.3348680034328015,
       "learning_rate": 2.894664728832377e-05,
-      "loss": 0.5878,
+      "loss": 0.5958,
       "step": 92
     },
     {
       "epoch": 0.16802168021680217,
-      "grad_norm": 0.30591224241436143,
+      "grad_norm": 0.25945936645525364,
       "learning_rate": 2.8913355002297367e-05,
-      "loss": 0.5943,
+      "loss": 0.6025,
       "step": 93
     },
     {
       "epoch": 0.16982836495031617,
-      "grad_norm": 0.3454363395865153,
+      "grad_norm": 0.31672412557275315,
       "learning_rate": 2.887956450710995e-05,
-      "loss": 0.5939,
+      "loss": 0.602,
       "step": 94
     },
     {
       "epoch": 0.17163504968383017,
-      "grad_norm": 0.3119824836679083,
+      "grad_norm": 0.2631935513788724,
       "learning_rate": 2.8845277012730963e-05,
-      "loss": 0.5859,
+      "loss": 0.5939,
       "step": 95
     },
     {
       "epoch": 0.17344173441734417,
-      "grad_norm": 0.29451741781860913,
+      "grad_norm": 0.28309967073656406,
       "learning_rate": 2.8810493746926364e-05,
-      "loss": 0.5853,
+      "loss": 0.5932,
       "step": 96
     },
     {
       "epoch": 0.17524841915085818,
-      "grad_norm": 0.3034863549374876,
+      "grad_norm": 0.28939178950900774,
       "learning_rate": 2.87752159552147e-05,
-      "loss": 0.591,
+      "loss": 0.5993,
       "step": 97
     },
     {
       "epoch": 0.17705510388437218,
-      "grad_norm": 0.28746917797897076,
+      "grad_norm": 0.3021445789644071,
       "learning_rate": 2.87394449008225e-05,
-      "loss": 0.5841,
+      "loss": 0.5924,
       "step": 98
     },
     {
       "epoch": 0.17886178861788618,
-      "grad_norm": 0.30996182677103346,
+      "grad_norm": 0.2648161341085879,
       "learning_rate": 2.8703181864639013e-05,
-      "loss": 0.5969,
+      "loss": 0.6058,
       "step": 99
     },
     {
       "epoch": 0.18066847335140018,
-      "grad_norm": 0.29091619146077263,
+      "grad_norm": 0.28484263640616314,
       "learning_rate": 2.8666428145170385e-05,
-      "loss": 0.5702,
+      "loss": 0.5789,
       "step": 100
     },
     {
       "epoch": 0.18247515808491419,
-      "grad_norm": 0.2868056287309143,
+      "grad_norm": 0.2611846886724786,
       "learning_rate": 2.8629185058493116e-05,
-      "loss": 0.5862,
+      "loss": 0.5949,
       "step": 101
     },
     {
       "epoch": 0.1842818428184282,
-      "grad_norm": 0.3505705678502723,
+      "grad_norm": 0.33149916071305763,
       "learning_rate": 2.8591453938206985e-05,
-      "loss": 0.6047,
+      "loss": 0.6134,
       "step": 102
     },
     {
       "epoch": 0.1860885275519422,
-      "grad_norm": 0.27071275031049963,
+      "grad_norm": 0.28402400837841096,
       "learning_rate": 2.8553236135387247e-05,
-      "loss": 0.5829,
+      "loss": 0.5914,
       "step": 103
     },
     {
       "epoch": 0.1878952122854562,
-      "grad_norm": 0.33734329421620535,
+      "grad_norm": 0.28825320782588004,
       "learning_rate": 2.8514533018536286e-05,
-      "loss": 0.5811,
+      "loss": 0.5897,
       "step": 104
     },
     {
       "epoch": 0.1897018970189702,
-      "grad_norm": 0.2770290286284249,
+      "grad_norm": 0.2901395812522203,
       "learning_rate": 2.8475345973534605e-05,
-      "loss": 0.5732,
+      "loss": 0.5822,
       "step": 105
     },
     {
       "epoch": 0.1915085817524842,
-      "grad_norm": 0.27942020628211717,
+      "grad_norm": 0.25034051990006584,
       "learning_rate": 2.8435676403591193e-05,
-      "loss": 0.576,
+      "loss": 0.5846,
       "step": 106
     },
     {
       "epoch": 0.1933152664859982,
-      "grad_norm": 0.28553078573573465,
+      "grad_norm": 0.27868357694305945,
       "learning_rate": 2.8395525729193284e-05,
-      "loss": 0.5827,
+      "loss": 0.5907,
       "step": 107
     },
     {
       "epoch": 0.1951219512195122,
-      "grad_norm": 0.25251226579381214,
+      "grad_norm": 0.257742952703987,
       "learning_rate": 2.835489538805548e-05,
-      "loss": 0.5802,
+      "loss": 0.5888,
       "step": 108
     },
     {
       "epoch": 0.1969286359530262,
-      "grad_norm": 0.27568353405316703,
+      "grad_norm": 0.26397326166674545,
       "learning_rate": 2.8313786835068314e-05,
-      "loss": 0.589,
+      "loss": 0.5976,
       "step": 109
     },
     {
       "epoch": 0.1987353206865402,
-      "grad_norm": 0.27356824941424274,
+      "grad_norm": 0.2721484510112116,
       "learning_rate": 2.8272201542246077e-05,
-      "loss": 0.5708,
+      "loss": 0.5792,
       "step": 110
     },
     {
       "epoch": 0.2005420054200542,
-      "grad_norm": 0.2930130437286294,
+      "grad_norm": 0.2374425057236497,
       "learning_rate": 2.8230140998674185e-05,
-      "loss": 0.5906,
+      "loss": 0.599,
       "step": 111
     },
     {
       "epoch": 0.2023486901535682,
-      "grad_norm": 0.27001628683011253,
+      "grad_norm": 0.24242218904343407,
       "learning_rate": 2.8187606710455807e-05,
-      "loss": 0.584,
+      "loss": 0.5921,
       "step": 112
     },
     {
       "epoch": 0.2041553748870822,
-      "grad_norm": 0.30271557970745333,
+      "grad_norm": 0.2742052397132371,
       "learning_rate": 2.8144600200657953e-05,
-      "loss": 0.5881,
+      "loss": 0.5965,
       "step": 113
     },
     {
       "epoch": 0.20596205962059622,
-      "grad_norm": 0.3099699158916623,
+      "grad_norm": 0.2240931438132582,
       "learning_rate": 2.8101123009256946e-05,
-      "loss": 0.5711,
+      "loss": 0.5792,
       "step": 114
     },
     {
       "epoch": 0.20776874435411022,
-      "grad_norm": 0.26752391302167267,
+      "grad_norm": 0.2763456467888191,
       "learning_rate": 2.8057176693083253e-05,
-      "loss": 0.5871,
+      "loss": 0.5958,
       "step": 115
     },
     {
       "epoch": 0.20957542908762422,
-      "grad_norm": 0.30529403725575444,
+      "grad_norm": 0.2435434093260049,
       "learning_rate": 2.8012762825765763e-05,
-      "loss": 0.5808,
+      "loss": 0.5891,
       "step": 116
     },
     {
       "epoch": 0.21138211382113822,
-      "grad_norm": 0.30990442497802834,
+      "grad_norm": 0.2769370185736096,
       "learning_rate": 2.7967882997675424e-05,
-      "loss": 0.5921,
+      "loss": 0.6012,
       "step": 117
     },
     {
       "epoch": 0.21318879855465223,
-      "grad_norm": 0.29406959285002965,
+      "grad_norm": 0.2556991024086139,
       "learning_rate": 2.7922538815868287e-05,
-      "loss": 0.5792,
+      "loss": 0.5879,
       "step": 118
     },
     {
       "epoch": 0.21499548328816623,
-      "grad_norm": 0.26020193379576106,
+      "grad_norm": 0.2913165244476914,
       "learning_rate": 2.7876731904027994e-05,
-      "loss": 0.5695,
+      "loss": 0.5784,
       "step": 119
     },
     {
       "epoch": 0.21680216802168023,
-      "grad_norm": 0.3062499009336232,
+      "grad_norm": 0.29037318268167045,
       "learning_rate": 2.78304639024076e-05,
-      "loss": 0.5885,
+      "loss": 0.5968,
       "step": 120
     },
     {
       "epoch": 0.2186088527551942,
-      "grad_norm": 0.26339824339450146,
+      "grad_norm": 0.24340049924612678,
       "learning_rate": 2.7783736467770863e-05,
-      "loss": 0.5839,
+      "loss": 0.5927,
       "step": 121
     },
     {
       "epoch": 0.2204155374887082,
-      "grad_norm": 0.2997530840298656,
+      "grad_norm": 0.29825692316659325,
       "learning_rate": 2.7736551273332908e-05,
-      "loss": 0.589,
+      "loss": 0.5972,
       "step": 122
     },
     {
       "epoch": 0.2222222222222222,
-      "grad_norm": 0.30497954819719497,
+      "grad_norm": 0.2593832259683122,
       "learning_rate": 2.7688910008700305e-05,
-      "loss": 0.5787,
+      "loss": 0.5876,
       "step": 123
     },
     {
       "epoch": 0.2240289069557362,
-      "grad_norm": 0.25400958693406966,
+      "grad_norm": 0.27547771011759425,
       "learning_rate": 2.764081437981059e-05,
-      "loss": 0.5651,
+      "loss": 0.5742,
       "step": 124
     },
     {
       "epoch": 0.22583559168925021,
-      "grad_norm": 0.27337312352788334,
+      "grad_norm": 0.27158658907185634,
       "learning_rate": 2.7592266108871158e-05,
-      "loss": 0.5721,
+      "loss": 0.5812,
       "step": 125
     },
     {
       "epoch": 0.22764227642276422,
-      "grad_norm": 0.3015648108540393,
+      "grad_norm": 0.2715497634460973,
       "learning_rate": 2.754326693429761e-05,
-      "loss": 0.5846,
+      "loss": 0.5931,
       "step": 126
     },
     {
       "epoch": 0.22944896115627822,
-      "grad_norm": 0.3066830899471946,
+      "grad_norm": 0.24142985625388147,
       "learning_rate": 2.7493818610651493e-05,
-      "loss": 0.5773,
+      "loss": 0.5859,
       "step": 127
     },
     {
       "epoch": 0.23125564588979222,
-      "grad_norm": 0.2557038265672841,
+      "grad_norm": 0.2530474955317245,
       "learning_rate": 2.744392290857747e-05,
-      "loss": 0.5766,
+      "loss": 0.5857,
       "step": 128
     },
     {
       "epoch": 0.23306233062330622,
-      "grad_norm": 0.28287498283890955,
+      "grad_norm": 0.2567731311347638,
       "learning_rate": 2.7393581614739924e-05,
-      "loss": 0.572,
+      "loss": 0.5803,
       "step": 129
     },
     {
       "epoch": 0.23486901535682023,
-      "grad_norm": 0.2760546012980017,
+      "grad_norm": 0.2628073110459229,
       "learning_rate": 2.7342796531758984e-05,
-      "loss": 0.5902,
+      "loss": 0.5987,
       "step": 130
     },
     {
       "epoch": 0.23667570009033423,
-      "grad_norm": 0.29650720341579806,
+      "grad_norm": 0.23510376935644756,
       "learning_rate": 2.729156947814598e-05,
-      "loss": 0.5849,
+      "loss": 0.5926,
       "step": 131
     },
     {
       "epoch": 0.23848238482384823,
-      "grad_norm": 0.2648334919033985,
+      "grad_norm": 0.23576954058784624,
       "learning_rate": 2.7239902288238297e-05,
-      "loss": 0.5635,
+      "loss": 0.5721,
       "step": 132
     },
     {
       "epoch": 0.24028906955736223,
-      "grad_norm": 0.2684479411326874,
+      "grad_norm": 0.24964231366212492,
       "learning_rate": 2.7187796812133733e-05,
-      "loss": 0.5789,
+      "loss": 0.5873,
       "step": 133
     },
     {
       "epoch": 0.24209575429087624,
-      "grad_norm": 0.2903853719359672,
+      "grad_norm": 0.23911643013915115,
       "learning_rate": 2.7135254915624213e-05,
-      "loss": 0.5795,
+      "loss": 0.5878,
       "step": 134
     },
     {
       "epoch": 0.24390243902439024,
-      "grad_norm": 0.2988296028667376,
+      "grad_norm": 0.23601189225311667,
       "learning_rate": 2.708227848012901e-05,
-      "loss": 0.5771,
+      "loss": 0.585,
       "step": 135
     },
     {
       "epoch": 0.24570912375790424,
-      "grad_norm": 0.278887060643492,
+      "grad_norm": 0.28061149806949875,
       "learning_rate": 2.7028869402627357e-05,
-      "loss": 0.5805,
+      "loss": 0.5889,
       "step": 136
     },
     {
       "epoch": 0.24751580849141824,
-      "grad_norm": 0.3079715134179689,
+      "grad_norm": 0.2537605160128264,
       "learning_rate": 2.6975029595590523e-05,
-      "loss": 0.5643,
+      "loss": 0.5726,
       "step": 137
     },
     {
       "epoch": 0.24932249322493225,
-      "grad_norm": 0.2797620060845942,
+      "grad_norm": 0.2631279788827005,
       "learning_rate": 2.6920760986913332e-05,
-      "loss": 0.5813,
+      "loss": 0.5901,
       "step": 138
     },
     {
       "epoch": 0.25112917795844625,
-      "grad_norm": 0.28689667632739463,
+      "grad_norm": 0.24684546421512338,
       "learning_rate": 2.6866065519845124e-05,
-      "loss": 0.5841,
+      "loss": 0.5932,
       "step": 139
     },
     {
       "epoch": 0.2529358626919603,
-      "grad_norm": 0.2648041926457305,
+      "grad_norm": 0.25108587954115535,
       "learning_rate": 2.681094515292018e-05,
-      "loss": 0.5837,
+      "loss": 0.5927,
       "step": 140
     },
     {
       "epoch": 0.25474254742547425,
-      "grad_norm": 0.25173007019005905,
+      "grad_norm": 0.2759732073497199,
       "learning_rate": 2.6755401859887598e-05,
-      "loss": 0.5647,
+      "loss": 0.573,
       "step": 141
     },
     {
       "epoch": 0.2565492321589883,
-      "grad_norm": 0.31032191815468113,
+      "grad_norm": 0.2927986426856055,
       "learning_rate": 2.6699437629640595e-05,
-      "loss": 0.5843,
+      "loss": 0.5934,
       "step": 142
     },
     {
       "epoch": 0.25835591689250226,
-      "grad_norm": 0.2888788250337772,
+      "grad_norm": 0.2915811926744858,
       "learning_rate": 2.6643054466145297e-05,
-      "loss": 0.5761,
+      "loss": 0.5846,
       "step": 143
     },
     {
       "epoch": 0.2601626016260163,
-      "grad_norm": 0.2760034707559814,
+      "grad_norm": 0.25639674407942853,
       "learning_rate": 2.6586254388368995e-05,
-      "loss": 0.5647,
+      "loss": 0.5733,
       "step": 144
     },
     {
       "epoch": 0.26196928635953026,
-      "grad_norm": 0.32528080890474936,
+      "grad_norm": 0.25466281147535325,
       "learning_rate": 2.652903943020783e-05,
-      "loss": 0.5772,
+      "loss": 0.5862,
       "step": 145
     },
     {
       "epoch": 0.26377597109304424,
-      "grad_norm": 0.2637573911390966,
+      "grad_norm": 0.24151461009286013,
       "learning_rate": 2.647141164041398e-05,
-      "loss": 0.5821,
+      "loss": 0.5904,
       "step": 146
     },
     {
       "epoch": 0.26558265582655827,
-      "grad_norm": 0.2761207440107144,
+      "grad_norm": 0.259822033974557,
       "learning_rate": 2.641337308252228e-05,
-      "loss": 0.5718,
+      "loss": 0.581,
       "step": 147
     },
     {
       "epoch": 0.26738934056007224,
-      "grad_norm": 0.2974380721456416,
+      "grad_norm": 0.24532475377494284,
       "learning_rate": 2.6354925834776346e-05,
-      "loss": 0.5733,
+      "loss": 0.5817,
       "step": 148
     },
     {
       "epoch": 0.26919602529358627,
-      "grad_norm": 0.2875371174946777,
+      "grad_norm": 0.2555788655192275,
       "learning_rate": 2.6296071990054167e-05,
-      "loss": 0.5703,
+      "loss": 0.579,
       "step": 149
     },
     {
       "epoch": 0.27100271002710025,
-      "grad_norm": 0.26400215153050155,
+      "grad_norm": 0.2534339164884998,
       "learning_rate": 2.6236813655793123e-05,
-      "loss": 0.5801,
+      "loss": 0.5886,
       "step": 150
     },
     {
       "epoch": 0.2728093947606143,
-      "grad_norm": 0.2740289239257524,
+      "grad_norm": 0.25366511050468843,
       "learning_rate": 2.617715295391457e-05,
-      "loss": 0.5621,
+      "loss": 0.5707,
       "step": 151
     },
     {
       "epoch": 0.27461607949412825,
-      "grad_norm": 0.26263956805016714,
+      "grad_norm": 0.26118391438335414,
       "learning_rate": 2.6117092020747824e-05,
-      "loss": 0.5697,
+      "loss": 0.5779,
       "step": 152
     },
     {
       "epoch": 0.2764227642276423,
-      "grad_norm": 0.27308995986851226,
+      "grad_norm": 0.31049055796662123,
       "learning_rate": 2.6056633006953677e-05,
-      "loss": 0.5697,
+      "loss": 0.5783,
       "step": 153
     },
     {
       "epoch": 0.27822944896115626,
-      "grad_norm": 0.2682634840950432,
+      "grad_norm": 0.2611788471953917,
       "learning_rate": 2.5995778077447393e-05,
-      "loss": 0.5735,
+      "loss": 0.5823,
       "step": 154
     },
     {
       "epoch": 0.2800361336946703,
-      "grad_norm": 0.30213654494482944,
+      "grad_norm": 0.3259190805002546,
       "learning_rate": 2.5934529411321174e-05,
-      "loss": 0.5668,
+      "loss": 0.5743,
       "step": 155
     },
     {
       "epoch": 0.28184281842818426,
-      "grad_norm": 0.24055343886463815,
+      "grad_norm": 0.2222204544644696,
       "learning_rate": 2.587288920176613e-05,
-      "loss": 0.5662,
+      "loss": 0.575,
       "step": 156
     },
     {
       "epoch": 0.2836495031616983,
-      "grad_norm": 0.2913187789114745,
+      "grad_norm": 0.29042132848143276,
       "learning_rate": 2.581085965599375e-05,
-      "loss": 0.5795,
+      "loss": 0.5877,
       "step": 157
     },
     {
       "epoch": 0.28545618789521227,
-      "grad_norm": 0.2576506841389344,
+      "grad_norm": 0.2577824036794116,
       "learning_rate": 2.5748442995156882e-05,
-      "loss": 0.5766,
+      "loss": 0.5854,
       "step": 158
     },
     {
       "epoch": 0.2872628726287263,
-      "grad_norm": 0.27596403754545956,
+      "grad_norm": 0.24041412490024394,
       "learning_rate": 2.5685641454270172e-05,
-      "loss": 0.5577,
+      "loss": 0.566,
       "step": 159
     },
     {
       "epoch": 0.28906955736224027,
-      "grad_norm": 0.2935051396800575,
+      "grad_norm": 0.33137613211077116,
       "learning_rate": 2.5622457282130046e-05,
-      "loss": 0.5668,
+      "loss": 0.5753,
       "step": 160
     },
     {
       "epoch": 0.2908762420957543,
-      "grad_norm": 0.261323419986792,
+      "grad_norm": 0.2252657452973701,
       "learning_rate": 2.5558892741234173e-05,
-      "loss": 0.5744,
+      "loss": 0.5827,
       "step": 161
     },
     {
       "epoch": 0.2926829268292683,
-      "grad_norm": 0.29994364267277224,
+      "grad_norm": 0.353225035311219,
       "learning_rate": 2.5494950107700482e-05,
-      "loss": 0.5606,
+      "loss": 0.5692,
       "step": 162
     },
     {
       "epoch": 0.2944896115627823,
-      "grad_norm": 0.25057252176689093,
+      "grad_norm": 0.2549710140850951,
       "learning_rate": 2.5430631671185616e-05,
-      "loss": 0.5689,
+      "loss": 0.5775,
       "step": 163
     },
     {
       "epoch": 0.2962962962962963,
-      "grad_norm": 0.30439652791987415,
+      "grad_norm": 0.320108207545845,
       "learning_rate": 2.5365939734802973e-05,
-      "loss": 0.5784,
+      "loss": 0.5871,
       "step": 164
     },
     {
       "epoch": 0.2981029810298103,
-      "grad_norm": 0.2561891058565834,
+      "grad_norm": 0.27118178617195304,
       "learning_rate": 2.5300876615040223e-05,
-      "loss": 0.5693,
+      "loss": 0.5777,
       "step": 165
     },
     {
       "epoch": 0.2999096657633243,
-      "grad_norm": 0.30789286843223074,
+      "grad_norm": 0.2732065296628375,
       "learning_rate": 2.523544464167637e-05,
-      "loss": 0.5755,
+      "loss": 0.5842,
       "step": 166
     },
     {
       "epoch": 0.3017163504968383,
-      "grad_norm": 0.2604413140600789,
+      "grad_norm": 0.2440418264084237,
       "learning_rate": 2.5169646157698313e-05,
-      "loss": 0.574,
+      "loss": 0.583,
       "step": 167
     },
     {
       "epoch": 0.3035230352303523,
-      "grad_norm": 0.2772614270807846,
+      "grad_norm": 0.2400624724182379,
       "learning_rate": 2.5103483519216964e-05,
-      "loss": 0.5731,
+      "loss": 0.5813,
       "step": 168
     },
     {
       "epoch": 0.3053297199638663,
-      "grad_norm": 0.26896696271290815,
+      "grad_norm": 0.25905283588713374,
       "learning_rate": 2.5036959095382875e-05,
-      "loss": 0.565,
+      "loss": 0.574,
       "step": 169
     },
     {
       "epoch": 0.3071364046973803,
-      "grad_norm": 0.29065186309501,
+      "grad_norm": 0.2591290671871167,
       "learning_rate": 2.4970075268301388e-05,
-      "loss": 0.5783,
+      "loss": 0.5877,
       "step": 170
     },
     {
       "epoch": 0.3089430894308943,
-      "grad_norm": 0.2466338266655888,
+      "grad_norm": 0.2235510897395504,
       "learning_rate": 2.4902834432947353e-05,
-      "loss": 0.5614,
+      "loss": 0.5706,
       "step": 171
     },
     {
       "epoch": 0.3107497741644083,
-      "grad_norm": 0.27214096978444124,
+      "grad_norm": 0.23760061910249497,
       "learning_rate": 2.4835238997079382e-05,
-      "loss": 0.5687,
+      "loss": 0.5771,
       "step": 172
     },
     {
       "epoch": 0.31255645889792233,
-      "grad_norm": 0.2651928040714497,
+      "grad_norm": 0.2617951363502666,
       "learning_rate": 2.4767291381153603e-05,
-      "loss": 0.5719,
+      "loss": 0.5807,
       "step": 173
     },
     {
       "epoch": 0.3143631436314363,
-      "grad_norm": 0.23672196782852778,
+      "grad_norm": 0.23091611449448254,
       "learning_rate": 2.4698994018236994e-05,
-      "loss": 0.5631,
+      "loss": 0.5721,
       "step": 174
     },
     {
       "epoch": 0.31616982836495033,
-      "grad_norm": 0.28356502585206267,
+      "grad_norm": 0.25262572503013164,
       "learning_rate": 2.4630349353920284e-05,
-      "loss": 0.5671,
+      "loss": 0.5767,
       "step": 175
     },
     {
       "epoch": 0.3179765130984643,
-      "grad_norm": 0.28540875579685554,
+      "grad_norm": 0.23055115622552902,
       "learning_rate": 2.4561359846230346e-05,
-      "loss": 0.5818,
+      "loss": 0.5906,
       "step": 176
     },
     {
       "epoch": 0.31978319783197834,
-      "grad_norm": 0.24190126114290808,
+      "grad_norm": 0.21968694104114944,
       "learning_rate": 2.4492027965542217e-05,
-      "loss": 0.5569,
+      "loss": 0.5657,
       "step": 177
     },
     {
       "epoch": 0.3215898825654923,
-      "grad_norm": 0.27287155700655424,
+      "grad_norm": 0.2525014182918365,
       "learning_rate": 2.44223561944906e-05,
-      "loss": 0.5643,
+      "loss": 0.5724,
       "step": 178
     },
     {
       "epoch": 0.32339656729900634,
-      "grad_norm": 0.24924695151585574,
+      "grad_norm": 0.2407328065060556,
       "learning_rate": 2.4352347027881003e-05,
-      "loss": 0.5738,
+      "loss": 0.5825,
       "step": 179
     },
     {
       "epoch": 0.3252032520325203,
-      "grad_norm": 0.2759090650898249,
+      "grad_norm": 0.2547387307288275,
       "learning_rate": 2.4282002972600382e-05,
-      "loss": 0.5817,
+      "loss": 0.5908,
       "step": 180
     },
     {
       "epoch": 0.32700993676603435,
-      "grad_norm": 0.22785083526499783,
+      "grad_norm": 0.2263495601766316,
       "learning_rate": 2.4211326547527377e-05,
-      "loss": 0.5601,
+      "loss": 0.5688,
       "step": 181
     },
     {
       "epoch": 0.3288166214995483,
-      "grad_norm": 0.2691907674221595,
+      "grad_norm": 0.2789402543570071,
       "learning_rate": 2.4140320283442125e-05,
-      "loss": 0.5699,
+      "loss": 0.579,
       "step": 182
     },
     {
       "epoch": 0.33062330623306235,
-      "grad_norm": 0.2708392714868768,
+      "grad_norm": 0.2567309540458022,
       "learning_rate": 2.4068986722935625e-05,
-      "loss": 0.5806,
+      "loss": 0.5893,
       "step": 183
     },
     {
       "epoch": 0.3324299909665763,
-      "grad_norm": 0.27339466736189244,
+      "grad_norm": 0.24182513399667138,
       "learning_rate": 2.3997328420318705e-05,
-      "loss": 0.5769,
+      "loss": 0.5858,
       "step": 184
     },
     {
       "epoch": 0.33423667570009036,
-      "grad_norm": 0.26435674776037377,
+      "grad_norm": 0.2675738732389291,
       "learning_rate": 2.3925347941530556e-05,
-      "loss": 0.5733,
+      "loss": 0.5822,
       "step": 185
     },
     {
       "epoch": 0.33604336043360433,
-      "grad_norm": 0.26341316111660884,
+      "grad_norm": 0.23428952659343405,
       "learning_rate": 2.3853047864046843e-05,
-      "loss": 0.5684,
+      "loss": 0.5779,
       "step": 186
     },
     {
       "epoch": 0.33785004516711836,
-      "grad_norm": 0.27858160542364235,
+      "grad_norm": 0.26339154899807604,
       "learning_rate": 2.3780430776787413e-05,
-      "loss": 0.5658,
+      "loss": 0.5747,
       "step": 187
     },
     {
       "epoch": 0.33965672990063234,
-      "grad_norm": 0.23833042598843737,
+      "grad_norm": 0.21349849308750005,
       "learning_rate": 2.3707499280023604e-05,
-      "loss": 0.5655,
+      "loss": 0.5747,
       "step": 188
     },
     {
       "epoch": 0.34146341463414637,
-      "grad_norm": 0.2808631689375272,
+      "grad_norm": 0.26554041110868815,
       "learning_rate": 2.3634255985285104e-05,
-      "loss": 0.5729,
+      "loss": 0.5825,
       "step": 189
     },
     {
       "epoch": 0.34327009936766034,
-      "grad_norm": 0.25111983735673515,
+      "grad_norm": 0.23538164196617103,
       "learning_rate": 2.356070351526648e-05,
-      "loss": 0.562,
+      "loss": 0.5708,
       "step": 190
     },
     {
       "epoch": 0.34507678410117437,
-      "grad_norm": 0.2571681206798971,
+      "grad_norm": 0.24516795740455555,
       "learning_rate": 2.348684450373322e-05,
-      "loss": 0.5599,
+      "loss": 0.5691,
       "step": 191
     },
     {
       "epoch": 0.34688346883468835,
-      "grad_norm": 0.2409025648925046,
+      "grad_norm": 0.2320939063694949,
       "learning_rate": 2.3412681595427467e-05,
-      "loss": 0.5674,
+      "loss": 0.5761,
       "step": 192
     },
     {
       "epoch": 0.3486901535682023,
-      "grad_norm": 0.29444654953284566,
+      "grad_norm": 0.24367157013907606,
       "learning_rate": 2.3338217445973268e-05,
-      "loss": 0.5687,
+      "loss": 0.5776,
       "step": 193
     },
     {
       "epoch": 0.35049683830171635,
-      "grad_norm": 0.2496920890877963,
+      "grad_norm": 0.2383952654545809,
       "learning_rate": 2.3263454721781537e-05,
-      "loss": 0.5705,
+      "loss": 0.5793,
       "step": 194
     },
     {
       "epoch": 0.3523035230352303,
-      "grad_norm": 0.27467425910302257,
+      "grad_norm": 0.21970860044862534,
       "learning_rate": 2.318839609995453e-05,
-      "loss": 0.5536,
+      "loss": 0.5625,
       "step": 195
     },
     {
       "epoch": 0.35411020776874436,
-      "grad_norm": 0.25067206006192067,
+      "grad_norm": 0.22393266445368756,
       "learning_rate": 2.3113044268189995e-05,
-      "loss": 0.5668,
+      "loss": 0.5758,
       "step": 196
     },
     {
       "epoch": 0.35591689250225833,
-      "grad_norm": 0.25127765224467463,
+      "grad_norm": 0.20965253283535495,
       "learning_rate": 2.303740192468495e-05,
-      "loss": 0.5671,
+      "loss": 0.5754,
       "step": 197
     },
     {
       "epoch": 0.35772357723577236,
-      "grad_norm": 0.2742190997822365,
+      "grad_norm": 0.2134213495454822,
       "learning_rate": 2.2961471778039045e-05,
-      "loss": 0.5436,
+      "loss": 0.5521,
       "step": 198
     },
     {
       "epoch": 0.35953026196928634,
-      "grad_norm": 0.2617420424365515,
+      "grad_norm": 0.2077804399624621,
       "learning_rate": 2.288525654715757e-05,
-      "loss": 0.567,
+      "loss": 0.5758,
       "step": 199
     },
     {
       "epoch": 0.36133694670280037,
-      "grad_norm": 0.2601868662327404,
+      "grad_norm": 0.21089298206975676,
       "learning_rate": 2.280875896115413e-05,
-      "loss": 0.556,
+      "loss": 0.5645,
       "step": 200
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e17e9ef49452dfbb88bdb398539e0416fca0be014460bc3a0231be831d4c7664
+oid sha256:7b75b4a596e16d5098959216e1c00d4bffb5d4776de6dbede10a6917de84c825
 size 8017