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 sha256:6004518858dd47923085a686e83eeac59ce66a86b1b38f9d7f5cf7a3f4c1f3af
+oid sha256:989593d8ed33cc1abae62df6a0d52f910dc57dd2564d4fc13633ac2554b5bac3
 size 4997184968

model-00002-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:162449c2609895d15f3a4430b3244855e446a70d75ad4462d1530e25304e81e0
+oid sha256:d3c2ad4d53eb38adb50a1375a1a0b3cf494064fb6392cc28790605abf44ae584
 size 4997741608

model-00003-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11b3e5a9e00c7c49e40b3e04f1aee7062609a151dd048ef704787405dfd0006f
+oid sha256:076964108eed91fa51eb76c43031788d8378d6062c0da67e2f50e261119a5945
 size 4997742208

model-00004-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6f0f28087ebb1f93ea2fd846843cb629dcad08698aff0c3170ea59286ce2d27
+oid sha256:eb4e2c71908e653ba278eb5c20738157bf532c4836dc810d620a2aa405f39525
 size 4997743184

model-00005-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0787c69725df734c1f833b93727a3cdd45475a36e6c1aa65b8f9480964fc07
+oid sha256:1fbf02ec139a6c96ba30347314f7dc80161dc0597f0c11b8fc76049a917037af
 size 4997743184

model-00006-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe4ca6398d259d9ed10e0326592108fa47922641036885c91bea92af7a01f68
+oid sha256:df1e4931e57af3566b1ff2f2d0e02aa7a36ec86de8f45499b950065ca78899b8
 size 4997743184

model-00007-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58395aaf9fa99306875360f01206090973f35cc5e417db5a3a5b9ad0098921b0
+oid sha256:71e8869186de6e5c07eeff512b5b77904620d6e6581d43c1e1549e0d31fbfb44
 size 4997743184

model-00008-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c338be253c9947423967e587c8b40404698ee27ea16ae8914ec21751800170
+oid sha256:a3eaa8f5d55c3bf92e889213baa27fca7b35696da3294ed98de54a259023641f
 size 4997743184

model-00009-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207813464df8e2277ec2f531dffbab79992012b0f57151d5fe610232e906f8a2
+oid sha256:5d469f47ce03c7faf42ed0734d79584d7c65f7697ccc78ebb88c630a6e2d52a4
 size 4997743184

model-00010-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d73a9c120c59ad5305d4c31d175a324104a03c37857b722f53b086e410da75b3
+oid sha256:c0c998d27ae2a52ca248daff93a0b07a2bc1311f1252dae12a7fbdb7e71adcc5
 size 4997743184

model-00011-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf80e6d153dc41232e869d37dcc5175f19c4560e8f29efe769896b56ed31bbe
+oid sha256:628809b2ac1f03d6ee78117a8736b3cd1503d9dedaa72c6b2cd618d3e3bc9d00
 size 4997743184

model-00012-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3718527ea8bc382e6dd575e8fab1329fdb9d3482046531a8044eb156f62b8ce
+oid sha256:a2e5bc7fc6e79063daafff4d4dc84c7549048b32be482e36723b4a03b5ce3cc1
 size 4997743184

model-00013-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed22c7351cbfcfc4b2e68bf36c9a1e84920534bec607da3f757a86f85fa90ac3
+oid sha256:a4e8000288d4b3af58c0e0e7abb5470f0b6578ccb02c4a4dad695d91c5bd717f
 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

@@ -11,702 +11,702 @@
   "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
     }
   ],

training_args.bin

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