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:b6edba9bbeccb3e931db4735c9015c163eb25c2a712bf3af6c1018da4302233b
+oid sha256:c4f25daa81041e3089f0c5611ff9eada4e29812eaaaf1414d46b011017465321
 size 4997184968

model-00002-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81c449f9b67c1a2df0127195d08f2e797c084b4c787c8f46fdb01ef9b1e16f2
+oid sha256:a54bcbe6f8fa2d01f059ad775d1ce2ca0a8748e56ac0a5c4e857a65e0d59401e
 size 4997741608

model-00003-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bae47680b03d19badc9113aef3db013b041dab7e2502a28b5adc4391e984858d
+oid sha256:7c745de27ec6798ffc207fcdcfee069d4922f5c0426019b24cb4405992776c6c
 size 4997742208

model-00004-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1581646182357e007f26a4410488b597242c10f737d6f026b9f912db1b3467
+oid sha256:4d68af5e887e6239c081bc847696c5cd741d44defe7d2188bf72f0eea7b0563c
 size 4997743184

model-00005-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24fe9a3affa483f00385859a5a3042bd250a068f5e5b4841c11dc6bbd5f6a4b6
+oid sha256:58395c4c944248528d4a1b62309f5944a36249ea1c409e20f90ff21c17bbf49a
 size 4997743184

model-00006-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0f1835e014aa5067f9c73c47ef1c464370d4e60a594799cdcdd538b9eb74db
+oid sha256:c9fcc33a21010650e8b266ea1537e594763e26c9b1eba1c28e21ec6313947cfe
 size 4997743184

model-00007-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e82e12fae00a395bdd0a1b42339245272957f88f41749861a35a1aecd86050ef
+oid sha256:630cc4683dc57615ce50a6b897f0bf964965e8b06446b57bf3327882e48a4383
 size 4997743184

model-00008-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39e975751c9162bff8c8ac336432f261f00e02ae2234699cbccc5db0abed0f7
+oid sha256:e94df70d8dae12edaa6398c6810eaceeca28443fe9da4abc064f7543a38eb4f9
 size 4997743184

model-00009-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f88ca74b7463e2beaf1305858e520635074d06c045057caccd91476355c247
+oid sha256:d871090f232f36371b5605657993f4dc24d1a2f045d023216e9e3e6b80131360
 size 4997743184

model-00010-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:209f711d8af0c56da0f0446199e089619b221978c1b95aa28f6471491a8572a7
+oid sha256:7ff5549d63d7c0b6bf6f57f105aeddc96a8c0f71b687912cfdaace928a1486d7
 size 4997743184

model-00011-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd247964026c0ae0bad785569dd4dfd0783220e8f1889e9861e93980c36772f
+oid sha256:bd42b9fbdc0159ffa146576fbe01ca567c0109ffc719ab06aa351d652ecccf3a
 size 4997743184

model-00012-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c906c2335dcec81fafb33ec4d13682d7995c7046a4b3c2a743e5f80f5a5351fe
+oid sha256:bb2ac1fcb28d411a4224268d44f7711ee81d6417a536f8c9d016688e8e0f4578
 size 4997743184

model-00013-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3f702ea8c0aa09fcbfc340b3d18f0e829ec0b127137148c70292756a6bff0ee
+oid sha256:f4301251d9ddd9244ed412a9126d9fbb549dea24a022adddcc65f536cc934219
 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

@@ -11,401 +11,401 @@
   "log_history": [
     {
       "epoch": 0.017543859649122806,
-      "grad_norm": 2.1737315354989266,
+      "grad_norm": 1.8317057887019643,
       "learning_rate": 0.0,
       "loss": 0.8483,
       "step": 1
     },
     {
       "epoch": 0.03508771929824561,
-      "grad_norm": 2.0657831287103607,
+      "grad_norm": 1.7353440418305668,
       "learning_rate": 3.3333333333333333e-06,
       "loss": 0.8763,
       "step": 2
     },
     {
       "epoch": 0.05263157894736842,
-      "grad_norm": 2.2705565927471225,
+      "grad_norm": 1.9110385217084043,
       "learning_rate": 6.666666666666667e-06,
-      "loss": 1.019,
+      "loss": 1.0195,
       "step": 3
     },
     {
       "epoch": 0.07017543859649122,
-      "grad_norm": 1.8847905520566954,
+      "grad_norm": 1.650455460756132,
       "learning_rate": 1e-05,
-      "loss": 1.0442,
+      "loss": 1.049,
       "step": 4
     },
     {
       "epoch": 0.08771929824561403,
-      "grad_norm": 1.6215868467951315,
+      "grad_norm": 0.9846115915202341,
       "learning_rate": 1.3333333333333333e-05,
-      "loss": 0.8301,
+      "loss": 0.8378,
       "step": 5
     },
     {
       "epoch": 0.10526315789473684,
-      "grad_norm": 1.3337654525321527,
+      "grad_norm": 1.2896673412488742,
       "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.967,
+      "loss": 0.9736,
       "step": 6
     },
     {
       "epoch": 0.12280701754385964,
-      "grad_norm": 2.3177821608360234,
+      "grad_norm": 2.011543412600694,
       "learning_rate": 2e-05,
-      "loss": 0.9657,
+      "loss": 0.9678,
       "step": 7
     },
     {
       "epoch": 0.14035087719298245,
-      "grad_norm": 1.9407807377668538,
+      "grad_norm": 1.6250329547144573,
       "learning_rate": 2.3333333333333336e-05,
-      "loss": 0.9063,
+      "loss": 0.9089,
       "step": 8
     },
     {
       "epoch": 0.15789473684210525,
-      "grad_norm": 2.333688544412328,
+      "grad_norm": 1.6751272065587126,
       "learning_rate": 2.6666666666666667e-05,
-      "loss": 0.9327,
+      "loss": 0.9359,
       "step": 9
     },
     {
       "epoch": 0.17543859649122806,
-      "grad_norm": 1.8911158364164133,
+      "grad_norm": 1.4234656524715992,
       "learning_rate": 3e-05,
-      "loss": 0.9615,
+      "loss": 0.9585,
       "step": 10
     },
     {
       "epoch": 0.19298245614035087,
-      "grad_norm": 1.559026746068459,
+      "grad_norm": 1.4638280218342359,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.9983,
+      "loss": 1.0041,
       "step": 11
     },
     {
       "epoch": 0.21052631578947367,
-      "grad_norm": 1.0012950206512936,
+      "grad_norm": 1.0419301809036907,
       "learning_rate": 3.6666666666666666e-05,
-      "loss": 0.8713,
+      "loss": 0.8763,
       "step": 12
     },
     {
       "epoch": 0.22807017543859648,
-      "grad_norm": 1.0896746007190306,
+      "grad_norm": 1.198346639614849,
       "learning_rate": 4e-05,
-      "loss": 0.9018,
+      "loss": 0.9129,
       "step": 13
     },
     {
       "epoch": 0.24561403508771928,
-      "grad_norm": 1.1472331615890097,
+      "grad_norm": 1.0034373969603534,
       "learning_rate": 4.3333333333333334e-05,
-      "loss": 0.8905,
+      "loss": 0.8965,
       "step": 14
     },
     {
       "epoch": 0.2631578947368421,
-      "grad_norm": 1.0827434164812821,
+      "grad_norm": 1.0380657919294447,
       "learning_rate": 4.666666666666667e-05,
-      "loss": 0.9487,
+      "loss": 0.957,
       "step": 15
     },
     {
       "epoch": 0.2807017543859649,
-      "grad_norm": 0.8407939026078357,
+      "grad_norm": 0.9533939175115029,
       "learning_rate": 5e-05,
-      "loss": 0.9016,
+      "loss": 0.91,
       "step": 16
     },
     {
       "epoch": 0.2982456140350877,
-      "grad_norm": 1.256351670462119,
+      "grad_norm": 1.2098882485474858,
       "learning_rate": 4.999830770009406e-05,
-      "loss": 1.0016,
+      "loss": 1.0061,
       "step": 17
     },
     {
       "epoch": 0.3157894736842105,
-      "grad_norm": 1.010708781438488,
+      "grad_norm": 0.9892702554456709,
       "learning_rate": 4.9993231029486544e-05,
-      "loss": 0.8827,
+      "loss": 0.8912,
       "step": 18
     },
     {
       "epoch": 0.3333333333333333,
-      "grad_norm": 0.7503718658890081,
+      "grad_norm": 0.715562209343003,
       "learning_rate": 4.99847706754774e-05,
-      "loss": 0.9054,
+      "loss": 0.9125,
       "step": 19
     },
     {
       "epoch": 0.3508771929824561,
-      "grad_norm": 0.8427918773123176,
+      "grad_norm": 0.8839740963896582,
       "learning_rate": 4.997292778346312e-05,
-      "loss": 0.9468,
+      "loss": 0.9544,
       "step": 20
     },
     {
       "epoch": 0.3684210526315789,
-      "grad_norm": 0.9103198542357233,
+      "grad_norm": 0.8672090781221823,
       "learning_rate": 4.995770395678171e-05,
-      "loss": 0.8832,
+      "loss": 0.8931,
       "step": 21
     },
     {
       "epoch": 0.38596491228070173,
-      "grad_norm": 0.743975757226857,
+      "grad_norm": 0.5657183889732781,
       "learning_rate": 4.993910125649561e-05,
-      "loss": 0.7529,
+      "loss": 0.7591,
       "step": 22
     },
     {
       "epoch": 0.40350877192982454,
-      "grad_norm": 0.8055578797506145,
+      "grad_norm": 0.8395194599838961,
       "learning_rate": 4.9917122201112656e-05,
-      "loss": 0.889,
+      "loss": 0.8958,
       "step": 23
     },
     {
       "epoch": 0.42105263157894735,
-      "grad_norm": 0.8546590892160185,
+      "grad_norm": 0.7949156783532444,
       "learning_rate": 4.989176976624511e-05,
-      "loss": 0.7896,
+      "loss": 0.7957,
       "step": 24
     },
     {
       "epoch": 0.43859649122807015,
-      "grad_norm": 0.6051439965679499,
+      "grad_norm": 0.6233078811754251,
       "learning_rate": 4.9863047384206835e-05,
-      "loss": 0.9219,
+      "loss": 0.9287,
       "step": 25
     },
     {
       "epoch": 0.45614035087719296,
-      "grad_norm": 0.7522440995111975,
+      "grad_norm": 0.6592512357205284,
       "learning_rate": 4.983095894354858e-05,
-      "loss": 0.8917,
+      "loss": 0.8961,
       "step": 26
     },
     {
       "epoch": 0.47368421052631576,
-      "grad_norm": 0.7072008972448397,
+      "grad_norm": 0.7540428801849153,
       "learning_rate": 4.979550878853154e-05,
-      "loss": 0.8044,
+      "loss": 0.8113,
       "step": 27
     },
     {
       "epoch": 0.49122807017543857,
-      "grad_norm": 0.5952822120665937,
+      "grad_norm": 0.6894407810210612,
       "learning_rate": 4.975670171853926e-05,
-      "loss": 0.8763,
+      "loss": 0.8837,
       "step": 28
     },
     {
       "epoch": 0.5087719298245614,
-      "grad_norm": 0.5803355862918257,
+      "grad_norm": 0.5962438335142802,
       "learning_rate": 4.971454298742779e-05,
-      "loss": 0.8983,
+      "loss": 0.9039,
       "step": 29
     },
     {
       "epoch": 0.5263157894736842,
-      "grad_norm": 0.666437418274057,
+      "grad_norm": 0.6159211013371156,
       "learning_rate": 4.966903830281449e-05,
-      "loss": 0.7866,
+      "loss": 0.7894,
       "step": 30
     },
     {
       "epoch": 0.543859649122807,
-      "grad_norm": 0.6919189164588267,
+      "grad_norm": 0.7929356664184409,
       "learning_rate": 4.962019382530521e-05,
-      "loss": 0.8412,
+      "loss": 0.8463,
       "step": 31
     },
     {
       "epoch": 0.5614035087719298,
-      "grad_norm": 0.5772289061045422,
+      "grad_norm": 0.5952896775612254,
       "learning_rate": 4.9568016167660334e-05,
-      "loss": 0.7779,
+      "loss": 0.7816,
       "step": 32
     },
     {
       "epoch": 0.5789473684210527,
-      "grad_norm": 0.6384456727598309,
+      "grad_norm": 0.6758915434113398,
       "learning_rate": 4.951251239389948e-05,
-      "loss": 0.8722,
+      "loss": 0.8776,
       "step": 33
     },
     {
       "epoch": 0.5964912280701754,
-      "grad_norm": 0.7003155529960633,
+      "grad_norm": 0.6318291971598253,
       "learning_rate": 4.9453690018345144e-05,
-      "loss": 0.9772,
+      "loss": 0.9796,
       "step": 34
     },
     {
       "epoch": 0.6140350877192983,
-      "grad_norm": 0.5892482774139678,
+      "grad_norm": 0.7115801773839961,
       "learning_rate": 4.939155700460536e-05,
-      "loss": 0.8181,
+      "loss": 0.8228,
       "step": 35
     },
     {
       "epoch": 0.631578947368421,
-      "grad_norm": 0.7141350627505272,
+      "grad_norm": 0.5864293536264706,
       "learning_rate": 4.9326121764495596e-05,
-      "loss": 0.8379,
+      "loss": 0.839,
       "step": 36
     },
     {
       "epoch": 0.6491228070175439,
-      "grad_norm": 0.6685379755417092,
+      "grad_norm": 0.6287778513114669,
       "learning_rate": 4.925739315689991e-05,
-      "loss": 0.876,
+      "loss": 0.8778,
       "step": 37
     },
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 0.5887972405354546,
+      "grad_norm": 0.6735952098345708,
       "learning_rate": 4.9185380486571595e-05,
-      "loss": 0.8834,
+      "loss": 0.885,
       "step": 38
     },
     {
       "epoch": 0.6842105263157895,
-      "grad_norm": 0.6547850047970274,
+      "grad_norm": 0.6067535888888641,
       "learning_rate": 4.9110093502873476e-05,
-      "loss": 0.9068,
+      "loss": 0.9082,
       "step": 39
     },
     {
       "epoch": 0.7017543859649122,
-      "grad_norm": 0.5095372843368391,
+      "grad_norm": 0.5247508841910119,
       "learning_rate": 4.9031542398457974e-05,
-      "loss": 0.871,
+      "loss": 0.8739,
       "step": 40
     },
     {
       "epoch": 0.7192982456140351,
-      "grad_norm": 0.5803092931334194,
+      "grad_norm": 0.5918453184670143,
       "learning_rate": 4.894973780788722e-05,
-      "loss": 0.8804,
+      "loss": 0.8829,
       "step": 41
     },
     {
       "epoch": 0.7368421052631579,
-      "grad_norm": 0.5157094405208372,
+      "grad_norm": 0.6372269077212606,
       "learning_rate": 4.88646908061933e-05,
-      "loss": 0.8112,
+      "loss": 0.8152,
       "step": 42
     },
     {
       "epoch": 0.7543859649122807,
-      "grad_norm": 0.5763799658576816,
+      "grad_norm": 0.5430663295315261,
       "learning_rate": 4.877641290737884e-05,
-      "loss": 0.8485,
+      "loss": 0.8514,
       "step": 43
     },
     {
       "epoch": 0.7719298245614035,
-      "grad_norm": 0.5206239155896253,
+      "grad_norm": 0.511597332007924,
       "learning_rate": 4.868491606285823e-05,
-      "loss": 0.7658,
+      "loss": 0.7675,
       "step": 44
     },
     {
       "epoch": 0.7894736842105263,
-      "grad_norm": 0.5163119284367372,
+      "grad_norm": 0.48967659833861754,
       "learning_rate": 4.859021265983959e-05,
-      "loss": 0.8806,
+      "loss": 0.8826,
       "step": 45
     },
     {
       "epoch": 0.8070175438596491,
-      "grad_norm": 0.5555872744357858,
+      "grad_norm": 0.5856811530030098,
       "learning_rate": 4.849231551964771e-05,
-      "loss": 0.8559,
+      "loss": 0.8585,
       "step": 46
     },
     {
       "epoch": 0.8245614035087719,
-      "grad_norm": 0.670329020537153,
+      "grad_norm": 0.5845644414839125,
       "learning_rate": 4.839123789598829e-05,
-      "loss": 0.8667,
+      "loss": 0.8677,
       "step": 47
     },
     {
       "epoch": 0.8421052631578947,
-      "grad_norm": 0.5517318833150326,
+      "grad_norm": 0.4974332648938187,
       "learning_rate": 4.828699347315356e-05,
-      "loss": 0.8424,
+      "loss": 0.845,
       "step": 48
     },
     {
       "epoch": 0.8596491228070176,
-      "grad_norm": 0.6399166130889407,
+      "grad_norm": 0.5566174918152419,
       "learning_rate": 4.817959636416969e-05,
-      "loss": 0.9417,
+      "loss": 0.9432,
       "step": 49
     },
     {
       "epoch": 0.8771929824561403,
-      "grad_norm": 0.460883037522045,
+      "grad_norm": 0.4921351014911049,
       "learning_rate": 4.806906110888606e-05,
-      "loss": 0.6751,
+      "loss": 0.6756,
       "step": 50
     },
     {
       "epoch": 0.8947368421052632,
-      "grad_norm": 0.6278603703151171,
+      "grad_norm": 0.6352002986003276,
       "learning_rate": 4.7955402672006854e-05,
-      "loss": 0.9086,
+      "loss": 0.9077,
       "step": 51
     },
     {
       "epoch": 0.9122807017543859,
-      "grad_norm": 0.5482062880943421,
+      "grad_norm": 0.5228777570085404,
       "learning_rate": 4.783863644106502e-05,
-      "loss": 0.8832,
+      "loss": 0.8815,
       "step": 52
     },
     {
       "epoch": 0.9298245614035088,
-      "grad_norm": 0.5538960900799985,
+      "grad_norm": 0.5753314530576694,
       "learning_rate": 4.771877822433911e-05,
-      "loss": 0.8332,
+      "loss": 0.8342,
       "step": 53
     },
     {
       "epoch": 0.9473684210526315,
-      "grad_norm": 0.5020357523197391,
+      "grad_norm": 0.5127814989448164,
       "learning_rate": 4.759584424871302e-05,
-      "loss": 0.7833,
+      "loss": 0.7837,
       "step": 54
     },
     {
       "epoch": 0.9649122807017544,
-      "grad_norm": 0.5299810912852558,
+      "grad_norm": 0.545931046230859,
       "learning_rate": 4.7469851157479177e-05,
-      "loss": 0.8219,
+      "loss": 0.8229,
       "step": 55
     },
     {
       "epoch": 0.9824561403508771,
-      "grad_norm": 0.48572413576489937,
+      "grad_norm": 0.4669374807712089,
       "learning_rate": 4.734081600808531e-05,
-      "loss": 0.8327,
+      "loss": 0.8341,
       "step": 56
     },
     {
       "epoch": 1.0,
-      "grad_norm": 0.7694567676131596,
+      "grad_norm": 0.5386650743226552,
       "learning_rate": 4.7208756269825104e-05,
-      "loss": 0.6932,
+      "loss": 0.7062,
       "step": 57
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d83b4df5d706e4c8bc431f088d2170998a3a8eafe51554ccb621ba77c95afe02
-size 8017
+oid sha256:14ce14cb5b4d1f6b7378f3a0d59f90353c316de79d943a6fb969a0b7df2b441c
+size 8081