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:c4ec39b8c542dec46c584428bcc41f239ddfa2d7f5f5e01282aa8fc17cfd43f7
+oid sha256:2cb82b1e4227f90eb539df67a23906a0d386529bd90e4416518981a939d50df4
 size 4997184968

model-00002-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888bc516d004ed68e4d137a0425fc721f903558076e2c5eb3091f98f13c2f7d7
+oid sha256:165c9b97ecf4122feed064367305d6b4ee747f28ff4fc7e8d94e393844c8fee0
 size 4997741608

model-00003-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9098519c5209091cdbf2ae6ad89e6f8623b2733f39415bb5e58e18a16c81182c
+oid sha256:21c28227bd44c09f75a1cc23b6223b02c78147ebfe2c9d137f0f3f06257be640
 size 4997742208

model-00004-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98285851600cd3b86069655c14976bdd8da7e969d489bdd46d0e0b37ba6c3ad0
+oid sha256:fce7c4b609b2199ba4bc2760712d703c3f2a4560ae5c3d32282c20d2abd1c67b
 size 4997743184

model-00005-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05637820a3e97cbe0c767eb03e0f7d83cff36fd50d4c8bc584d936d7e068e3b
+oid sha256:308943706770822f3f0e3c55998232a8c0632e9d10eda02c9106273735d1b726
 size 4997743184

model-00006-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bc5f4b89fbc1cfde43a03bcbd497bc48c2e5664e8d5d0ff18b5f4f99968b881
+oid sha256:adb6b63d7f05f576a681ed78e82162d3b8416dfbb288ae68e3f68b1dd6a8ea2f
 size 4997743184

model-00007-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cdcf393112aee1f1b1979b9a8d317ecbd3f30ba04b45640981768ef8cc8641b
+oid sha256:e6c55451276d19052507d488e74846ea84bd17a3ea982b7e1c8c5d4502b120fe
 size 4997743184

model-00008-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a0c698599c34c6ebca6bce94f7d2bf4b01ba907b12dc3687ce69cb08e302ed0
+oid sha256:493720f40234c7d1c82dded0266793cc1d77bfe3d3cf196ba6d16dc197a4330a
 size 4997743184

model-00009-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc388c6012d6ddba57665bfe588a5c3791d0ed33a18117ef0e8fe13364a81bc
+oid sha256:24f9ebf5e271e1b068f8fbf4312a124a5855857286fd063e78a25c6c46f735d9
 size 4997743184

model-00010-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab710fe0b2f24fffdb29679d2eb5d3224e762cb3615c74d37f405bb3c3a9b18b
+oid sha256:d0fc67b140de70461152ffe0d1d4f39d610273d498a180520eb93519a9578a1f
 size 4997743184

model-00011-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12e18dc22e8b72e7a489b13911b19ccf42f66d360b823f5f92a005bdedcc827e
+oid sha256:c15508f97bd308053a4316b31a4eac5c24e60a9e1df4d762ebfaac10e9e0ed58
 size 4997743184

model-00012-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b94eec06606cc616588201353704c6b13b76af4a4c9631cbd86d6baa60107a32
+oid sha256:da7e4a9da619d34efd17daed024a177a1251ff995b46630f755b6699327d912d
 size 4997743184

model-00013-of-00013.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e617bdbabf28f382f1b6c67e6031a9e42bed1fd93899be3c91232a9ebbd627
+oid sha256:6f27829fb905e82ca6602bfe1c29fed13cf8084e97dab950a5ccc8b35ef990aa
 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

@@ -11,800 +11,800 @@
   "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
     },
     {
       "epoch": 1.0175438596491229,
-      "grad_norm": 0.8079734171770722,
+      "grad_norm": 0.6793013357179898,
       "learning_rate": 4.707368982147318e-05,
-      "loss": 0.7363,
+      "loss": 0.7762,
       "step": 58
     },
     {
       "epoch": 1.0350877192982457,
-      "grad_norm": 0.647606443516366,
+      "grad_norm": 0.627446069759414,
       "learning_rate": 4.693563494886455e-05,
-      "loss": 0.628,
+      "loss": 0.6663,
       "step": 59
     },
     {
       "epoch": 1.0526315789473684,
-      "grad_norm": 1.0392055903524327,
+      "grad_norm": 0.6603925054843989,
       "learning_rate": 4.679461034241906e-05,
-      "loss": 0.7284,
+      "loss": 0.7633,
       "step": 60
     },
     {
       "epoch": 1.0701754385964912,
-      "grad_norm": 0.8936107628035881,
+      "grad_norm": 0.8788262913431679,
       "learning_rate": 4.665063509461097e-05,
-      "loss": 0.6199,
+      "loss": 0.6608,
       "step": 61
     },
     {
       "epoch": 1.087719298245614,
-      "grad_norm": 0.8579847990954221,
+      "grad_norm": 0.6735739896088276,
       "learning_rate": 4.650372869738414e-05,
-      "loss": 0.6542,
+      "loss": 0.7057,
       "step": 62
     },
     {
       "epoch": 1.1052631578947367,
-      "grad_norm": 1.2135497198079113,
+      "grad_norm": 1.1748331139699308,
       "learning_rate": 4.6353911039513145e-05,
-      "loss": 0.7282,
+      "loss": 0.7607,
       "step": 63
     },
     {
       "epoch": 1.1228070175438596,
-      "grad_norm": 0.8104073129740915,
+      "grad_norm": 0.8665469540278155,
       "learning_rate": 4.620120240391065e-05,
-      "loss": 0.6731,
+      "loss": 0.7229,
       "step": 64
     },
     {
       "epoch": 1.1403508771929824,
-      "grad_norm": 0.6601313754612921,
+      "grad_norm": 0.6395824700230515,
       "learning_rate": 4.604562346488144e-05,
-      "loss": 0.6216,
+      "loss": 0.6613,
       "step": 65
     },
     {
       "epoch": 1.1578947368421053,
-      "grad_norm": 0.7521560385174539,
+      "grad_norm": 0.7075740149066272,
       "learning_rate": 4.588719528532342e-05,
-      "loss": 0.6368,
+      "loss": 0.6818,
       "step": 66
     },
     {
       "epoch": 1.1754385964912282,
-      "grad_norm": 0.6696118869453084,
+      "grad_norm": 0.6512740767179199,
       "learning_rate": 4.572593931387604e-05,
-      "loss": 0.6243,
+      "loss": 0.6719,
       "step": 67
     },
     {
       "epoch": 1.1929824561403508,
-      "grad_norm": 0.7323191679088321,
+      "grad_norm": 0.7391191118171585,
       "learning_rate": 4.556187738201656e-05,
-      "loss": 0.6631,
+      "loss": 0.716,
       "step": 68
     },
     {
       "epoch": 1.2105263157894737,
-      "grad_norm": 0.7881911923428006,
+      "grad_norm": 0.6544655450388867,
       "learning_rate": 4.539503170110431e-05,
-      "loss": 0.702,
+      "loss": 0.7671,
       "step": 69
     },
     {
       "epoch": 1.2280701754385965,
-      "grad_norm": 0.5443171520898024,
+      "grad_norm": 0.4890450142415007,
       "learning_rate": 4.522542485937369e-05,
-      "loss": 0.6556,
+      "loss": 0.7089,
       "step": 70
     },
     {
       "epoch": 1.2456140350877192,
-      "grad_norm": 0.7465685103291306,
+      "grad_norm": 0.6629174444368172,
       "learning_rate": 4.50530798188761e-05,
-      "loss": 0.7226,
+      "loss": 0.7644,
       "step": 71
     },
     {
       "epoch": 1.263157894736842,
-      "grad_norm": 1.531802448485134,
+      "grad_norm": 1.313611758541734,
       "learning_rate": 4.48780199123712e-05,
-      "loss": 0.6821,
+      "loss": 0.7247,
       "step": 72
     },
     {
       "epoch": 1.280701754385965,
-      "grad_norm": 0.624551106382425,
+      "grad_norm": 0.621594494051855,
       "learning_rate": 4.4700268840168045e-05,
-      "loss": 0.6704,
+      "loss": 0.7177,
       "step": 73
     },
     {
       "epoch": 1.2982456140350878,
-      "grad_norm": 0.5646709447787752,
+      "grad_norm": 0.543283643604564,
       "learning_rate": 4.4519850666916484e-05,
-      "loss": 0.6031,
+      "loss": 0.6484,
       "step": 74
     },
     {
       "epoch": 1.3157894736842106,
-      "grad_norm": 0.6162637626547116,
+      "grad_norm": 0.5692124563338323,
       "learning_rate": 4.43367898183491e-05,
-      "loss": 0.7309,
+      "loss": 0.7805,
       "step": 75
     },
     {
       "epoch": 1.3333333333333333,
-      "grad_norm": 0.484728084443174,
+      "grad_norm": 0.5140372497115965,
       "learning_rate": 4.415111107797445e-05,
-      "loss": 0.6089,
+      "loss": 0.6551,
       "step": 76
     },
     {
       "epoch": 1.3508771929824561,
-      "grad_norm": 0.5348661093893772,
+      "grad_norm": 0.5556993211984754,
       "learning_rate": 4.396283958372173e-05,
-      "loss": 0.6013,
+      "loss": 0.6435,
       "step": 77
     },
     {
       "epoch": 1.368421052631579,
-      "grad_norm": 0.6972365743462106,
+      "grad_norm": 0.6297070634295856,
       "learning_rate": 4.377200082453749e-05,
-      "loss": 0.7103,
+      "loss": 0.7551,
       "step": 78
     },
     {
       "epoch": 1.3859649122807016,
-      "grad_norm": 0.6386714887467159,
+      "grad_norm": 0.5343607416783988,
       "learning_rate": 4.357862063693486e-05,
-      "loss": 0.6876,
+      "loss": 0.7401,
       "step": 79
     },
     {
       "epoch": 1.4035087719298245,
-      "grad_norm": 0.6068938883006068,
+      "grad_norm": 0.6933983776921214,
       "learning_rate": 4.3382725201495723e-05,
-      "loss": 0.6655,
+      "loss": 0.7092,
       "step": 80
     },
     {
       "epoch": 1.4210526315789473,
-      "grad_norm": 0.5578279802500624,
+      "grad_norm": 0.48867547087530555,
       "learning_rate": 4.318434103932622e-05,
-      "loss": 0.6688,
+      "loss": 0.7157,
       "step": 81
     },
     {
       "epoch": 1.4385964912280702,
-      "grad_norm": 0.5450559810011418,
+      "grad_norm": 0.5074429307644182,
       "learning_rate": 4.2983495008466276e-05,
-      "loss": 0.6545,
+      "loss": 0.6988,
       "step": 82
     },
     {
       "epoch": 1.456140350877193,
-      "grad_norm": 0.549555813592061,
+      "grad_norm": 0.546003726314663,
       "learning_rate": 4.278021430025343e-05,
-      "loss": 0.5803,
+      "loss": 0.6233,
       "step": 83
     },
     {
       "epoch": 1.4736842105263157,
-      "grad_norm": 0.44599243421537427,
+      "grad_norm": 0.46092178005444556,
       "learning_rate": 4.257452643564155e-05,
-      "loss": 0.5056,
+      "loss": 0.5562,
       "step": 84
     },
     {
       "epoch": 1.4912280701754386,
-      "grad_norm": 0.6512205627641299,
+      "grad_norm": 0.5753767938443312,
       "learning_rate": 4.2366459261474933e-05,
-      "loss": 0.6704,
+      "loss": 0.7155,
       "step": 85
     },
     {
       "epoch": 1.5087719298245614,
-      "grad_norm": 0.5031784031963774,
+      "grad_norm": 0.5118274305991928,
       "learning_rate": 4.215604094671835e-05,
-      "loss": 0.6411,
+      "loss": 0.6921,
       "step": 86
     },
     {
       "epoch": 1.526315789473684,
-      "grad_norm": 0.5371693274835859,
+      "grad_norm": 0.6380979260118252,
       "learning_rate": 4.194329997864331e-05,
-      "loss": 0.7647,
+      "loss": 0.8256,
       "step": 87
     },
     {
       "epoch": 1.543859649122807,
-      "grad_norm": 0.5952220323734707,
+      "grad_norm": 0.5435984291436712,
       "learning_rate": 4.172826515897146e-05,
-      "loss": 0.6663,
+      "loss": 0.7167,
       "step": 88
     },
     {
       "epoch": 1.5614035087719298,
-      "grad_norm": 0.5194062067573968,
+      "grad_norm": 0.4654905831182726,
       "learning_rate": 4.1510965599975196e-05,
-      "loss": 0.7005,
+      "loss": 0.7498,
       "step": 89
     },
     {
       "epoch": 1.5789473684210527,
-      "grad_norm": 0.5666524807032483,
+      "grad_norm": 0.5655561181667187,
       "learning_rate": 4.129143072053638e-05,
-      "loss": 0.604,
+      "loss": 0.6566,
       "step": 90
     },
     {
       "epoch": 1.5964912280701755,
-      "grad_norm": 0.5389713669315125,
+      "grad_norm": 0.46666240125611763,
       "learning_rate": 4.1069690242163484e-05,
-      "loss": 0.6349,
+      "loss": 0.6798,
       "step": 91
     },
     {
       "epoch": 1.6140350877192984,
-      "grad_norm": 0.5311149694642213,
+      "grad_norm": 0.45866681537946846,
       "learning_rate": 4.0845774184967754e-05,
-      "loss": 0.652,
+      "loss": 0.702,
       "step": 92
     },
     {
       "epoch": 1.631578947368421,
-      "grad_norm": 0.5012325622032431,
+      "grad_norm": 0.41578111266812384,
       "learning_rate": 4.0619712863599e-05,
-      "loss": 0.5946,
+      "loss": 0.6448,
       "step": 93
     },
     {
       "epoch": 1.6491228070175439,
-      "grad_norm": 0.4814283230741368,
+      "grad_norm": 0.37343214189013274,
       "learning_rate": 4.039153688314145e-05,
-      "loss": 0.6008,
+      "loss": 0.6486,
       "step": 94
     },
     {
       "epoch": 1.6666666666666665,
-      "grad_norm": 0.5273571145503247,
+      "grad_norm": 0.4534534413589986,
       "learning_rate": 4.0161277134970345e-05,
-      "loss": 0.6998,
+      "loss": 0.7514,
       "step": 95
     },
     {
       "epoch": 1.6842105263157894,
-      "grad_norm": 0.6037954834513913,
+      "grad_norm": 0.5086874484641599,
       "learning_rate": 3.9928964792569655e-05,
-      "loss": 0.6152,
+      "loss": 0.6561,
       "step": 96
     },
     {
       "epoch": 1.7017543859649122,
-      "grad_norm": 0.5375890783535183,
+      "grad_norm": 0.5099982692153668,
       "learning_rate": 3.969463130731183e-05,
-      "loss": 0.7677,
+      "loss": 0.818,
       "step": 97
     },
     {
       "epoch": 1.719298245614035,
-      "grad_norm": 0.6267427489443681,
+      "grad_norm": 0.5239173636107562,
       "learning_rate": 3.945830840419966e-05,
-      "loss": 0.6621,
+      "loss": 0.707,
       "step": 98
     },
     {
       "epoch": 1.736842105263158,
-      "grad_norm": 0.5070654701641488,
+      "grad_norm": 0.5057288153759746,
       "learning_rate": 3.9220028077571295e-05,
-      "loss": 0.679,
+      "loss": 0.7297,
       "step": 99
     },
     {
       "epoch": 1.7543859649122808,
-      "grad_norm": 0.49591448977957925,
+      "grad_norm": 0.4578235248160848,
       "learning_rate": 3.897982258676867e-05,
-      "loss": 0.6153,
+      "loss": 0.6636,
       "step": 100
     },
     {
       "epoch": 1.7719298245614035,
-      "grad_norm": 0.5563015062976071,
+      "grad_norm": 0.4741202765186654,
       "learning_rate": 3.873772445177015e-05,
-      "loss": 0.7054,
+      "loss": 0.7528,
       "step": 101
     },
     {
       "epoch": 1.7894736842105263,
-      "grad_norm": 0.4874896431926999,
+      "grad_norm": 0.4039174802249478,
       "learning_rate": 3.8493766448787825e-05,
-      "loss": 0.6942,
+      "loss": 0.7435,
       "step": 102
     },
     {
       "epoch": 1.807017543859649,
-      "grad_norm": 0.6557911386705954,
+      "grad_norm": 0.589597565267169,
       "learning_rate": 3.824798160583012e-05,
-      "loss": 0.695,
+      "loss": 0.7506,
       "step": 103
     },
     {
       "epoch": 1.8245614035087718,
-      "grad_norm": 0.5154404737450541,
+      "grad_norm": 0.44486881957400587,
       "learning_rate": 3.8000403198230387e-05,
-      "loss": 0.5788,
+      "loss": 0.6197,
       "step": 104
     },
     {
       "epoch": 1.8421052631578947,
-      "grad_norm": 0.4665270737354506,
+      "grad_norm": 0.4171720478200468,
       "learning_rate": 3.775106474414188e-05,
-      "loss": 0.5437,
+      "loss": 0.5865,
       "step": 105
     },
     {
       "epoch": 1.8596491228070176,
-      "grad_norm": 0.7148660834996573,
+      "grad_norm": 0.6688671369020073,
       "learning_rate": 3.7500000000000003e-05,
-      "loss": 0.758,
+      "loss": 0.8046,
       "step": 106
     },
     {
       "epoch": 1.8771929824561404,
-      "grad_norm": 0.7335976271467938,
+      "grad_norm": 0.594947999839499,
       "learning_rate": 3.7247242955952175e-05,
-      "loss": 0.6691,
+      "loss": 0.7218,
       "step": 107
     },
     {
       "epoch": 1.8947368421052633,
-      "grad_norm": 0.5963174425512796,
+      "grad_norm": 0.4541655734242718,
       "learning_rate": 3.699282783125616e-05,
-      "loss": 0.668,
+      "loss": 0.7191,
       "step": 108
     },
     {
       "epoch": 1.912280701754386,
-      "grad_norm": 0.5791219305747107,
+      "grad_norm": 0.44254870382471806,
       "learning_rate": 3.673678906964727e-05,
-      "loss": 0.5826,
+      "loss": 0.6318,
       "step": 109
     },
     {
       "epoch": 1.9298245614035088,
-      "grad_norm": 0.5583303920187029,
+      "grad_norm": 0.5177824211881119,
       "learning_rate": 3.6479161334675296e-05,
-      "loss": 0.7001,
+      "loss": 0.7521,
       "step": 110
     },
     {
       "epoch": 1.9473684210526314,
-      "grad_norm": 0.6110054211158291,
+      "grad_norm": 0.5109935026690099,
       "learning_rate": 3.621997950501156e-05,
-      "loss": 0.7133,
+      "loss": 0.7555,
       "step": 111
     },
     {
       "epoch": 1.9649122807017543,
-      "grad_norm": 0.617058874054503,
+      "grad_norm": 0.6025137993464594,
       "learning_rate": 3.5959278669726935e-05,
-      "loss": 0.6776,
+      "loss": 0.7303,
       "step": 112
     },
     {
       "epoch": 1.9824561403508771,
-      "grad_norm": 0.5818691639875067,
+      "grad_norm": 0.45225891946430735,
       "learning_rate": 3.569709412354136e-05,
-      "loss": 0.7395,
+      "loss": 0.7882,
       "step": 113
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.7383826511530396,
+      "grad_norm": 0.613838203258988,
       "learning_rate": 3.543346136204545e-05,
-      "loss": 0.5666,
+      "loss": 0.6483,
       "step": 114
     }
   ],

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