Upload folder using huggingface_hub

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-2000/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-2000/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217da57954c18cbe2b526c274a89ca622b0e78a4d0aac7dc38e7edf2ba4e3c0b
+size 323014168

checkpoint-2000/chat_template.jinja

@@ -0,0 +1,53 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e4e938c2f3b94837f04728c0b768cfbf743b4aeffed0e19609d6a8a4e563931
+size 164469317

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
+size 14645

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ba9eb2d1189b868edc58f70ee446df3397991a4dbc37188b18900d533f5de3
+size 1465

checkpoint-2000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1624497421110344,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000812248710555172,
+      "grad_norm": 0.3937675654888153,
+      "learning_rate": 0.00018,
+      "loss": 1.2718635559082032,
+      "step": 10
+    },
+    {
+      "epoch": 0.001624497421110344,
+      "grad_norm": 0.15561772882938385,
+      "learning_rate": 0.00019939799331103678,
+      "loss": 0.79568510055542,
+      "step": 20
+    },
+    {
+      "epoch": 0.0024367461316655158,
+      "grad_norm": 0.1349518895149231,
+      "learning_rate": 0.00019872909698996657,
+      "loss": 0.6877449035644532,
+      "step": 30
+    },
+    {
+      "epoch": 0.003248994842220688,
+      "grad_norm": 0.1342487335205078,
+      "learning_rate": 0.00019806020066889633,
+      "loss": 0.7130545616149903,
+      "step": 40
+    },
+    {
+      "epoch": 0.00406124355277586,
+      "grad_norm": 0.11474266648292542,
+      "learning_rate": 0.0001973913043478261,
+      "loss": 0.6835604190826416,
+      "step": 50
+    },
+    {
+      "epoch": 0.0048734922633310316,
+      "grad_norm": 0.10755404084920883,
+      "learning_rate": 0.00019672240802675586,
+      "loss": 0.652743148803711,
+      "step": 60
+    },
+    {
+      "epoch": 0.005685740973886204,
+      "grad_norm": 0.11963178217411041,
+      "learning_rate": 0.00019605351170568562,
+      "loss": 0.6648129940032959,
+      "step": 70
+    },
+    {
+      "epoch": 0.006497989684441376,
+      "grad_norm": 0.0965123176574707,
+      "learning_rate": 0.0001953846153846154,
+      "loss": 0.6699862003326416,
+      "step": 80
+    },
+    {
+      "epoch": 0.007310238394996548,
+      "grad_norm": 0.10343202203512192,
+      "learning_rate": 0.00019471571906354515,
+      "loss": 0.7039784908294677,
+      "step": 90
+    },
+    {
+      "epoch": 0.00812248710555172,
+      "grad_norm": 0.12766548991203308,
+      "learning_rate": 0.00019404682274247492,
+      "loss": 0.6552480697631836,
+      "step": 100
+    },
+    {
+      "epoch": 0.008934735816106891,
+      "grad_norm": 0.10638143867254257,
+      "learning_rate": 0.00019337792642140468,
+      "loss": 0.6422908782958985,
+      "step": 110
+    },
+    {
+      "epoch": 0.009746984526662063,
+      "grad_norm": 0.13318222761154175,
+      "learning_rate": 0.00019270903010033444,
+      "loss": 0.6597362995147705,
+      "step": 120
+    },
+    {
+      "epoch": 0.010559233237217237,
+      "grad_norm": 0.11342291533946991,
+      "learning_rate": 0.0001920401337792642,
+      "loss": 0.6484825611114502,
+      "step": 130
+    },
+    {
+      "epoch": 0.011371481947772408,
+      "grad_norm": 0.10095760971307755,
+      "learning_rate": 0.000191371237458194,
+      "loss": 0.6201153755187988,
+      "step": 140
+    },
+    {
+      "epoch": 0.01218373065832758,
+      "grad_norm": 0.12489528954029083,
+      "learning_rate": 0.00019070234113712376,
+      "loss": 0.6547854900360107,
+      "step": 150
+    },
+    {
+      "epoch": 0.012995979368882752,
+      "grad_norm": 0.10871083289384842,
+      "learning_rate": 0.00019003344481605353,
+      "loss": 0.654566764831543,
+      "step": 160
+    },
+    {
+      "epoch": 0.013808228079437924,
+      "grad_norm": 0.1039392426609993,
+      "learning_rate": 0.0001893645484949833,
+      "loss": 0.649402379989624,
+      "step": 170
+    },
+    {
+      "epoch": 0.014620476789993096,
+      "grad_norm": 0.1328577846288681,
+      "learning_rate": 0.00018869565217391305,
+      "loss": 0.6331918716430665,
+      "step": 180
+    },
+    {
+      "epoch": 0.015432725500548267,
+      "grad_norm": 0.1274302750825882,
+      "learning_rate": 0.00018802675585284282,
+      "loss": 0.6307297706604004,
+      "step": 190
+    },
+    {
+      "epoch": 0.01624497421110344,
+      "grad_norm": 0.12753233313560486,
+      "learning_rate": 0.00018735785953177258,
+      "loss": 0.6115467071533203,
+      "step": 200
+    },
+    {
+      "epoch": 0.01705722292165861,
+      "grad_norm": 0.10285915434360504,
+      "learning_rate": 0.00018668896321070235,
+      "loss": 0.6152299880981446,
+      "step": 210
+    },
+    {
+      "epoch": 0.017869471632213783,
+      "grad_norm": 0.17819221317768097,
+      "learning_rate": 0.0001860200668896321,
+      "loss": 0.6279479026794433,
+      "step": 220
+    },
+    {
+      "epoch": 0.018681720342768954,
+      "grad_norm": 0.11906374990940094,
+      "learning_rate": 0.00018535117056856187,
+      "loss": 0.642233943939209,
+      "step": 230
+    },
+    {
+      "epoch": 0.019493969053324126,
+      "grad_norm": 0.13238145411014557,
+      "learning_rate": 0.00018468227424749164,
+      "loss": 0.6336838245391846,
+      "step": 240
+    },
+    {
+      "epoch": 0.0203062177638793,
+      "grad_norm": 0.11965897679328918,
+      "learning_rate": 0.00018401337792642143,
+      "loss": 0.6414345264434814,
+      "step": 250
+    },
+    {
+      "epoch": 0.021118466474434473,
+      "grad_norm": 0.11781352013349533,
+      "learning_rate": 0.0001833444816053512,
+      "loss": 0.6286166191101075,
+      "step": 260
+    },
+    {
+      "epoch": 0.021930715184989645,
+      "grad_norm": 0.13107237219810486,
+      "learning_rate": 0.00018267558528428096,
+      "loss": 0.6182798385620117,
+      "step": 270
+    },
+    {
+      "epoch": 0.022742963895544817,
+      "grad_norm": 0.11255916953086853,
+      "learning_rate": 0.00018200668896321072,
+      "loss": 0.6299595832824707,
+      "step": 280
+    },
+    {
+      "epoch": 0.02355521260609999,
+      "grad_norm": 0.11259932816028595,
+      "learning_rate": 0.00018133779264214048,
+      "loss": 0.6332510471343994,
+      "step": 290
+    },
+    {
+      "epoch": 0.02436746131665516,
+      "grad_norm": 0.11110201478004456,
+      "learning_rate": 0.00018066889632107025,
+      "loss": 0.6277278900146485,
+      "step": 300
+    },
+    {
+      "epoch": 0.025179710027210332,
+      "grad_norm": 0.11659885942935944,
+      "learning_rate": 0.00018,
+      "loss": 0.6012191772460938,
+      "step": 310
+    },
+    {
+      "epoch": 0.025991958737765504,
+      "grad_norm": 0.11534283310174942,
+      "learning_rate": 0.00017933110367892978,
+      "loss": 0.6344992160797119,
+      "step": 320
+    },
+    {
+      "epoch": 0.026804207448320676,
+      "grad_norm": 0.13291247189044952,
+      "learning_rate": 0.00017866220735785954,
+      "loss": 0.6238264560699462,
+      "step": 330
+    },
+    {
+      "epoch": 0.027616456158875848,
+      "grad_norm": 0.12442389875650406,
+      "learning_rate": 0.0001779933110367893,
+      "loss": 0.6141870975494385,
+      "step": 340
+    },
+    {
+      "epoch": 0.02842870486943102,
+      "grad_norm": 0.10461113601922989,
+      "learning_rate": 0.00017732441471571907,
+      "loss": 0.6277643203735351,
+      "step": 350
+    },
+    {
+      "epoch": 0.02924095357998619,
+      "grad_norm": 0.11059945821762085,
+      "learning_rate": 0.00017665551839464886,
+      "loss": 0.650815773010254,
+      "step": 360
+    },
+    {
+      "epoch": 0.030053202290541363,
+      "grad_norm": 0.1186944767832756,
+      "learning_rate": 0.00017598662207357862,
+      "loss": 0.6423202991485596,
+      "step": 370
+    },
+    {
+      "epoch": 0.030865451001096535,
+      "grad_norm": 0.1306525617837906,
+      "learning_rate": 0.00017531772575250839,
+      "loss": 0.6001749038696289,
+      "step": 380
+    },
+    {
+      "epoch": 0.031677699711651706,
+      "grad_norm": 0.12819500267505646,
+      "learning_rate": 0.00017464882943143815,
+      "loss": 0.6060415744781494,
+      "step": 390
+    },
+    {
+      "epoch": 0.03248994842220688,
+      "grad_norm": 0.13138507306575775,
+      "learning_rate": 0.0001739799331103679,
+      "loss": 0.5925205707550049,
+      "step": 400
+    },
+    {
+      "epoch": 0.03330219713276205,
+      "grad_norm": 0.14968585968017578,
+      "learning_rate": 0.00017331103678929768,
+      "loss": 0.6501868724822998,
+      "step": 410
+    },
+    {
+      "epoch": 0.03411444584331722,
+      "grad_norm": 0.12787474691867828,
+      "learning_rate": 0.00017264214046822744,
+      "loss": 0.6108675956726074,
+      "step": 420
+    },
+    {
+      "epoch": 0.034926694553872394,
+      "grad_norm": 0.13028663396835327,
+      "learning_rate": 0.0001719732441471572,
+      "loss": 0.6132050514221191,
+      "step": 430
+    },
+    {
+      "epoch": 0.035738943264427565,
+      "grad_norm": 0.1314769834280014,
+      "learning_rate": 0.00017130434782608697,
+      "loss": 0.6264569759368896,
+      "step": 440
+    },
+    {
+      "epoch": 0.03655119197498274,
+      "grad_norm": 0.11964884400367737,
+      "learning_rate": 0.00017063545150501673,
+      "loss": 0.6445899486541748,
+      "step": 450
+    },
+    {
+      "epoch": 0.03736344068553791,
+      "grad_norm": 0.11594310402870178,
+      "learning_rate": 0.0001699665551839465,
+      "loss": 0.6022776603698731,
+      "step": 460
+    },
+    {
+      "epoch": 0.03817568939609308,
+      "grad_norm": 0.11167627573013306,
+      "learning_rate": 0.00016929765886287626,
+      "loss": 0.6172833442687988,
+      "step": 470
+    },
+    {
+      "epoch": 0.03898793810664825,
+      "grad_norm": 0.131842702627182,
+      "learning_rate": 0.00016862876254180602,
+      "loss": 0.6316081523895264,
+      "step": 480
+    },
+    {
+      "epoch": 0.039800186817203424,
+      "grad_norm": 0.12949836254119873,
+      "learning_rate": 0.0001679598662207358,
+      "loss": 0.5979058742523193,
+      "step": 490
+    },
+    {
+      "epoch": 0.0406124355277586,
+      "grad_norm": 0.1311161369085312,
+      "learning_rate": 0.00016729096989966555,
+      "loss": 0.6085984230041503,
+      "step": 500
+    },
+    {
+      "epoch": 0.041424684238313775,
+      "grad_norm": 0.11565863341093063,
+      "learning_rate": 0.00016662207357859532,
+      "loss": 0.5864393234252929,
+      "step": 510
+    },
+    {
+      "epoch": 0.04223693294886895,
+      "grad_norm": 0.14647597074508667,
+      "learning_rate": 0.00016595317725752508,
+      "loss": 0.565390157699585,
+      "step": 520
+    },
+    {
+      "epoch": 0.04304918165942412,
+      "grad_norm": 0.11932296305894852,
+      "learning_rate": 0.00016528428093645484,
+      "loss": 0.6000445365905762,
+      "step": 530
+    },
+    {
+      "epoch": 0.04386143036997929,
+      "grad_norm": 0.14222687482833862,
+      "learning_rate": 0.0001646153846153846,
+      "loss": 0.6550194263458252,
+      "step": 540
+    },
+    {
+      "epoch": 0.04467367908053446,
+      "grad_norm": 0.12822918593883514,
+      "learning_rate": 0.00016394648829431437,
+      "loss": 0.6483684062957764,
+      "step": 550
+    },
+    {
+      "epoch": 0.045485927791089634,
+      "grad_norm": 0.13619735836982727,
+      "learning_rate": 0.00016327759197324413,
+      "loss": 0.6203540802001953,
+      "step": 560
+    },
+    {
+      "epoch": 0.046298176501644805,
+      "grad_norm": 0.13233502209186554,
+      "learning_rate": 0.00016260869565217393,
+      "loss": 0.6185849189758301,
+      "step": 570
+    },
+    {
+      "epoch": 0.04711042521219998,
+      "grad_norm": 0.12952451407909393,
+      "learning_rate": 0.0001619397993311037,
+      "loss": 0.5921258449554443,
+      "step": 580
+    },
+    {
+      "epoch": 0.04792267392275515,
+      "grad_norm": 0.12617622315883636,
+      "learning_rate": 0.00016127090301003345,
+      "loss": 0.6221595287322998,
+      "step": 590
+    },
+    {
+      "epoch": 0.04873492263331032,
+      "grad_norm": 0.10956388711929321,
+      "learning_rate": 0.00016060200668896322,
+      "loss": 0.599628210067749,
+      "step": 600
+    },
+    {
+      "epoch": 0.04954717134386549,
+      "grad_norm": 0.11363332718610764,
+      "learning_rate": 0.00015993311036789298,
+      "loss": 0.5865818977355957,
+      "step": 610
+    },
+    {
+      "epoch": 0.050359420054420664,
+      "grad_norm": 0.1252753585577011,
+      "learning_rate": 0.00015926421404682275,
+      "loss": 0.5941249847412109,
+      "step": 620
+    },
+    {
+      "epoch": 0.051171668764975836,
+      "grad_norm": 0.12859514355659485,
+      "learning_rate": 0.0001585953177257525,
+      "loss": 0.598096513748169,
+      "step": 630
+    },
+    {
+      "epoch": 0.05198391747553101,
+      "grad_norm": 0.11355341970920563,
+      "learning_rate": 0.00015792642140468227,
+      "loss": 0.6211743354797363,
+      "step": 640
+    },
+    {
+      "epoch": 0.05279616618608618,
+      "grad_norm": 0.12344721704721451,
+      "learning_rate": 0.00015725752508361204,
+      "loss": 0.5909175395965576,
+      "step": 650
+    },
+    {
+      "epoch": 0.05360841489664135,
+      "grad_norm": 0.1423984318971634,
+      "learning_rate": 0.0001565886287625418,
+      "loss": 0.5645668029785156,
+      "step": 660
+    },
+    {
+      "epoch": 0.05442066360719652,
+      "grad_norm": 0.11847086995840073,
+      "learning_rate": 0.00015591973244147156,
+      "loss": 0.6111773014068603,
+      "step": 670
+    },
+    {
+      "epoch": 0.055232912317751695,
+      "grad_norm": 0.10838636755943298,
+      "learning_rate": 0.00015525083612040136,
+      "loss": 0.598857069015503,
+      "step": 680
+    },
+    {
+      "epoch": 0.05604516102830687,
+      "grad_norm": 0.12422847002744675,
+      "learning_rate": 0.00015458193979933112,
+      "loss": 0.6086232185363769,
+      "step": 690
+    },
+    {
+      "epoch": 0.05685740973886204,
+      "grad_norm": 0.11844707280397415,
+      "learning_rate": 0.00015391304347826088,
+      "loss": 0.6083204269409179,
+      "step": 700
+    },
+    {
+      "epoch": 0.05766965844941721,
+      "grad_norm": 0.12434474378824234,
+      "learning_rate": 0.00015324414715719065,
+      "loss": 0.5938045024871826,
+      "step": 710
+    },
+    {
+      "epoch": 0.05848190715997238,
+      "grad_norm": 0.1373196393251419,
+      "learning_rate": 0.0001525752508361204,
+      "loss": 0.5924835205078125,
+      "step": 720
+    },
+    {
+      "epoch": 0.059294155870527554,
+      "grad_norm": 0.1279742270708084,
+      "learning_rate": 0.00015190635451505017,
+      "loss": 0.5970086574554443,
+      "step": 730
+    },
+    {
+      "epoch": 0.060106404581082726,
+      "grad_norm": 0.1276446133852005,
+      "learning_rate": 0.00015123745819397994,
+      "loss": 0.6073202610015869,
+      "step": 740
+    },
+    {
+      "epoch": 0.0609186532916379,
+      "grad_norm": 0.15001341700553894,
+      "learning_rate": 0.0001505685618729097,
+      "loss": 0.5822910785675048,
+      "step": 750
+    },
+    {
+      "epoch": 0.06173090200219307,
+      "grad_norm": 0.13396278023719788,
+      "learning_rate": 0.00014989966555183947,
+      "loss": 0.5936754226684571,
+      "step": 760
+    },
+    {
+      "epoch": 0.06254315071274824,
+      "grad_norm": 0.21268559992313385,
+      "learning_rate": 0.00014923076923076923,
+      "loss": 0.6138639926910401,
+      "step": 770
+    },
+    {
+      "epoch": 0.06335539942330341,
+      "grad_norm": 0.1419883519411087,
+      "learning_rate": 0.000148561872909699,
+      "loss": 0.6192237854003906,
+      "step": 780
+    },
+    {
+      "epoch": 0.06416764813385858,
+      "grad_norm": 0.12715154886245728,
+      "learning_rate": 0.00014789297658862879,
+      "loss": 0.6032827377319336,
+      "step": 790
+    },
+    {
+      "epoch": 0.06497989684441376,
+      "grad_norm": 0.14222534000873566,
+      "learning_rate": 0.00014722408026755855,
+      "loss": 0.5837327480316162,
+      "step": 800
+    },
+    {
+      "epoch": 0.06579214555496893,
+      "grad_norm": 0.12761105597019196,
+      "learning_rate": 0.0001465551839464883,
+      "loss": 0.5880168437957763,
+      "step": 810
+    },
+    {
+      "epoch": 0.0666043942655241,
+      "grad_norm": 0.13514447212219238,
+      "learning_rate": 0.00014588628762541808,
+      "loss": 0.6178320407867431,
+      "step": 820
+    },
+    {
+      "epoch": 0.06741664297607927,
+      "grad_norm": 0.1156405657529831,
+      "learning_rate": 0.00014521739130434784,
+      "loss": 0.5975133895874023,
+      "step": 830
+    },
+    {
+      "epoch": 0.06822889168663444,
+      "grad_norm": 0.13029585778713226,
+      "learning_rate": 0.0001445484949832776,
+      "loss": 0.6032638549804688,
+      "step": 840
+    },
+    {
+      "epoch": 0.06904114039718962,
+      "grad_norm": 0.12680095434188843,
+      "learning_rate": 0.00014387959866220737,
+      "loss": 0.5651222705841065,
+      "step": 850
+    },
+    {
+      "epoch": 0.06985338910774479,
+      "grad_norm": 0.14011035859584808,
+      "learning_rate": 0.00014321070234113713,
+      "loss": 0.5644700050354003,
+      "step": 860
+    },
+    {
+      "epoch": 0.07066563781829996,
+      "grad_norm": 0.12153138220310211,
+      "learning_rate": 0.0001425418060200669,
+      "loss": 0.5840569019317627,
+      "step": 870
+    },
+    {
+      "epoch": 0.07147788652885513,
+      "grad_norm": 0.13272343575954437,
+      "learning_rate": 0.00014187290969899666,
+      "loss": 0.6429564476013183,
+      "step": 880
+    },
+    {
+      "epoch": 0.0722901352394103,
+      "grad_norm": 0.14595189690589905,
+      "learning_rate": 0.00014120401337792642,
+      "loss": 0.5844541072845459,
+      "step": 890
+    },
+    {
+      "epoch": 0.07310238394996547,
+      "grad_norm": 0.1272500455379486,
+      "learning_rate": 0.00014053511705685621,
+      "loss": 0.6260814189910888,
+      "step": 900
+    },
+    {
+      "epoch": 0.07391463266052065,
+      "grad_norm": 0.1340891271829605,
+      "learning_rate": 0.00013986622073578598,
+      "loss": 0.5867656707763672,
+      "step": 910
+    },
+    {
+      "epoch": 0.07472688137107582,
+      "grad_norm": 0.14307370781898499,
+      "learning_rate": 0.00013919732441471574,
+      "loss": 0.577037000656128,
+      "step": 920
+    },
+    {
+      "epoch": 0.07553913008163099,
+      "grad_norm": 0.15650159120559692,
+      "learning_rate": 0.0001385284280936455,
+      "loss": 0.6175992488861084,
+      "step": 930
+    },
+    {
+      "epoch": 0.07635137879218616,
+      "grad_norm": 0.15327556431293488,
+      "learning_rate": 0.00013785953177257527,
+      "loss": 0.5842644691467285,
+      "step": 940
+    },
+    {
+      "epoch": 0.07716362750274133,
+      "grad_norm": 0.12911345064640045,
+      "learning_rate": 0.00013719063545150503,
+      "loss": 0.5888010025024414,
+      "step": 950
+    },
+    {
+      "epoch": 0.0779758762132965,
+      "grad_norm": 0.16856183111667633,
+      "learning_rate": 0.00013652173913043477,
+      "loss": 0.6148488521575928,
+      "step": 960
+    },
+    {
+      "epoch": 0.07878812492385168,
+      "grad_norm": 0.1216643676161766,
+      "learning_rate": 0.00013585284280936453,
+      "loss": 0.5580620765686035,
+      "step": 970
+    },
+    {
+      "epoch": 0.07960037363440685,
+      "grad_norm": 0.12570665776729584,
+      "learning_rate": 0.0001351839464882943,
+      "loss": 0.5656413078308106,
+      "step": 980
+    },
+    {
+      "epoch": 0.08041262234496203,
+      "grad_norm": 0.1392045021057129,
+      "learning_rate": 0.0001345150501672241,
+      "loss": 0.6019979000091553,
+      "step": 990
+    },
+    {
+      "epoch": 0.0812248710555172,
+      "grad_norm": 0.13696540892124176,
+      "learning_rate": 0.00013384615384615385,
+      "loss": 0.5685174465179443,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08203711976607238,
+      "grad_norm": 0.14112041890621185,
+      "learning_rate": 0.00013317725752508362,
+      "loss": 0.535148286819458,
+      "step": 1010
+    },
+    {
+      "epoch": 0.08284936847662755,
+      "grad_norm": 0.1285763531923294,
+      "learning_rate": 0.00013250836120401338,
+      "loss": 0.5774772644042969,
+      "step": 1020
+    },
+    {
+      "epoch": 0.08366161718718272,
+      "grad_norm": 0.1508583426475525,
+      "learning_rate": 0.00013183946488294314,
+      "loss": 0.5898845195770264,
+      "step": 1030
+    },
+    {
+      "epoch": 0.0844738658977379,
+      "grad_norm": 0.12597988545894623,
+      "learning_rate": 0.0001311705685618729,
+      "loss": 0.584897518157959,
+      "step": 1040
+    },
+    {
+      "epoch": 0.08528611460829306,
+      "grad_norm": 0.12997767329216003,
+      "learning_rate": 0.00013050167224080267,
+      "loss": 0.5317728519439697,
+      "step": 1050
+    },
+    {
+      "epoch": 0.08609836331884824,
+      "grad_norm": 0.16254128515720367,
+      "learning_rate": 0.00012983277591973244,
+      "loss": 0.592738151550293,
+      "step": 1060
+    },
+    {
+      "epoch": 0.08691061202940341,
+      "grad_norm": 0.13483339548110962,
+      "learning_rate": 0.0001291638795986622,
+      "loss": 0.594193696975708,
+      "step": 1070
+    },
+    {
+      "epoch": 0.08772286073995858,
+      "grad_norm": 0.13220393657684326,
+      "learning_rate": 0.00012849498327759196,
+      "loss": 0.5847390174865723,
+      "step": 1080
+    },
+    {
+      "epoch": 0.08853510945051375,
+      "grad_norm": 0.12664461135864258,
+      "learning_rate": 0.00012782608695652173,
+      "loss": 0.5779556274414063,
+      "step": 1090
+    },
+    {
+      "epoch": 0.08934735816106892,
+      "grad_norm": 0.13398249447345734,
+      "learning_rate": 0.00012715719063545152,
+      "loss": 0.5889631271362304,
+      "step": 1100
+    },
+    {
+      "epoch": 0.0901596068716241,
+      "grad_norm": 0.12293358892202377,
+      "learning_rate": 0.00012648829431438128,
+      "loss": 0.564399528503418,
+      "step": 1110
+    },
+    {
+      "epoch": 0.09097185558217927,
+      "grad_norm": 0.12228182703256607,
+      "learning_rate": 0.00012581939799331105,
+      "loss": 0.5679853916168213,
+      "step": 1120
+    },
+    {
+      "epoch": 0.09178410429273444,
+      "grad_norm": 0.1359013170003891,
+      "learning_rate": 0.0001251505016722408,
+      "loss": 0.5924704074859619,
+      "step": 1130
+    },
+    {
+      "epoch": 0.09259635300328961,
+      "grad_norm": 0.13595755398273468,
+      "learning_rate": 0.00012448160535117057,
+      "loss": 0.591594648361206,
+      "step": 1140
+    },
+    {
+      "epoch": 0.09340860171384478,
+      "grad_norm": 0.13194268941879272,
+      "learning_rate": 0.00012381270903010034,
+      "loss": 0.5524315357208252,
+      "step": 1150
+    },
+    {
+      "epoch": 0.09422085042439995,
+      "grad_norm": 0.11575695127248764,
+      "learning_rate": 0.0001231438127090301,
+      "loss": 0.5879955768585206,
+      "step": 1160
+    },
+    {
+      "epoch": 0.09503309913495513,
+      "grad_norm": 0.1535615622997284,
+      "learning_rate": 0.00012247491638795987,
+      "loss": 0.5723489761352539,
+      "step": 1170
+    },
+    {
+      "epoch": 0.0958453478455103,
+      "grad_norm": 0.12228162586688995,
+      "learning_rate": 0.00012180602006688964,
+      "loss": 0.5735376834869385,
+      "step": 1180
+    },
+    {
+      "epoch": 0.09665759655606547,
+      "grad_norm": 0.1566033512353897,
+      "learning_rate": 0.00012113712374581941,
+      "loss": 0.6008642673492431,
+      "step": 1190
+    },
+    {
+      "epoch": 0.09746984526662064,
+      "grad_norm": 0.13811111450195312,
+      "learning_rate": 0.00012046822742474917,
+      "loss": 0.5407697200775147,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09828209397717581,
+      "grad_norm": 0.12737876176834106,
+      "learning_rate": 0.00011979933110367893,
+      "loss": 0.5691880226135254,
+      "step": 1210
+    },
+    {
+      "epoch": 0.09909434268773099,
+      "grad_norm": 0.13377262651920319,
+      "learning_rate": 0.0001191304347826087,
+      "loss": 0.5830073833465577,
+      "step": 1220
+    },
+    {
+      "epoch": 0.09990659139828616,
+      "grad_norm": 0.14325854182243347,
+      "learning_rate": 0.00011846153846153846,
+      "loss": 0.5941594123840332,
+      "step": 1230
+    },
+    {
+      "epoch": 0.10071884010884133,
+      "grad_norm": 0.12132641673088074,
+      "learning_rate": 0.00011779264214046824,
+      "loss": 0.5778646469116211,
+      "step": 1240
+    },
+    {
+      "epoch": 0.1015310888193965,
+      "grad_norm": 0.12815552949905396,
+      "learning_rate": 0.000117123745819398,
+      "loss": 0.5816358089447021,
+      "step": 1250
+    },
+    {
+      "epoch": 0.10234333752995167,
+      "grad_norm": 0.13188569247722626,
+      "learning_rate": 0.00011645484949832777,
+      "loss": 0.5472152233123779,
+      "step": 1260
+    },
+    {
+      "epoch": 0.10315558624050684,
+      "grad_norm": 0.14639215171337128,
+      "learning_rate": 0.00011578595317725753,
+      "loss": 0.5536880493164062,
+      "step": 1270
+    },
+    {
+      "epoch": 0.10396783495106202,
+      "grad_norm": 0.17097154259681702,
+      "learning_rate": 0.0001151170568561873,
+      "loss": 0.5719417095184326,
+      "step": 1280
+    },
+    {
+      "epoch": 0.10478008366161719,
+      "grad_norm": 0.14343994855880737,
+      "learning_rate": 0.00011444816053511706,
+      "loss": 0.5711230278015137,
+      "step": 1290
+    },
+    {
+      "epoch": 0.10559233237217236,
+      "grad_norm": 0.12943314015865326,
+      "learning_rate": 0.00011377926421404684,
+      "loss": 0.569601583480835,
+      "step": 1300
+    },
+    {
+      "epoch": 0.10640458108272753,
+      "grad_norm": 0.14928926527500153,
+      "learning_rate": 0.0001131103678929766,
+      "loss": 0.5634595394134522,
+      "step": 1310
+    },
+    {
+      "epoch": 0.1072168297932827,
+      "grad_norm": 0.13440050184726715,
+      "learning_rate": 0.00011244147157190636,
+      "loss": 0.5858289718627929,
+      "step": 1320
+    },
+    {
+      "epoch": 0.10802907850383787,
+      "grad_norm": 0.14640192687511444,
+      "learning_rate": 0.00011177257525083613,
+      "loss": 0.5742006301879883,
+      "step": 1330
+    },
+    {
+      "epoch": 0.10884132721439305,
+      "grad_norm": 0.13655342161655426,
+      "learning_rate": 0.00011110367892976589,
+      "loss": 0.5680341243743896,
+      "step": 1340
+    },
+    {
+      "epoch": 0.10965357592494822,
+      "grad_norm": 0.14617116749286652,
+      "learning_rate": 0.00011043478260869567,
+      "loss": 0.521897840499878,
+      "step": 1350
+    },
+    {
+      "epoch": 0.11046582463550339,
+      "grad_norm": 0.12586890161037445,
+      "learning_rate": 0.00010976588628762543,
+      "loss": 0.5649400234222413,
+      "step": 1360
+    },
+    {
+      "epoch": 0.11127807334605856,
+      "grad_norm": 0.13755163550376892,
+      "learning_rate": 0.0001090969899665552,
+      "loss": 0.5622130870819092,
+      "step": 1370
+    },
+    {
+      "epoch": 0.11209032205661373,
+      "grad_norm": 0.1405872404575348,
+      "learning_rate": 0.00010842809364548496,
+      "loss": 0.5692743778228759,
+      "step": 1380
+    },
+    {
+      "epoch": 0.1129025707671689,
+      "grad_norm": 0.12281648069620132,
+      "learning_rate": 0.00010775919732441473,
+      "loss": 0.5326085567474366,
+      "step": 1390
+    },
+    {
+      "epoch": 0.11371481947772408,
+      "grad_norm": 0.1537039428949356,
+      "learning_rate": 0.00010709030100334449,
+      "loss": 0.5351646900177002,
+      "step": 1400
+    },
+    {
+      "epoch": 0.11452706818827925,
+      "grad_norm": 0.14019237458705902,
+      "learning_rate": 0.00010642140468227427,
+      "loss": 0.5573231220245362,
+      "step": 1410
+    },
+    {
+      "epoch": 0.11533931689883442,
+      "grad_norm": 0.13344921171665192,
+      "learning_rate": 0.00010575250836120403,
+      "loss": 0.5791097640991211,
+      "step": 1420
+    },
+    {
+      "epoch": 0.11615156560938959,
+      "grad_norm": 0.15044879913330078,
+      "learning_rate": 0.0001050836120401338,
+      "loss": 0.5930334091186523,
+      "step": 1430
+    },
+    {
+      "epoch": 0.11696381431994476,
+      "grad_norm": 0.12816403806209564,
+      "learning_rate": 0.00010441471571906356,
+      "loss": 0.5483273983001709,
+      "step": 1440
+    },
+    {
+      "epoch": 0.11777606303049994,
+      "grad_norm": 0.1419902890920639,
+      "learning_rate": 0.00010374581939799332,
+      "loss": 0.543612003326416,
+      "step": 1450
+    },
+    {
+      "epoch": 0.11858831174105511,
+      "grad_norm": 0.1339890956878662,
+      "learning_rate": 0.00010307692307692307,
+      "loss": 0.5436506271362305,
+      "step": 1460
+    },
+    {
+      "epoch": 0.11940056045161028,
+      "grad_norm": 0.1383645087480545,
+      "learning_rate": 0.00010240802675585284,
+      "loss": 0.5666821002960205,
+      "step": 1470
+    },
+    {
+      "epoch": 0.12021280916216545,
+      "grad_norm": 0.1582079976797104,
+      "learning_rate": 0.0001017391304347826,
+      "loss": 0.626584529876709,
+      "step": 1480
+    },
+    {
+      "epoch": 0.12102505787272062,
+      "grad_norm": 0.1362374722957611,
+      "learning_rate": 0.00010107023411371236,
+      "loss": 0.525059700012207,
+      "step": 1490
+    },
+    {
+      "epoch": 0.1218373065832758,
+      "grad_norm": 0.13763943314552307,
+      "learning_rate": 0.00010040133779264214,
+      "loss": 0.5590079307556153,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12264955529383097,
+      "grad_norm": 0.1370711624622345,
+      "learning_rate": 9.973244147157192e-05,
+      "loss": 0.5663545608520508,
+      "step": 1510
+    },
+    {
+      "epoch": 0.12346180400438614,
+      "grad_norm": 0.1474352777004242,
+      "learning_rate": 9.906354515050168e-05,
+      "loss": 0.5713413715362549,
+      "step": 1520
+    },
+    {
+      "epoch": 0.12427405271494131,
+      "grad_norm": 0.16058789193630219,
+      "learning_rate": 9.839464882943145e-05,
+      "loss": 0.5543087482452392,
+      "step": 1530
+    },
+    {
+      "epoch": 0.12508630142549648,
+      "grad_norm": 0.1326485127210617,
+      "learning_rate": 9.772575250836121e-05,
+      "loss": 0.5147572517395019,
+      "step": 1540
+    },
+    {
+      "epoch": 0.12589855013605167,
+      "grad_norm": 0.13315606117248535,
+      "learning_rate": 9.705685618729097e-05,
+      "loss": 0.5362074375152588,
+      "step": 1550
+    },
+    {
+      "epoch": 0.12671079884660683,
+      "grad_norm": 0.1448029726743698,
+      "learning_rate": 9.638795986622075e-05,
+      "loss": 0.5359432220458984,
+      "step": 1560
+    },
+    {
+      "epoch": 0.127523047557162,
+      "grad_norm": 0.13855981826782227,
+      "learning_rate": 9.571906354515052e-05,
+      "loss": 0.6001797199249268,
+      "step": 1570
+    },
+    {
+      "epoch": 0.12833529626771717,
+      "grad_norm": 0.14771045744419098,
+      "learning_rate": 9.505016722408028e-05,
+      "loss": 0.5607345581054688,
+      "step": 1580
+    },
+    {
+      "epoch": 0.12914754497827236,
+      "grad_norm": 0.13563105463981628,
+      "learning_rate": 9.438127090301003e-05,
+      "loss": 0.544070816040039,
+      "step": 1590
+    },
+    {
+      "epoch": 0.1299597936888275,
+      "grad_norm": 0.14828725159168243,
+      "learning_rate": 9.371237458193979e-05,
+      "loss": 0.5783030986785889,
+      "step": 1600
+    },
+    {
+      "epoch": 0.1307720423993827,
+      "grad_norm": 0.12361393123865128,
+      "learning_rate": 9.304347826086957e-05,
+      "loss": 0.5871748447418212,
+      "step": 1610
+    },
+    {
+      "epoch": 0.13158429110993786,
+      "grad_norm": 0.14219100773334503,
+      "learning_rate": 9.237458193979933e-05,
+      "loss": 0.5626397609710694,
+      "step": 1620
+    },
+    {
+      "epoch": 0.13239653982049304,
+      "grad_norm": 0.14112858474254608,
+      "learning_rate": 9.17056856187291e-05,
+      "loss": 0.5763169765472412,
+      "step": 1630
+    },
+    {
+      "epoch": 0.1332087885310482,
+      "grad_norm": 0.13030873239040375,
+      "learning_rate": 9.103678929765886e-05,
+      "loss": 0.5603885650634766,
+      "step": 1640
+    },
+    {
+      "epoch": 0.13402103724160339,
+      "grad_norm": 0.15187381207942963,
+      "learning_rate": 9.036789297658863e-05,
+      "loss": 0.5786955833435059,
+      "step": 1650
+    },
+    {
+      "epoch": 0.13483328595215854,
+      "grad_norm": 0.13238519430160522,
+      "learning_rate": 8.96989966555184e-05,
+      "loss": 0.5465178489685059,
+      "step": 1660
+    },
+    {
+      "epoch": 0.13564553466271373,
+      "grad_norm": 0.15359745919704437,
+      "learning_rate": 8.903010033444817e-05,
+      "loss": 0.5435216426849365,
+      "step": 1670
+    },
+    {
+      "epoch": 0.1364577833732689,
+      "grad_norm": 0.1419076770544052,
+      "learning_rate": 8.836120401337793e-05,
+      "loss": 0.5662240982055664,
+      "step": 1680
+    },
+    {
+      "epoch": 0.13727003208382407,
+      "grad_norm": 0.1322913020849228,
+      "learning_rate": 8.76923076923077e-05,
+      "loss": 0.5744258880615234,
+      "step": 1690
+    },
+    {
+      "epoch": 0.13808228079437923,
+      "grad_norm": 0.1452193707227707,
+      "learning_rate": 8.702341137123746e-05,
+      "loss": 0.5542884826660156,
+      "step": 1700
+    },
+    {
+      "epoch": 0.13889452950493442,
+      "grad_norm": 0.14488045871257782,
+      "learning_rate": 8.635451505016722e-05,
+      "loss": 0.5822937965393067,
+      "step": 1710
+    },
+    {
+      "epoch": 0.13970677821548957,
+      "grad_norm": 0.1601410210132599,
+      "learning_rate": 8.5685618729097e-05,
+      "loss": 0.5679747581481933,
+      "step": 1720
+    },
+    {
+      "epoch": 0.14051902692604476,
+      "grad_norm": 0.14050708711147308,
+      "learning_rate": 8.501672240802676e-05,
+      "loss": 0.5476060390472413,
+      "step": 1730
+    },
+    {
+      "epoch": 0.14133127563659992,
+      "grad_norm": 0.13699111342430115,
+      "learning_rate": 8.434782608695653e-05,
+      "loss": 0.5368577480316162,
+      "step": 1740
+    },
+    {
+      "epoch": 0.1421435243471551,
+      "grad_norm": 0.15727275609970093,
+      "learning_rate": 8.367892976588629e-05,
+      "loss": 0.5533368110656738,
+      "step": 1750
+    },
+    {
+      "epoch": 0.14295577305771026,
+      "grad_norm": 0.1250455528497696,
+      "learning_rate": 8.301003344481606e-05,
+      "loss": 0.5124822616577148,
+      "step": 1760
+    },
+    {
+      "epoch": 0.14376802176826545,
+      "grad_norm": 0.14270517230033875,
+      "learning_rate": 8.234113712374582e-05,
+      "loss": 0.4951145648956299,
+      "step": 1770
+    },
+    {
+      "epoch": 0.1445802704788206,
+      "grad_norm": 0.1323961317539215,
+      "learning_rate": 8.16722408026756e-05,
+      "loss": 0.5427422046661377,
+      "step": 1780
+    },
+    {
+      "epoch": 0.1453925191893758,
+      "grad_norm": 0.12723498046398163,
+      "learning_rate": 8.100334448160536e-05,
+      "loss": 0.5693273067474365,
+      "step": 1790
+    },
+    {
+      "epoch": 0.14620476789993095,
+      "grad_norm": 0.16872361302375793,
+      "learning_rate": 8.033444816053512e-05,
+      "loss": 0.5806541919708252,
+      "step": 1800
+    },
+    {
+      "epoch": 0.14701701661048613,
+      "grad_norm": 0.1746852695941925,
+      "learning_rate": 7.966555183946489e-05,
+      "loss": 0.5519280910491944,
+      "step": 1810
+    },
+    {
+      "epoch": 0.1478292653210413,
+      "grad_norm": 0.1339474767446518,
+      "learning_rate": 7.899665551839465e-05,
+      "loss": 0.5633978366851806,
+      "step": 1820
+    },
+    {
+      "epoch": 0.14864151403159648,
+      "grad_norm": 0.15579932928085327,
+      "learning_rate": 7.832775919732442e-05,
+      "loss": 0.5654179573059082,
+      "step": 1830
+    },
+    {
+      "epoch": 0.14945376274215164,
+      "grad_norm": 0.1376143991947174,
+      "learning_rate": 7.765886287625418e-05,
+      "loss": 0.5682297229766846,
+      "step": 1840
+    },
+    {
+      "epoch": 0.15026601145270682,
+      "grad_norm": 0.13763904571533203,
+      "learning_rate": 7.698996655518394e-05,
+      "loss": 0.5459368228912354,
+      "step": 1850
+    },
+    {
+      "epoch": 0.15107826016326198,
+      "grad_norm": 0.1451306790113449,
+      "learning_rate": 7.632107023411371e-05,
+      "loss": 0.5715532302856445,
+      "step": 1860
+    },
+    {
+      "epoch": 0.15189050887381716,
+      "grad_norm": 0.13482438027858734,
+      "learning_rate": 7.565217391304347e-05,
+      "loss": 0.5574208259582519,
+      "step": 1870
+    },
+    {
+      "epoch": 0.15270275758437232,
+      "grad_norm": 0.1368977129459381,
+      "learning_rate": 7.498327759197325e-05,
+      "loss": 0.5740077018737793,
+      "step": 1880
+    },
+    {
+      "epoch": 0.1535150062949275,
+      "grad_norm": 0.15516723692417145,
+      "learning_rate": 7.431438127090301e-05,
+      "loss": 0.5351629734039307,
+      "step": 1890
+    },
+    {
+      "epoch": 0.15432725500548267,
+      "grad_norm": 0.14029201865196228,
+      "learning_rate": 7.364548494983278e-05,
+      "loss": 0.5698582649230957,
+      "step": 1900
+    },
+    {
+      "epoch": 0.15513950371603785,
+      "grad_norm": 0.14146295189857483,
+      "learning_rate": 7.297658862876254e-05,
+      "loss": 0.5102039813995362,
+      "step": 1910
+    },
+    {
+      "epoch": 0.155951752426593,
+      "grad_norm": 0.13546870648860931,
+      "learning_rate": 7.23076923076923e-05,
+      "loss": 0.5165145397186279,
+      "step": 1920
+    },
+    {
+      "epoch": 0.1567640011371482,
+      "grad_norm": 0.14060750603675842,
+      "learning_rate": 7.163879598662208e-05,
+      "loss": 0.5620519161224365,
+      "step": 1930
+    },
+    {
+      "epoch": 0.15757624984770335,
+      "grad_norm": 0.14041195809841156,
+      "learning_rate": 7.096989966555185e-05,
+      "loss": 0.5427090167999268,
+      "step": 1940
+    },
+    {
+      "epoch": 0.15838849855825854,
+      "grad_norm": 0.13412784039974213,
+      "learning_rate": 7.030100334448161e-05,
+      "loss": 0.576103687286377,
+      "step": 1950
+    },
+    {
+      "epoch": 0.1592007472688137,
+      "grad_norm": 0.15830129384994507,
+      "learning_rate": 6.963210702341137e-05,
+      "loss": 0.5335178852081299,
+      "step": 1960
+    },
+    {
+      "epoch": 0.16001299597936888,
+      "grad_norm": 0.14285124838352203,
+      "learning_rate": 6.896321070234114e-05,
+      "loss": 0.5639289379119873,
+      "step": 1970
+    },
+    {
+      "epoch": 0.16082524468992407,
+      "grad_norm": 0.14816631376743317,
+      "learning_rate": 6.82943143812709e-05,
+      "loss": 0.5724262237548828,
+      "step": 1980
+    },
+    {
+      "epoch": 0.16163749340047923,
+      "grad_norm": 0.1573079526424408,
+      "learning_rate": 6.762541806020068e-05,
+      "loss": 0.5576060295104981,
+      "step": 1990
+    },
+    {
+      "epoch": 0.1624497421110344,
+      "grad_norm": 0.12953346967697144,
+      "learning_rate": 6.695652173913044e-05,
+      "loss": 0.5110755443572998,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3396287021439795e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3324b919dea632cc45c535989e075b3980c20273cb5208547417e5758ffe6fa9
+size 5585