Upload folder using huggingface_hub

README.md

@@ -204,4 +204,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.20.0
+- PEFT 0.21.0

adapter_config.json

@@ -12,6 +12,7 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "kasa_config": null,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
@@ -25,17 +26,17 @@
   "modules_to_save": null,
   "monteclora_config": null,
   "peft_type": "LORA",
-  "peft_version": "0.20.0",
+  "peft_version": "0.21.0",
   "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "v_proj",
+    "up_proj",
     "o_proj",
     "q_proj",
-    "up_proj",
+    "k_proj",
     "down_proj",
     "gate_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9b7a7ec166f087837439d434741fdf1ce77f6e2ba34a5fb2cd595bf6e1b46d8
+oid sha256:35013cd0735cf2635d1d3b5e58b19417211fb610c11e92ceb933dd5185ffcfde
 size 73911112

checkpoint-1600/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.21.0

checkpoint-1600/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoint-1600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c861d369d0cdb908eeec0816ea7385e5a6cd05c27723a35302871c611f9c6b
+size 73911112

checkpoint-1600/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- 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-1600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d69b707c2ae8409acadf79b331cd6f78e2f4e55686a0fe4e357434b3d0bfa8
+size 148048187

checkpoint-1600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73dfa230d7b4bd3b7fddaa62a7b067b9e345a87c2b7e57037afb75d0ec7fa287
+size 14645

checkpoint-1600/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e4420338904222790575638e536e5d59f25756f58070a9dfc3e73602e7fbef5
+size 1383

checkpoint-1600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af815d5bc24ad8df1fbdaab50f8d1cbaf8b220f09946238308c5da2973fe1575
+size 1465

checkpoint-1600/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f55e63353d3d978b390d346bae531be8b83bc9532c0be500d62b7253aa4c595
+size 11421991

checkpoint-1600/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1600/trainer_state.json

@@ -0,0 +1,1154 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4505747126436783,
+  "eval_steps": 500,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01532567049808429,
+      "grad_norm": 1.7315932512283325,
+      "learning_rate": 3.461538461538462e-05,
+      "loss": 1.2715375900268555,
+      "step": 10
+    },
+    {
+      "epoch": 0.03065134099616858,
+      "grad_norm": 0.8982687592506409,
+      "learning_rate": 7.307692307692307e-05,
+      "loss": 0.7381579399108886,
+      "step": 20
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.30448803305625916,
+      "learning_rate": 0.00011153846153846154,
+      "loss": 0.3694685220718384,
+      "step": 30
+    },
+    {
+      "epoch": 0.06130268199233716,
+      "grad_norm": 0.235411137342453,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.33196756839752195,
+      "step": 40
+    },
+    {
+      "epoch": 0.07662835249042145,
+      "grad_norm": 0.24934549629688263,
+      "learning_rate": 0.00018846153846153847,
+      "loss": 0.36157524585723877,
+      "step": 50
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.23371638357639313,
+      "learning_rate": 0.0001999916134297838,
+      "loss": 0.3544674634933472,
+      "step": 60
+    },
+    {
+      "epoch": 0.10727969348659004,
+      "grad_norm": 0.25476178526878357,
+      "learning_rate": 0.00019995053973750825,
+      "loss": 0.3414992570877075,
+      "step": 70
+    },
+    {
+      "epoch": 0.12260536398467432,
+      "grad_norm": 0.25480854511260986,
+      "learning_rate": 0.00019987525257483818,
+      "loss": 0.3117872476577759,
+      "step": 80
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.2153773307800293,
+      "learning_rate": 0.00019976577771287128,
+      "loss": 0.319127631187439,
+      "step": 90
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "grad_norm": 0.2098936140537262,
+      "learning_rate": 0.00019962215262529155,
+      "loss": 0.3204960823059082,
+      "step": 100
+    },
+    {
+      "epoch": 0.1685823754789272,
+      "grad_norm": 0.24129652976989746,
+      "learning_rate": 0.0001994444264755422,
+      "loss": 0.30017311573028566,
+      "step": 110
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.20696483552455902,
+      "learning_rate": 0.0001992326600999967,
+      "loss": 0.31872761249542236,
+      "step": 120
+    },
+    {
+      "epoch": 0.19923371647509577,
+      "grad_norm": 0.2713371813297272,
+      "learning_rate": 0.0001989869259871342,
+      "loss": 0.30037286281585696,
+      "step": 130
+    },
+    {
+      "epoch": 0.21455938697318008,
+      "grad_norm": 0.1990661919116974,
+      "learning_rate": 0.0001987073082527266,
+      "loss": 0.3093862771987915,
+      "step": 140
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.25070610642433167,
+      "learning_rate": 0.00019839390261104515,
+      "loss": 0.31338260173797605,
+      "step": 150
+    },
+    {
+      "epoch": 0.24521072796934865,
+      "grad_norm": 0.25297442078590393,
+      "learning_rate": 0.00019804681634209725,
+      "loss": 0.3277841329574585,
+      "step": 160
+    },
+    {
+      "epoch": 0.26053639846743293,
+      "grad_norm": 0.20755986869335175,
+      "learning_rate": 0.00019766616825490408,
+      "loss": 0.30395307540893557,
+      "step": 170
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.26024317741394043,
+      "learning_rate": 0.00019725208864683166,
+      "loss": 0.3044783592224121,
+      "step": 180
+    },
+    {
+      "epoch": 0.29118773946360155,
+      "grad_norm": 0.19299627840518951,
+      "learning_rate": 0.0001968047192589896,
+      "loss": 0.3172396898269653,
+      "step": 190
+    },
+    {
+      "epoch": 0.3065134099616858,
+      "grad_norm": 0.2235356867313385,
+      "learning_rate": 0.00019632421322771264,
+      "loss": 0.30823068618774413,
+      "step": 200
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.22727671265602112,
+      "learning_rate": 0.00019581073503214128,
+      "loss": 0.3229329586029053,
+      "step": 210
+    },
+    {
+      "epoch": 0.3371647509578544,
+      "grad_norm": 0.20518285036087036,
+      "learning_rate": 0.0001952644604379202,
+      "loss": 0.30754120349884034,
+      "step": 220
+    },
+    {
+      "epoch": 0.3524904214559387,
+      "grad_norm": 0.18881909549236298,
+      "learning_rate": 0.0001946855764370326,
+      "loss": 0.3070927619934082,
+      "step": 230
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.1794276088476181,
+      "learning_rate": 0.0001940742811837924,
+      "loss": 0.2929072380065918,
+      "step": 240
+    },
+    {
+      "epoch": 0.3831417624521073,
+      "grad_norm": 0.21480266749858856,
+      "learning_rate": 0.00019343078392701512,
+      "loss": 0.3045187473297119,
+      "step": 250
+    },
+    {
+      "epoch": 0.39846743295019155,
+      "grad_norm": 0.20736214518547058,
+      "learning_rate": 0.00019275530493839118,
+      "loss": 0.2853532791137695,
+      "step": 260
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.2377932071685791,
+      "learning_rate": 0.00019204807543708597,
+      "loss": 0.31055545806884766,
+      "step": 270
+    },
+    {
+      "epoch": 0.42911877394636017,
+      "grad_norm": 0.2220766693353653,
+      "learning_rate": 0.0001913093375105926,
+      "loss": 0.30534508228302004,
+      "step": 280
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.1769602745771408,
+      "learning_rate": 0.00019053934403186448,
+      "loss": 0.3000555276870728,
+      "step": 290
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.1880396157503128,
+      "learning_rate": 0.00018973835857275586,
+      "loss": 0.2925630331039429,
+      "step": 300
+    },
+    {
+      "epoch": 0.47509578544061304,
+      "grad_norm": 0.20192766189575195,
+      "learning_rate": 0.00018890665531380007,
+      "loss": 0.30003533363342283,
+      "step": 310
+    },
+    {
+      "epoch": 0.4904214559386973,
+      "grad_norm": 0.18706700205802917,
+      "learning_rate": 0.00018804451895035643,
+      "loss": 0.3043027639389038,
+      "step": 320
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.24098548293113708,
+      "learning_rate": 0.00018715224459515796,
+      "loss": 0.2952123641967773,
+      "step": 330
+    },
+    {
+      "epoch": 0.5210727969348659,
+      "grad_norm": 0.18655002117156982,
+      "learning_rate": 0.00018623013767729303,
+      "loss": 0.2932705879211426,
+      "step": 340
+    },
+    {
+      "epoch": 0.5363984674329502,
+      "grad_norm": 0.19691458344459534,
+      "learning_rate": 0.00018527851383765578,
+      "loss": 0.31863603591918943,
+      "step": 350
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.18485110998153687,
+      "learning_rate": 0.00018429769882090104,
+      "loss": 0.2955839395523071,
+      "step": 360
+    },
+    {
+      "epoch": 0.5670498084291188,
+      "grad_norm": 0.23259525001049042,
+      "learning_rate": 0.00018328802836394055,
+      "loss": 0.3062273979187012,
+      "step": 370
+    },
+    {
+      "epoch": 0.5823754789272031,
+      "grad_norm": 0.1704971045255661,
+      "learning_rate": 0.00018224984808101887,
+      "loss": 0.28621697425842285,
+      "step": 380
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.206704780459404,
+      "learning_rate": 0.00018118351334540833,
+      "loss": 0.28846466541290283,
+      "step": 390
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "grad_norm": 0.20759014785289764,
+      "learning_rate": 0.00018008938916776323,
+      "loss": 0.30964126586914065,
+      "step": 400
+    },
+    {
+      "epoch": 0.6283524904214559,
+      "grad_norm": 0.1952156275510788,
+      "learning_rate": 0.00017896785007117524,
+      "loss": 0.306485652923584,
+      "step": 410
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.16880711913108826,
+      "learning_rate": 0.0001778192799629727,
+      "loss": 0.3217456579208374,
+      "step": 420
+    },
+    {
+      "epoch": 0.6590038314176245,
+      "grad_norm": 0.2303844839334488,
+      "learning_rate": 0.00017664407200330767,
+      "loss": 0.28161351680755614,
+      "step": 430
+    },
+    {
+      "epoch": 0.6743295019157088,
+      "grad_norm": 0.2218875139951706,
+      "learning_rate": 0.00017544262847057532,
+      "loss": 0.2977366209030151,
+      "step": 440
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.20623792707920074,
+      "learning_rate": 0.00017421536062371286,
+      "loss": 0.29798321723937987,
+      "step": 450
+    },
+    {
+      "epoch": 0.7049808429118773,
+      "grad_norm": 0.22805136442184448,
+      "learning_rate": 0.00017296268856142365,
+      "loss": 0.2869698524475098,
+      "step": 460
+    },
+    {
+      "epoch": 0.7203065134099617,
+      "grad_norm": 0.19344043731689453,
+      "learning_rate": 0.00017168504107837582,
+      "loss": 0.2964784145355225,
+      "step": 470
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.2286471724510193,
+      "learning_rate": 0.00017038285551842412,
+      "loss": 0.302842903137207,
+      "step": 480
+    },
+    {
+      "epoch": 0.7509578544061303,
+      "grad_norm": 0.19522379338741302,
+      "learning_rate": 0.00016905657762490548,
+      "loss": 0.3244823694229126,
+      "step": 490
+    },
+    {
+      "epoch": 0.7662835249042146,
+      "grad_norm": 0.1601998209953308,
+      "learning_rate": 0.00016770666138805904,
+      "loss": 0.2811170816421509,
+      "step": 500
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.16715656220912933,
+      "learning_rate": 0.0001663335688896237,
+      "loss": 0.2751513719558716,
+      "step": 510
+    },
+    {
+      "epoch": 0.7969348659003831,
+      "grad_norm": 0.19661696255207062,
+      "learning_rate": 0.00016493777014466563,
+      "loss": 0.3170422077178955,
+      "step": 520
+    },
+    {
+      "epoch": 0.8122605363984674,
+      "grad_norm": 0.18826834857463837,
+      "learning_rate": 0.0001635197429406901,
+      "loss": 0.2818011283874512,
+      "step": 530
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.18041561543941498,
+      "learning_rate": 0.00016207997267409313,
+      "loss": 0.30449423789978025,
+      "step": 540
+    },
+    {
+      "epoch": 0.842911877394636,
+      "grad_norm": 0.1955738365650177,
+      "learning_rate": 0.00016061895218400806,
+      "loss": 0.2753497362136841,
+      "step": 550
+    },
+    {
+      "epoch": 0.8582375478927203,
+      "grad_norm": 0.19417400658130646,
+      "learning_rate": 0.0001591371815836051,
+      "loss": 0.28362064361572265,
+      "step": 560
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.1948927491903305,
+      "learning_rate": 0.00015763516808890024,
+      "loss": 0.2855699062347412,
+      "step": 570
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.18820644915103912,
+      "learning_rate": 0.00015611342584513342,
+      "loss": 0.28289546966552737,
+      "step": 580
+    },
+    {
+      "epoch": 0.9042145593869731,
+      "grad_norm": 0.18016715347766876,
+      "learning_rate": 0.00015457247575077445,
+      "loss": 0.29960951805114744,
+      "step": 590
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.22913143038749695,
+      "learning_rate": 0.0001530128452792174,
+      "loss": 0.28281118869781496,
+      "step": 600
+    },
+    {
+      "epoch": 0.9348659003831418,
+      "grad_norm": 0.20966900885105133,
+      "learning_rate": 0.00015143506829822426,
+      "loss": 0.30697131156921387,
+      "step": 610
+    },
+    {
+      "epoch": 0.9501915708812261,
+      "grad_norm": 0.2458924800157547,
+      "learning_rate": 0.00014983968488718006,
+      "loss": 0.30470201969146726,
+      "step": 620
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.18874205648899078,
+      "learning_rate": 0.00014822724115222128,
+      "loss": 0.30251691341400144,
+      "step": 630
+    },
+    {
+      "epoch": 0.9808429118773946,
+      "grad_norm": 0.22530531883239746,
+      "learning_rate": 0.00014659828903930178,
+      "loss": 0.29744977951049806,
+      "step": 640
+    },
+    {
+      "epoch": 0.9961685823754789,
+      "grad_norm": 0.20111751556396484,
+      "learning_rate": 0.00014495338614525926,
+      "loss": 0.28247039318084716,
+      "step": 650
+    },
+    {
+      "epoch": 1.010727969348659,
+      "grad_norm": 0.17702056467533112,
+      "learning_rate": 0.00014329309552694783,
+      "loss": 0.2753941774368286,
+      "step": 660
+    },
+    {
+      "epoch": 1.0260536398467432,
+      "grad_norm": 0.17669467628002167,
+      "learning_rate": 0.00014161798550850124,
+      "loss": 0.2545931816101074,
+      "step": 670
+    },
+    {
+      "epoch": 1.0413793103448277,
+      "grad_norm": 0.1835271567106247,
+      "learning_rate": 0.00013992862948679333,
+      "loss": 0.24901304244995118,
+      "step": 680
+    },
+    {
+      "epoch": 1.0567049808429119,
+      "grad_norm": 0.19968923926353455,
+      "learning_rate": 0.00013822560573516194,
+      "loss": 0.27475411891937257,
+      "step": 690
+    },
+    {
+      "epoch": 1.072030651340996,
+      "grad_norm": 0.17976751923561096,
+      "learning_rate": 0.00013650949720546372,
+      "loss": 0.2584954023361206,
+      "step": 700
+    },
+    {
+      "epoch": 1.0873563218390805,
+      "grad_norm": 0.19866906106472015,
+      "learning_rate": 0.00013478089132852716,
+      "loss": 0.26185197830200196,
+      "step": 710
+    },
+    {
+      "epoch": 1.1026819923371647,
+      "grad_norm": 0.2139822244644165,
+      "learning_rate": 0.0001330403798130729,
+      "loss": 0.2664598226547241,
+      "step": 720
+    },
+    {
+      "epoch": 1.118007662835249,
+      "grad_norm": 0.1918357014656067,
+      "learning_rate": 0.00013128855844316944,
+      "loss": 0.26914339065551757,
+      "step": 730
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.21598224341869354,
+      "learning_rate": 0.00012952602687429362,
+      "loss": 0.24881536960601808,
+      "step": 740
+    },
+    {
+      "epoch": 1.1486590038314177,
+      "grad_norm": 0.16682575643062592,
+      "learning_rate": 0.00012775338842806647,
+      "loss": 0.2527227163314819,
+      "step": 750
+    },
+    {
+      "epoch": 1.163984674329502,
+      "grad_norm": 0.18836885690689087,
+      "learning_rate": 0.00012597124988573353,
+      "loss": 0.2735306739807129,
+      "step": 760
+    },
+    {
+      "epoch": 1.1793103448275861,
+      "grad_norm": 0.20422716438770294,
+      "learning_rate": 0.00012418022128046142,
+      "loss": 0.2547746181488037,
+      "step": 770
+    },
+    {
+      "epoch": 1.1946360153256705,
+      "grad_norm": 0.18123748898506165,
+      "learning_rate": 0.00012238091568852086,
+      "loss": 0.2550168037414551,
+      "step": 780
+    },
+    {
+      "epoch": 1.2099616858237547,
+      "grad_norm": 0.1850244104862213,
+      "learning_rate": 0.00012057394901942834,
+      "loss": 0.2556851148605347,
+      "step": 790
+    },
+    {
+      "epoch": 1.2252873563218392,
+      "grad_norm": 0.18734942376613617,
+      "learning_rate": 0.00011875993980511773,
+      "loss": 0.25217125415802,
+      "step": 800
+    },
+    {
+      "epoch": 1.2406130268199234,
+      "grad_norm": 0.25744232535362244,
+      "learning_rate": 0.00011693950898821442,
+      "loss": 0.25321738719940184,
+      "step": 810
+    },
+    {
+      "epoch": 1.2559386973180078,
+      "grad_norm": 0.24140717089176178,
+      "learning_rate": 0.00011511327970948398,
+      "loss": 0.2695934295654297,
+      "step": 820
+    },
+    {
+      "epoch": 1.271264367816092,
+      "grad_norm": 0.19622239470481873,
+      "learning_rate": 0.00011328187709452884,
+      "loss": 0.25709664821624756,
+      "step": 830
+    },
+    {
+      "epoch": 1.2865900383141762,
+      "grad_norm": 0.18637792766094208,
+      "learning_rate": 0.00011144592803980507,
+      "loss": 0.25869600772857665,
+      "step": 840
+    },
+    {
+      "epoch": 1.3019157088122606,
+      "grad_norm": 0.19393154978752136,
+      "learning_rate": 0.00010960606099803339,
+      "loss": 0.2554497003555298,
+      "step": 850
+    },
+    {
+      "epoch": 1.3172413793103448,
+      "grad_norm": 0.2453709989786148,
+      "learning_rate": 0.0001077629057630771,
+      "loss": 0.26648812294006347,
+      "step": 860
+    },
+    {
+      "epoch": 1.332567049808429,
+      "grad_norm": 0.25964638590812683,
+      "learning_rate": 0.00010591709325436123,
+      "loss": 0.26240499019622804,
+      "step": 870
+    },
+    {
+      "epoch": 1.3478927203065134,
+      "grad_norm": 0.21236255764961243,
+      "learning_rate": 0.00010406925530090625,
+      "loss": 0.26952788829803465,
+      "step": 880
+    },
+    {
+      "epoch": 1.3632183908045978,
+      "grad_norm": 0.20102430880069733,
+      "learning_rate": 0.00010222002442505056,
+      "loss": 0.2485269546508789,
+      "step": 890
+    },
+    {
+      "epoch": 1.378544061302682,
+      "grad_norm": 0.23220829665660858,
+      "learning_rate": 0.00010037003362593544,
+      "loss": 0.2720418214797974,
+      "step": 900
+    },
+    {
+      "epoch": 1.3938697318007662,
+      "grad_norm": 0.21482332050800323,
+      "learning_rate": 9.85199161628269e-05,
+      "loss": 0.24709177017211914,
+      "step": 910
+    },
+    {
+      "epoch": 1.4091954022988507,
+      "grad_norm": 0.24010054767131805,
+      "learning_rate": 9.667030533834862e-05,
+      "loss": 0.25513901710510256,
+      "step": 920
+    },
+    {
+      "epoch": 1.4245210727969349,
+      "grad_norm": 0.19649599492549896,
+      "learning_rate": 9.482183428169975e-05,
+      "loss": 0.2543267965316772,
+      "step": 930
+    },
+    {
+      "epoch": 1.439846743295019,
+      "grad_norm": 0.217982679605484,
+      "learning_rate": 9.297513573193246e-05,
+      "loss": 0.256868314743042,
+      "step": 940
+    },
+    {
+      "epoch": 1.4551724137931035,
+      "grad_norm": 0.24914859235286713,
+      "learning_rate": 9.113084182136266e-05,
+      "loss": 0.24767658710479737,
+      "step": 950
+    },
+    {
+      "epoch": 1.4704980842911877,
+      "grad_norm": 0.2257557511329651,
+      "learning_rate": 8.928958385918855e-05,
+      "loss": 0.2683919668197632,
+      "step": 960
+    },
+    {
+      "epoch": 1.485823754789272,
+      "grad_norm": 0.21158252656459808,
+      "learning_rate": 8.745199211539117e-05,
+      "loss": 0.24358506202697755,
+      "step": 970
+    },
+    {
+      "epoch": 1.5011494252873563,
+      "grad_norm": 0.20610959827899933,
+      "learning_rate": 8.561869560499016e-05,
+      "loss": 0.27091827392578127,
+      "step": 980
+    },
+    {
+      "epoch": 1.5164750957854407,
+      "grad_norm": 0.17570218443870544,
+      "learning_rate": 8.379032187272968e-05,
+      "loss": 0.2440960168838501,
+      "step": 990
+    },
+    {
+      "epoch": 1.531800766283525,
+      "grad_norm": 0.18110089004039764,
+      "learning_rate": 8.196749677826713e-05,
+      "loss": 0.2696054935455322,
+      "step": 1000
+    },
+    {
+      "epoch": 1.547126436781609,
+      "grad_norm": 0.19731608033180237,
+      "learning_rate": 8.015084428193895e-05,
+      "loss": 0.26104373931884767,
+      "step": 1010
+    },
+    {
+      "epoch": 1.5624521072796935,
+      "grad_norm": 0.20462389290332794,
+      "learning_rate": 7.834098623117652e-05,
+      "loss": 0.2606567144393921,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5777777777777777,
+      "grad_norm": 0.21685872972011566,
+      "learning_rate": 7.65385421476453e-05,
+      "loss": 0.26782615184783937,
+      "step": 1030
+    },
+    {
+      "epoch": 1.593103448275862,
+      "grad_norm": 0.20966307818889618,
+      "learning_rate": 7.474412901517997e-05,
+      "loss": 0.26112306118011475,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6084291187739463,
+      "grad_norm": 0.19245949387550354,
+      "learning_rate": 7.295836106858854e-05,
+      "loss": 0.2425548553466797,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6237547892720308,
+      "grad_norm": 0.207347109913826,
+      "learning_rate": 7.118184958339713e-05,
+      "loss": 0.2567357301712036,
+      "step": 1060
+    },
+    {
+      "epoch": 1.639080459770115,
+      "grad_norm": 0.20875895023345947,
+      "learning_rate": 6.941520266660818e-05,
+      "loss": 0.26581392288208006,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6544061302681992,
+      "grad_norm": 0.20320458710193634,
+      "learning_rate": 6.765902504854276e-05,
+      "loss": 0.25880563259124756,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6697318007662836,
+      "grad_norm": 0.2191975712776184,
+      "learning_rate": 6.59139178758389e-05,
+      "loss": 0.2446974515914917,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6850574712643678,
+      "grad_norm": 0.19045910239219666,
+      "learning_rate": 6.418047850567699e-05,
+      "loss": 0.2456514596939087,
+      "step": 1100
+    },
+    {
+      "epoch": 1.700383141762452,
+      "grad_norm": 0.2059805542230606,
+      "learning_rate": 6.24593003013018e-05,
+      "loss": 0.25358903408050537,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7157088122605364,
+      "grad_norm": 0.22913187742233276,
+      "learning_rate": 6.075097242891179e-05,
+      "loss": 0.2545517921447754,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7310344827586208,
+      "grad_norm": 0.21482746303081512,
+      "learning_rate": 5.905607965598542e-05,
+      "loss": 0.26140122413635253,
+      "step": 1130
+    },
+    {
+      "epoch": 1.746360153256705,
+      "grad_norm": 0.17455799877643585,
+      "learning_rate": 5.737520215111256e-05,
+      "loss": 0.2500907897949219,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7616858237547892,
+      "grad_norm": 0.19934211671352386,
+      "learning_rate": 5.5708915285400934e-05,
+      "loss": 0.2561262369155884,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7770114942528736,
+      "grad_norm": 0.22233599424362183,
+      "learning_rate": 5.4057789435523734e-05,
+      "loss": 0.27218654155731203,
+      "step": 1160
+    },
+    {
+      "epoch": 1.7923371647509578,
+      "grad_norm": 0.19874989986419678,
+      "learning_rate": 5.242238978847772e-05,
+      "loss": 0.25201215744018557,
+      "step": 1170
+    },
+    {
+      "epoch": 1.807662835249042,
+      "grad_norm": 0.20110537111759186,
+      "learning_rate": 5.080327614811746e-05,
+      "loss": 0.24972200393676758,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8229885057471265,
+      "grad_norm": 0.18864119052886963,
+      "learning_rate": 4.920100274353218e-05,
+      "loss": 0.2667801856994629,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8383141762452109,
+      "grad_norm": 0.20197594165802002,
+      "learning_rate": 4.761611803933072e-05,
+      "loss": 0.2678064823150635,
+      "step": 1200
+    },
+    {
+      "epoch": 1.853639846743295,
+      "grad_norm": 0.1802796870470047,
+      "learning_rate": 4.604916454790027e-05,
+      "loss": 0.25614442825317385,
+      "step": 1210
+    },
+    {
+      "epoch": 1.8689655172413793,
+      "grad_norm": 0.26386988162994385,
+      "learning_rate": 4.450067864370187e-05,
+      "loss": 0.24004197120666504,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8842911877394637,
+      "grad_norm": 0.19681376218795776,
+      "learning_rate": 4.297119037966755e-05,
+      "loss": 0.2666898488998413,
+      "step": 1230
+    },
+    {
+      "epoch": 1.899616858237548,
+      "grad_norm": 0.21600529551506042,
+      "learning_rate": 4.146122330576087e-05,
+      "loss": 0.2697048902511597,
+      "step": 1240
+    },
+    {
+      "epoch": 1.914942528735632,
+      "grad_norm": 0.2030036747455597,
+      "learning_rate": 3.997129428976374e-05,
+      "loss": 0.2609272003173828,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9302681992337165,
+      "grad_norm": 0.22189973294734955,
+      "learning_rate": 3.8501913340350625e-05,
+      "loss": 0.2639767169952393,
+      "step": 1260
+    },
+    {
+      "epoch": 1.945593869731801,
+      "grad_norm": 0.2469155639410019,
+      "learning_rate": 3.7053583432510406e-05,
+      "loss": 0.26217553615570066,
+      "step": 1270
+    },
+    {
+      "epoch": 1.960919540229885,
+      "grad_norm": 0.23733453452587128,
+      "learning_rate": 3.5626800335375976e-05,
+      "loss": 0.26022138595581057,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9762452107279693,
+      "grad_norm": 0.1800413727760315,
+      "learning_rate": 3.422205244252067e-05,
+      "loss": 0.2549219369888306,
+      "step": 1290
+    },
+    {
+      "epoch": 1.9915708812260537,
+      "grad_norm": 0.21898971498012543,
+      "learning_rate": 3.283982060477895e-05,
+      "loss": 0.2534105062484741,
+      "step": 1300
+    },
+    {
+      "epoch": 2.0061302681992337,
+      "grad_norm": 0.19016309082508087,
+      "learning_rate": 3.148057796564944e-05,
+      "loss": 0.25081026554107666,
+      "step": 1310
+    },
+    {
+      "epoch": 2.021455938697318,
+      "grad_norm": 0.18190482258796692,
+      "learning_rate": 3.014478979933595e-05,
+      "loss": 0.2276550054550171,
+      "step": 1320
+    },
+    {
+      "epoch": 2.036781609195402,
+      "grad_norm": 0.1764170229434967,
+      "learning_rate": 2.8832913351482148e-05,
+      "loss": 0.22775135040283204,
+      "step": 1330
+    },
+    {
+      "epoch": 2.0521072796934865,
+      "grad_norm": 0.20627553761005402,
+      "learning_rate": 2.7545397682654695e-05,
+      "loss": 0.2405186414718628,
+      "step": 1340
+    },
+    {
+      "epoch": 2.067432950191571,
+      "grad_norm": 0.17293164134025574,
+      "learning_rate": 2.628268351462785e-05,
+      "loss": 0.23299973011016845,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0827586206896553,
+      "grad_norm": 0.21754054725170135,
+      "learning_rate": 2.5045203079522862e-05,
+      "loss": 0.22688329219818115,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0980842911877393,
+      "grad_norm": 0.17403560876846313,
+      "learning_rate": 2.3833379971852987e-05,
+      "loss": 0.2133577823638916,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1134099616858237,
+      "grad_norm": 0.2100820094347,
+      "learning_rate": 2.2647629003525428e-05,
+      "loss": 0.22004613876342774,
+      "step": 1380
+    },
+    {
+      "epoch": 2.128735632183908,
+      "grad_norm": 0.23395074903964996,
+      "learning_rate": 2.1488356061849636e-05,
+      "loss": 0.22840588092803954,
+      "step": 1390
+    },
+    {
+      "epoch": 2.144061302681992,
+      "grad_norm": 0.2112017124891281,
+      "learning_rate": 2.0355957970600403e-05,
+      "loss": 0.23168041706085205,
+      "step": 1400
+    },
+    {
+      "epoch": 2.1593869731800766,
+      "grad_norm": 0.21420609951019287,
+      "learning_rate": 1.925082235418346e-05,
+      "loss": 0.22593750953674316,
+      "step": 1410
+    },
+    {
+      "epoch": 2.174712643678161,
+      "grad_norm": 0.19721633195877075,
+      "learning_rate": 1.817332750495012e-05,
+      "loss": 0.2368011951446533,
+      "step": 1420
+    },
+    {
+      "epoch": 2.1900383141762454,
+      "grad_norm": 0.22296306490898132,
+      "learning_rate": 1.7123842253706302e-05,
+      "loss": 0.22809298038482667,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2053639846743294,
+      "grad_norm": 0.2142433077096939,
+      "learning_rate": 1.6102725843460277e-05,
+      "loss": 0.22773525714874268,
+      "step": 1440
+    },
+    {
+      "epoch": 2.220689655172414,
+      "grad_norm": 0.2203645557165146,
+      "learning_rate": 1.5110327806452362e-05,
+      "loss": 0.23412787914276123,
+      "step": 1450
+    },
+    {
+      "epoch": 2.236015325670498,
+      "grad_norm": 0.23082444071769714,
+      "learning_rate": 1.4146987844508508e-05,
+      "loss": 0.2073367118835449,
+      "step": 1460
+    },
+    {
+      "epoch": 2.251340996168582,
+      "grad_norm": 0.22913500666618347,
+      "learning_rate": 1.321303571275917e-05,
+      "loss": 0.21699509620666504,
+      "step": 1470
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.20030102133750916,
+      "learning_rate": 1.2308791106762718e-05,
+      "loss": 0.21742606163024902,
+      "step": 1480
+    },
+    {
+      "epoch": 2.281992337164751,
+      "grad_norm": 0.2148463875055313,
+      "learning_rate": 1.143456355307233e-05,
+      "loss": 0.2208996295928955,
+      "step": 1490
+    },
+    {
+      "epoch": 2.2973180076628354,
+      "grad_norm": 0.2605825662612915,
+      "learning_rate": 1.0590652303283932e-05,
+      "loss": 0.2229763984680176,
+      "step": 1500
+    },
+    {
+      "epoch": 2.3126436781609194,
+      "grad_norm": 0.228949174284935,
+      "learning_rate": 9.777346231601037e-06,
+      "loss": 0.22366030216217042,
+      "step": 1510
+    },
+    {
+      "epoch": 2.327969348659004,
+      "grad_norm": 0.23017998039722443,
+      "learning_rate": 8.994923735952032e-06,
+      "loss": 0.22504253387451173,
+      "step": 1520
+    },
+    {
+      "epoch": 2.3432950191570883,
+      "grad_norm": 0.20919591188430786,
+      "learning_rate": 8.243652642693478e-06,
+      "loss": 0.22776470184326172,
+      "step": 1530
+    },
+    {
+      "epoch": 2.3586206896551722,
+      "grad_norm": 0.203067809343338,
+      "learning_rate": 7.523790114931961e-06,
+      "loss": 0.2204723358154297,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3739463601532567,
+      "grad_norm": 0.27626660466194153,
+      "learning_rate": 6.835582564496256e-06,
+      "loss": 0.24098660945892333,
+      "step": 1550
+    },
+    {
+      "epoch": 2.389272030651341,
+      "grad_norm": 0.2158137708902359,
+      "learning_rate": 6.179265567589509e-06,
+      "loss": 0.23224225044250488,
+      "step": 1560
+    },
+    {
+      "epoch": 2.4045977011494255,
+      "grad_norm": 0.22840788960456848,
+      "learning_rate": 5.5550637841505045e-06,
+      "loss": 0.24213042259216308,
+      "step": 1570
+    },
+    {
+      "epoch": 2.4199233716475095,
+      "grad_norm": 0.22339899837970734,
+      "learning_rate": 4.963190880951807e-06,
+      "loss": 0.2249614715576172,
+      "step": 1580
+    },
+    {
+      "epoch": 2.435249042145594,
+      "grad_norm": 0.23574717342853546,
+      "learning_rate": 4.403849458460629e-06,
+      "loss": 0.2342482328414917,
+      "step": 1590
+    },
+    {
+      "epoch": 2.4505747126436783,
+      "grad_norm": 0.20539292693138123,
+      "learning_rate": 3.877230981487934e-06,
+      "loss": 0.23070881366729737,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4867093386142515e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a0dace2cc4eb22cc895e26540e9207a0c24ec0150b8e0768b062a4fcc440ba
+size 5201

checkpoint-1700/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.21.0

checkpoint-1700/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoint-1700/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc1d20c1eb7a358788c12faea6137af185a030ac212a9387c66b6e93970cfba
+size 73911112

checkpoint-1700/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- 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-1700/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb231dafc05501000b3599c1359aacfed547ee320d0a1a4c5e9efa8a6a78aba
+size 148048187

checkpoint-1700/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac06f92da68773f35c857961d1b058497a496e4e19cd610902cab34cb8e47c0
+size 14645

checkpoint-1700/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa51844685f0c9eba4b82b43196c2b2110d38e25e38d9a8664bf3dec077ba414
+size 1383

checkpoint-1700/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea181fadcc76682bba2a1386cc4e6a08c2d82a9e44e843548910f2294640947
+size 1465

checkpoint-1700/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f55e63353d3d978b390d346bae531be8b83bc9532c0be500d62b7253aa4c595
+size 11421991

checkpoint-1700/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1700/trainer_state.json

@@ -0,0 +1,1224 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.603831417624521,
+  "eval_steps": 500,
+  "global_step": 1700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01532567049808429,
+      "grad_norm": 1.7315932512283325,
+      "learning_rate": 3.461538461538462e-05,
+      "loss": 1.2715375900268555,
+      "step": 10
+    },
+    {
+      "epoch": 0.03065134099616858,
+      "grad_norm": 0.8982687592506409,
+      "learning_rate": 7.307692307692307e-05,
+      "loss": 0.7381579399108886,
+      "step": 20
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.30448803305625916,
+      "learning_rate": 0.00011153846153846154,
+      "loss": 0.3694685220718384,
+      "step": 30
+    },
+    {
+      "epoch": 0.06130268199233716,
+      "grad_norm": 0.235411137342453,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.33196756839752195,
+      "step": 40
+    },
+    {
+      "epoch": 0.07662835249042145,
+      "grad_norm": 0.24934549629688263,
+      "learning_rate": 0.00018846153846153847,
+      "loss": 0.36157524585723877,
+      "step": 50
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.23371638357639313,
+      "learning_rate": 0.0001999916134297838,
+      "loss": 0.3544674634933472,
+      "step": 60
+    },
+    {
+      "epoch": 0.10727969348659004,
+      "grad_norm": 0.25476178526878357,
+      "learning_rate": 0.00019995053973750825,
+      "loss": 0.3414992570877075,
+      "step": 70
+    },
+    {
+      "epoch": 0.12260536398467432,
+      "grad_norm": 0.25480854511260986,
+      "learning_rate": 0.00019987525257483818,
+      "loss": 0.3117872476577759,
+      "step": 80
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.2153773307800293,
+      "learning_rate": 0.00019976577771287128,
+      "loss": 0.319127631187439,
+      "step": 90
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "grad_norm": 0.2098936140537262,
+      "learning_rate": 0.00019962215262529155,
+      "loss": 0.3204960823059082,
+      "step": 100
+    },
+    {
+      "epoch": 0.1685823754789272,
+      "grad_norm": 0.24129652976989746,
+      "learning_rate": 0.0001994444264755422,
+      "loss": 0.30017311573028566,
+      "step": 110
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.20696483552455902,
+      "learning_rate": 0.0001992326600999967,
+      "loss": 0.31872761249542236,
+      "step": 120
+    },
+    {
+      "epoch": 0.19923371647509577,
+      "grad_norm": 0.2713371813297272,
+      "learning_rate": 0.0001989869259871342,
+      "loss": 0.30037286281585696,
+      "step": 130
+    },
+    {
+      "epoch": 0.21455938697318008,
+      "grad_norm": 0.1990661919116974,
+      "learning_rate": 0.0001987073082527266,
+      "loss": 0.3093862771987915,
+      "step": 140
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.25070610642433167,
+      "learning_rate": 0.00019839390261104515,
+      "loss": 0.31338260173797605,
+      "step": 150
+    },
+    {
+      "epoch": 0.24521072796934865,
+      "grad_norm": 0.25297442078590393,
+      "learning_rate": 0.00019804681634209725,
+      "loss": 0.3277841329574585,
+      "step": 160
+    },
+    {
+      "epoch": 0.26053639846743293,
+      "grad_norm": 0.20755986869335175,
+      "learning_rate": 0.00019766616825490408,
+      "loss": 0.30395307540893557,
+      "step": 170
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.26024317741394043,
+      "learning_rate": 0.00019725208864683166,
+      "loss": 0.3044783592224121,
+      "step": 180
+    },
+    {
+      "epoch": 0.29118773946360155,
+      "grad_norm": 0.19299627840518951,
+      "learning_rate": 0.0001968047192589896,
+      "loss": 0.3172396898269653,
+      "step": 190
+    },
+    {
+      "epoch": 0.3065134099616858,
+      "grad_norm": 0.2235356867313385,
+      "learning_rate": 0.00019632421322771264,
+      "loss": 0.30823068618774413,
+      "step": 200
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.22727671265602112,
+      "learning_rate": 0.00019581073503214128,
+      "loss": 0.3229329586029053,
+      "step": 210
+    },
+    {
+      "epoch": 0.3371647509578544,
+      "grad_norm": 0.20518285036087036,
+      "learning_rate": 0.0001952644604379202,
+      "loss": 0.30754120349884034,
+      "step": 220
+    },
+    {
+      "epoch": 0.3524904214559387,
+      "grad_norm": 0.18881909549236298,
+      "learning_rate": 0.0001946855764370326,
+      "loss": 0.3070927619934082,
+      "step": 230
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.1794276088476181,
+      "learning_rate": 0.0001940742811837924,
+      "loss": 0.2929072380065918,
+      "step": 240
+    },
+    {
+      "epoch": 0.3831417624521073,
+      "grad_norm": 0.21480266749858856,
+      "learning_rate": 0.00019343078392701512,
+      "loss": 0.3045187473297119,
+      "step": 250
+    },
+    {
+      "epoch": 0.39846743295019155,
+      "grad_norm": 0.20736214518547058,
+      "learning_rate": 0.00019275530493839118,
+      "loss": 0.2853532791137695,
+      "step": 260
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.2377932071685791,
+      "learning_rate": 0.00019204807543708597,
+      "loss": 0.31055545806884766,
+      "step": 270
+    },
+    {
+      "epoch": 0.42911877394636017,
+      "grad_norm": 0.2220766693353653,
+      "learning_rate": 0.0001913093375105926,
+      "loss": 0.30534508228302004,
+      "step": 280
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.1769602745771408,
+      "learning_rate": 0.00019053934403186448,
+      "loss": 0.3000555276870728,
+      "step": 290
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.1880396157503128,
+      "learning_rate": 0.00018973835857275586,
+      "loss": 0.2925630331039429,
+      "step": 300
+    },
+    {
+      "epoch": 0.47509578544061304,
+      "grad_norm": 0.20192766189575195,
+      "learning_rate": 0.00018890665531380007,
+      "loss": 0.30003533363342283,
+      "step": 310
+    },
+    {
+      "epoch": 0.4904214559386973,
+      "grad_norm": 0.18706700205802917,
+      "learning_rate": 0.00018804451895035643,
+      "loss": 0.3043027639389038,
+      "step": 320
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.24098548293113708,
+      "learning_rate": 0.00018715224459515796,
+      "loss": 0.2952123641967773,
+      "step": 330
+    },
+    {
+      "epoch": 0.5210727969348659,
+      "grad_norm": 0.18655002117156982,
+      "learning_rate": 0.00018623013767729303,
+      "loss": 0.2932705879211426,
+      "step": 340
+    },
+    {
+      "epoch": 0.5363984674329502,
+      "grad_norm": 0.19691458344459534,
+      "learning_rate": 0.00018527851383765578,
+      "loss": 0.31863603591918943,
+      "step": 350
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.18485110998153687,
+      "learning_rate": 0.00018429769882090104,
+      "loss": 0.2955839395523071,
+      "step": 360
+    },
+    {
+      "epoch": 0.5670498084291188,
+      "grad_norm": 0.23259525001049042,
+      "learning_rate": 0.00018328802836394055,
+      "loss": 0.3062273979187012,
+      "step": 370
+    },
+    {
+      "epoch": 0.5823754789272031,
+      "grad_norm": 0.1704971045255661,
+      "learning_rate": 0.00018224984808101887,
+      "loss": 0.28621697425842285,
+      "step": 380
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.206704780459404,
+      "learning_rate": 0.00018118351334540833,
+      "loss": 0.28846466541290283,
+      "step": 390
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "grad_norm": 0.20759014785289764,
+      "learning_rate": 0.00018008938916776323,
+      "loss": 0.30964126586914065,
+      "step": 400
+    },
+    {
+      "epoch": 0.6283524904214559,
+      "grad_norm": 0.1952156275510788,
+      "learning_rate": 0.00017896785007117524,
+      "loss": 0.306485652923584,
+      "step": 410
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.16880711913108826,
+      "learning_rate": 0.0001778192799629727,
+      "loss": 0.3217456579208374,
+      "step": 420
+    },
+    {
+      "epoch": 0.6590038314176245,
+      "grad_norm": 0.2303844839334488,
+      "learning_rate": 0.00017664407200330767,
+      "loss": 0.28161351680755614,
+      "step": 430
+    },
+    {
+      "epoch": 0.6743295019157088,
+      "grad_norm": 0.2218875139951706,
+      "learning_rate": 0.00017544262847057532,
+      "loss": 0.2977366209030151,
+      "step": 440
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.20623792707920074,
+      "learning_rate": 0.00017421536062371286,
+      "loss": 0.29798321723937987,
+      "step": 450
+    },
+    {
+      "epoch": 0.7049808429118773,
+      "grad_norm": 0.22805136442184448,
+      "learning_rate": 0.00017296268856142365,
+      "loss": 0.2869698524475098,
+      "step": 460
+    },
+    {
+      "epoch": 0.7203065134099617,
+      "grad_norm": 0.19344043731689453,
+      "learning_rate": 0.00017168504107837582,
+      "loss": 0.2964784145355225,
+      "step": 470
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.2286471724510193,
+      "learning_rate": 0.00017038285551842412,
+      "loss": 0.302842903137207,
+      "step": 480
+    },
+    {
+      "epoch": 0.7509578544061303,
+      "grad_norm": 0.19522379338741302,
+      "learning_rate": 0.00016905657762490548,
+      "loss": 0.3244823694229126,
+      "step": 490
+    },
+    {
+      "epoch": 0.7662835249042146,
+      "grad_norm": 0.1601998209953308,
+      "learning_rate": 0.00016770666138805904,
+      "loss": 0.2811170816421509,
+      "step": 500
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.16715656220912933,
+      "learning_rate": 0.0001663335688896237,
+      "loss": 0.2751513719558716,
+      "step": 510
+    },
+    {
+      "epoch": 0.7969348659003831,
+      "grad_norm": 0.19661696255207062,
+      "learning_rate": 0.00016493777014466563,
+      "loss": 0.3170422077178955,
+      "step": 520
+    },
+    {
+      "epoch": 0.8122605363984674,
+      "grad_norm": 0.18826834857463837,
+      "learning_rate": 0.0001635197429406901,
+      "loss": 0.2818011283874512,
+      "step": 530
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.18041561543941498,
+      "learning_rate": 0.00016207997267409313,
+      "loss": 0.30449423789978025,
+      "step": 540
+    },
+    {
+      "epoch": 0.842911877394636,
+      "grad_norm": 0.1955738365650177,
+      "learning_rate": 0.00016061895218400806,
+      "loss": 0.2753497362136841,
+      "step": 550
+    },
+    {
+      "epoch": 0.8582375478927203,
+      "grad_norm": 0.19417400658130646,
+      "learning_rate": 0.0001591371815836051,
+      "loss": 0.28362064361572265,
+      "step": 560
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.1948927491903305,
+      "learning_rate": 0.00015763516808890024,
+      "loss": 0.2855699062347412,
+      "step": 570
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.18820644915103912,
+      "learning_rate": 0.00015611342584513342,
+      "loss": 0.28289546966552737,
+      "step": 580
+    },
+    {
+      "epoch": 0.9042145593869731,
+      "grad_norm": 0.18016715347766876,
+      "learning_rate": 0.00015457247575077445,
+      "loss": 0.29960951805114744,
+      "step": 590
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.22913143038749695,
+      "learning_rate": 0.0001530128452792174,
+      "loss": 0.28281118869781496,
+      "step": 600
+    },
+    {
+      "epoch": 0.9348659003831418,
+      "grad_norm": 0.20966900885105133,
+      "learning_rate": 0.00015143506829822426,
+      "loss": 0.30697131156921387,
+      "step": 610
+    },
+    {
+      "epoch": 0.9501915708812261,
+      "grad_norm": 0.2458924800157547,
+      "learning_rate": 0.00014983968488718006,
+      "loss": 0.30470201969146726,
+      "step": 620
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.18874205648899078,
+      "learning_rate": 0.00014822724115222128,
+      "loss": 0.30251691341400144,
+      "step": 630
+    },
+    {
+      "epoch": 0.9808429118773946,
+      "grad_norm": 0.22530531883239746,
+      "learning_rate": 0.00014659828903930178,
+      "loss": 0.29744977951049806,
+      "step": 640
+    },
+    {
+      "epoch": 0.9961685823754789,
+      "grad_norm": 0.20111751556396484,
+      "learning_rate": 0.00014495338614525926,
+      "loss": 0.28247039318084716,
+      "step": 650
+    },
+    {
+      "epoch": 1.010727969348659,
+      "grad_norm": 0.17702056467533112,
+      "learning_rate": 0.00014329309552694783,
+      "loss": 0.2753941774368286,
+      "step": 660
+    },
+    {
+      "epoch": 1.0260536398467432,
+      "grad_norm": 0.17669467628002167,
+      "learning_rate": 0.00014161798550850124,
+      "loss": 0.2545931816101074,
+      "step": 670
+    },
+    {
+      "epoch": 1.0413793103448277,
+      "grad_norm": 0.1835271567106247,
+      "learning_rate": 0.00013992862948679333,
+      "loss": 0.24901304244995118,
+      "step": 680
+    },
+    {
+      "epoch": 1.0567049808429119,
+      "grad_norm": 0.19968923926353455,
+      "learning_rate": 0.00013822560573516194,
+      "loss": 0.27475411891937257,
+      "step": 690
+    },
+    {
+      "epoch": 1.072030651340996,
+      "grad_norm": 0.17976751923561096,
+      "learning_rate": 0.00013650949720546372,
+      "loss": 0.2584954023361206,
+      "step": 700
+    },
+    {
+      "epoch": 1.0873563218390805,
+      "grad_norm": 0.19866906106472015,
+      "learning_rate": 0.00013478089132852716,
+      "loss": 0.26185197830200196,
+      "step": 710
+    },
+    {
+      "epoch": 1.1026819923371647,
+      "grad_norm": 0.2139822244644165,
+      "learning_rate": 0.0001330403798130729,
+      "loss": 0.2664598226547241,
+      "step": 720
+    },
+    {
+      "epoch": 1.118007662835249,
+      "grad_norm": 0.1918357014656067,
+      "learning_rate": 0.00013128855844316944,
+      "loss": 0.26914339065551757,
+      "step": 730
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.21598224341869354,
+      "learning_rate": 0.00012952602687429362,
+      "loss": 0.24881536960601808,
+      "step": 740
+    },
+    {
+      "epoch": 1.1486590038314177,
+      "grad_norm": 0.16682575643062592,
+      "learning_rate": 0.00012775338842806647,
+      "loss": 0.2527227163314819,
+      "step": 750
+    },
+    {
+      "epoch": 1.163984674329502,
+      "grad_norm": 0.18836885690689087,
+      "learning_rate": 0.00012597124988573353,
+      "loss": 0.2735306739807129,
+      "step": 760
+    },
+    {
+      "epoch": 1.1793103448275861,
+      "grad_norm": 0.20422716438770294,
+      "learning_rate": 0.00012418022128046142,
+      "loss": 0.2547746181488037,
+      "step": 770
+    },
+    {
+      "epoch": 1.1946360153256705,
+      "grad_norm": 0.18123748898506165,
+      "learning_rate": 0.00012238091568852086,
+      "loss": 0.2550168037414551,
+      "step": 780
+    },
+    {
+      "epoch": 1.2099616858237547,
+      "grad_norm": 0.1850244104862213,
+      "learning_rate": 0.00012057394901942834,
+      "loss": 0.2556851148605347,
+      "step": 790
+    },
+    {
+      "epoch": 1.2252873563218392,
+      "grad_norm": 0.18734942376613617,
+      "learning_rate": 0.00011875993980511773,
+      "loss": 0.25217125415802,
+      "step": 800
+    },
+    {
+      "epoch": 1.2406130268199234,
+      "grad_norm": 0.25744232535362244,
+      "learning_rate": 0.00011693950898821442,
+      "loss": 0.25321738719940184,
+      "step": 810
+    },
+    {
+      "epoch": 1.2559386973180078,
+      "grad_norm": 0.24140717089176178,
+      "learning_rate": 0.00011511327970948398,
+      "loss": 0.2695934295654297,
+      "step": 820
+    },
+    {
+      "epoch": 1.271264367816092,
+      "grad_norm": 0.19622239470481873,
+      "learning_rate": 0.00011328187709452884,
+      "loss": 0.25709664821624756,
+      "step": 830
+    },
+    {
+      "epoch": 1.2865900383141762,
+      "grad_norm": 0.18637792766094208,
+      "learning_rate": 0.00011144592803980507,
+      "loss": 0.25869600772857665,
+      "step": 840
+    },
+    {
+      "epoch": 1.3019157088122606,
+      "grad_norm": 0.19393154978752136,
+      "learning_rate": 0.00010960606099803339,
+      "loss": 0.2554497003555298,
+      "step": 850
+    },
+    {
+      "epoch": 1.3172413793103448,
+      "grad_norm": 0.2453709989786148,
+      "learning_rate": 0.0001077629057630771,
+      "loss": 0.26648812294006347,
+      "step": 860
+    },
+    {
+      "epoch": 1.332567049808429,
+      "grad_norm": 0.25964638590812683,
+      "learning_rate": 0.00010591709325436123,
+      "loss": 0.26240499019622804,
+      "step": 870
+    },
+    {
+      "epoch": 1.3478927203065134,
+      "grad_norm": 0.21236255764961243,
+      "learning_rate": 0.00010406925530090625,
+      "loss": 0.26952788829803465,
+      "step": 880
+    },
+    {
+      "epoch": 1.3632183908045978,
+      "grad_norm": 0.20102430880069733,
+      "learning_rate": 0.00010222002442505056,
+      "loss": 0.2485269546508789,
+      "step": 890
+    },
+    {
+      "epoch": 1.378544061302682,
+      "grad_norm": 0.23220829665660858,
+      "learning_rate": 0.00010037003362593544,
+      "loss": 0.2720418214797974,
+      "step": 900
+    },
+    {
+      "epoch": 1.3938697318007662,
+      "grad_norm": 0.21482332050800323,
+      "learning_rate": 9.85199161628269e-05,
+      "loss": 0.24709177017211914,
+      "step": 910
+    },
+    {
+      "epoch": 1.4091954022988507,
+      "grad_norm": 0.24010054767131805,
+      "learning_rate": 9.667030533834862e-05,
+      "loss": 0.25513901710510256,
+      "step": 920
+    },
+    {
+      "epoch": 1.4245210727969349,
+      "grad_norm": 0.19649599492549896,
+      "learning_rate": 9.482183428169975e-05,
+      "loss": 0.2543267965316772,
+      "step": 930
+    },
+    {
+      "epoch": 1.439846743295019,
+      "grad_norm": 0.217982679605484,
+      "learning_rate": 9.297513573193246e-05,
+      "loss": 0.256868314743042,
+      "step": 940
+    },
+    {
+      "epoch": 1.4551724137931035,
+      "grad_norm": 0.24914859235286713,
+      "learning_rate": 9.113084182136266e-05,
+      "loss": 0.24767658710479737,
+      "step": 950
+    },
+    {
+      "epoch": 1.4704980842911877,
+      "grad_norm": 0.2257557511329651,
+      "learning_rate": 8.928958385918855e-05,
+      "loss": 0.2683919668197632,
+      "step": 960
+    },
+    {
+      "epoch": 1.485823754789272,
+      "grad_norm": 0.21158252656459808,
+      "learning_rate": 8.745199211539117e-05,
+      "loss": 0.24358506202697755,
+      "step": 970
+    },
+    {
+      "epoch": 1.5011494252873563,
+      "grad_norm": 0.20610959827899933,
+      "learning_rate": 8.561869560499016e-05,
+      "loss": 0.27091827392578127,
+      "step": 980
+    },
+    {
+      "epoch": 1.5164750957854407,
+      "grad_norm": 0.17570218443870544,
+      "learning_rate": 8.379032187272968e-05,
+      "loss": 0.2440960168838501,
+      "step": 990
+    },
+    {
+      "epoch": 1.531800766283525,
+      "grad_norm": 0.18110089004039764,
+      "learning_rate": 8.196749677826713e-05,
+      "loss": 0.2696054935455322,
+      "step": 1000
+    },
+    {
+      "epoch": 1.547126436781609,
+      "grad_norm": 0.19731608033180237,
+      "learning_rate": 8.015084428193895e-05,
+      "loss": 0.26104373931884767,
+      "step": 1010
+    },
+    {
+      "epoch": 1.5624521072796935,
+      "grad_norm": 0.20462389290332794,
+      "learning_rate": 7.834098623117652e-05,
+      "loss": 0.2606567144393921,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5777777777777777,
+      "grad_norm": 0.21685872972011566,
+      "learning_rate": 7.65385421476453e-05,
+      "loss": 0.26782615184783937,
+      "step": 1030
+    },
+    {
+      "epoch": 1.593103448275862,
+      "grad_norm": 0.20966307818889618,
+      "learning_rate": 7.474412901517997e-05,
+      "loss": 0.26112306118011475,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6084291187739463,
+      "grad_norm": 0.19245949387550354,
+      "learning_rate": 7.295836106858854e-05,
+      "loss": 0.2425548553466797,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6237547892720308,
+      "grad_norm": 0.207347109913826,
+      "learning_rate": 7.118184958339713e-05,
+      "loss": 0.2567357301712036,
+      "step": 1060
+    },
+    {
+      "epoch": 1.639080459770115,
+      "grad_norm": 0.20875895023345947,
+      "learning_rate": 6.941520266660818e-05,
+      "loss": 0.26581392288208006,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6544061302681992,
+      "grad_norm": 0.20320458710193634,
+      "learning_rate": 6.765902504854276e-05,
+      "loss": 0.25880563259124756,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6697318007662836,
+      "grad_norm": 0.2191975712776184,
+      "learning_rate": 6.59139178758389e-05,
+      "loss": 0.2446974515914917,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6850574712643678,
+      "grad_norm": 0.19045910239219666,
+      "learning_rate": 6.418047850567699e-05,
+      "loss": 0.2456514596939087,
+      "step": 1100
+    },
+    {
+      "epoch": 1.700383141762452,
+      "grad_norm": 0.2059805542230606,
+      "learning_rate": 6.24593003013018e-05,
+      "loss": 0.25358903408050537,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7157088122605364,
+      "grad_norm": 0.22913187742233276,
+      "learning_rate": 6.075097242891179e-05,
+      "loss": 0.2545517921447754,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7310344827586208,
+      "grad_norm": 0.21482746303081512,
+      "learning_rate": 5.905607965598542e-05,
+      "loss": 0.26140122413635253,
+      "step": 1130
+    },
+    {
+      "epoch": 1.746360153256705,
+      "grad_norm": 0.17455799877643585,
+      "learning_rate": 5.737520215111256e-05,
+      "loss": 0.2500907897949219,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7616858237547892,
+      "grad_norm": 0.19934211671352386,
+      "learning_rate": 5.5708915285400934e-05,
+      "loss": 0.2561262369155884,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7770114942528736,
+      "grad_norm": 0.22233599424362183,
+      "learning_rate": 5.4057789435523734e-05,
+      "loss": 0.27218654155731203,
+      "step": 1160
+    },
+    {
+      "epoch": 1.7923371647509578,
+      "grad_norm": 0.19874989986419678,
+      "learning_rate": 5.242238978847772e-05,
+      "loss": 0.25201215744018557,
+      "step": 1170
+    },
+    {
+      "epoch": 1.807662835249042,
+      "grad_norm": 0.20110537111759186,
+      "learning_rate": 5.080327614811746e-05,
+      "loss": 0.24972200393676758,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8229885057471265,
+      "grad_norm": 0.18864119052886963,
+      "learning_rate": 4.920100274353218e-05,
+      "loss": 0.2667801856994629,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8383141762452109,
+      "grad_norm": 0.20197594165802002,
+      "learning_rate": 4.761611803933072e-05,
+      "loss": 0.2678064823150635,
+      "step": 1200
+    },
+    {
+      "epoch": 1.853639846743295,
+      "grad_norm": 0.1802796870470047,
+      "learning_rate": 4.604916454790027e-05,
+      "loss": 0.25614442825317385,
+      "step": 1210
+    },
+    {
+      "epoch": 1.8689655172413793,
+      "grad_norm": 0.26386988162994385,
+      "learning_rate": 4.450067864370187e-05,
+      "loss": 0.24004197120666504,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8842911877394637,
+      "grad_norm": 0.19681376218795776,
+      "learning_rate": 4.297119037966755e-05,
+      "loss": 0.2666898488998413,
+      "step": 1230
+    },
+    {
+      "epoch": 1.899616858237548,
+      "grad_norm": 0.21600529551506042,
+      "learning_rate": 4.146122330576087e-05,
+      "loss": 0.2697048902511597,
+      "step": 1240
+    },
+    {
+      "epoch": 1.914942528735632,
+      "grad_norm": 0.2030036747455597,
+      "learning_rate": 3.997129428976374e-05,
+      "loss": 0.2609272003173828,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9302681992337165,
+      "grad_norm": 0.22189973294734955,
+      "learning_rate": 3.8501913340350625e-05,
+      "loss": 0.2639767169952393,
+      "step": 1260
+    },
+    {
+      "epoch": 1.945593869731801,
+      "grad_norm": 0.2469155639410019,
+      "learning_rate": 3.7053583432510406e-05,
+      "loss": 0.26217553615570066,
+      "step": 1270
+    },
+    {
+      "epoch": 1.960919540229885,
+      "grad_norm": 0.23733453452587128,
+      "learning_rate": 3.5626800335375976e-05,
+      "loss": 0.26022138595581057,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9762452107279693,
+      "grad_norm": 0.1800413727760315,
+      "learning_rate": 3.422205244252067e-05,
+      "loss": 0.2549219369888306,
+      "step": 1290
+    },
+    {
+      "epoch": 1.9915708812260537,
+      "grad_norm": 0.21898971498012543,
+      "learning_rate": 3.283982060477895e-05,
+      "loss": 0.2534105062484741,
+      "step": 1300
+    },
+    {
+      "epoch": 2.0061302681992337,
+      "grad_norm": 0.19016309082508087,
+      "learning_rate": 3.148057796564944e-05,
+      "loss": 0.25081026554107666,
+      "step": 1310
+    },
+    {
+      "epoch": 2.021455938697318,
+      "grad_norm": 0.18190482258796692,
+      "learning_rate": 3.014478979933595e-05,
+      "loss": 0.2276550054550171,
+      "step": 1320
+    },
+    {
+      "epoch": 2.036781609195402,
+      "grad_norm": 0.1764170229434967,
+      "learning_rate": 2.8832913351482148e-05,
+      "loss": 0.22775135040283204,
+      "step": 1330
+    },
+    {
+      "epoch": 2.0521072796934865,
+      "grad_norm": 0.20627553761005402,
+      "learning_rate": 2.7545397682654695e-05,
+      "loss": 0.2405186414718628,
+      "step": 1340
+    },
+    {
+      "epoch": 2.067432950191571,
+      "grad_norm": 0.17293164134025574,
+      "learning_rate": 2.628268351462785e-05,
+      "loss": 0.23299973011016845,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0827586206896553,
+      "grad_norm": 0.21754054725170135,
+      "learning_rate": 2.5045203079522862e-05,
+      "loss": 0.22688329219818115,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0980842911877393,
+      "grad_norm": 0.17403560876846313,
+      "learning_rate": 2.3833379971852987e-05,
+      "loss": 0.2133577823638916,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1134099616858237,
+      "grad_norm": 0.2100820094347,
+      "learning_rate": 2.2647629003525428e-05,
+      "loss": 0.22004613876342774,
+      "step": 1380
+    },
+    {
+      "epoch": 2.128735632183908,
+      "grad_norm": 0.23395074903964996,
+      "learning_rate": 2.1488356061849636e-05,
+      "loss": 0.22840588092803954,
+      "step": 1390
+    },
+    {
+      "epoch": 2.144061302681992,
+      "grad_norm": 0.2112017124891281,
+      "learning_rate": 2.0355957970600403e-05,
+      "loss": 0.23168041706085205,
+      "step": 1400
+    },
+    {
+      "epoch": 2.1593869731800766,
+      "grad_norm": 0.21420609951019287,
+      "learning_rate": 1.925082235418346e-05,
+      "loss": 0.22593750953674316,
+      "step": 1410
+    },
+    {
+      "epoch": 2.174712643678161,
+      "grad_norm": 0.19721633195877075,
+      "learning_rate": 1.817332750495012e-05,
+      "loss": 0.2368011951446533,
+      "step": 1420
+    },
+    {
+      "epoch": 2.1900383141762454,
+      "grad_norm": 0.22296306490898132,
+      "learning_rate": 1.7123842253706302e-05,
+      "loss": 0.22809298038482667,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2053639846743294,
+      "grad_norm": 0.2142433077096939,
+      "learning_rate": 1.6102725843460277e-05,
+      "loss": 0.22773525714874268,
+      "step": 1440
+    },
+    {
+      "epoch": 2.220689655172414,
+      "grad_norm": 0.2203645557165146,
+      "learning_rate": 1.5110327806452362e-05,
+      "loss": 0.23412787914276123,
+      "step": 1450
+    },
+    {
+      "epoch": 2.236015325670498,
+      "grad_norm": 0.23082444071769714,
+      "learning_rate": 1.4146987844508508e-05,
+      "loss": 0.2073367118835449,
+      "step": 1460
+    },
+    {
+      "epoch": 2.251340996168582,
+      "grad_norm": 0.22913500666618347,
+      "learning_rate": 1.321303571275917e-05,
+      "loss": 0.21699509620666504,
+      "step": 1470
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.20030102133750916,
+      "learning_rate": 1.2308791106762718e-05,
+      "loss": 0.21742606163024902,
+      "step": 1480
+    },
+    {
+      "epoch": 2.281992337164751,
+      "grad_norm": 0.2148463875055313,
+      "learning_rate": 1.143456355307233e-05,
+      "loss": 0.2208996295928955,
+      "step": 1490
+    },
+    {
+      "epoch": 2.2973180076628354,
+      "grad_norm": 0.2605825662612915,
+      "learning_rate": 1.0590652303283932e-05,
+      "loss": 0.2229763984680176,
+      "step": 1500
+    },
+    {
+      "epoch": 2.3126436781609194,
+      "grad_norm": 0.228949174284935,
+      "learning_rate": 9.777346231601037e-06,
+      "loss": 0.22366030216217042,
+      "step": 1510
+    },
+    {
+      "epoch": 2.327969348659004,
+      "grad_norm": 0.23017998039722443,
+      "learning_rate": 8.994923735952032e-06,
+      "loss": 0.22504253387451173,
+      "step": 1520
+    },
+    {
+      "epoch": 2.3432950191570883,
+      "grad_norm": 0.20919591188430786,
+      "learning_rate": 8.243652642693478e-06,
+      "loss": 0.22776470184326172,
+      "step": 1530
+    },
+    {
+      "epoch": 2.3586206896551722,
+      "grad_norm": 0.203067809343338,
+      "learning_rate": 7.523790114931961e-06,
+      "loss": 0.2204723358154297,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3739463601532567,
+      "grad_norm": 0.27626660466194153,
+      "learning_rate": 6.835582564496256e-06,
+      "loss": 0.24098660945892333,
+      "step": 1550
+    },
+    {
+      "epoch": 2.389272030651341,
+      "grad_norm": 0.2158137708902359,
+      "learning_rate": 6.179265567589509e-06,
+      "loss": 0.23224225044250488,
+      "step": 1560
+    },
+    {
+      "epoch": 2.4045977011494255,
+      "grad_norm": 0.22840788960456848,
+      "learning_rate": 5.5550637841505045e-06,
+      "loss": 0.24213042259216308,
+      "step": 1570
+    },
+    {
+      "epoch": 2.4199233716475095,
+      "grad_norm": 0.22339899837970734,
+      "learning_rate": 4.963190880951807e-06,
+      "loss": 0.2249614715576172,
+      "step": 1580
+    },
+    {
+      "epoch": 2.435249042145594,
+      "grad_norm": 0.23574717342853546,
+      "learning_rate": 4.403849458460629e-06,
+      "loss": 0.2342482328414917,
+      "step": 1590
+    },
+    {
+      "epoch": 2.4505747126436783,
+      "grad_norm": 0.20539292693138123,
+      "learning_rate": 3.877230981487934e-06,
+      "loss": 0.23070881366729737,
+      "step": 1600
+    },
+    {
+      "epoch": 2.4659003831417623,
+      "grad_norm": 0.2082466185092926,
+      "learning_rate": 3.3835157136493435e-06,
+      "loss": 0.22563157081604004,
+      "step": 1610
+    },
+    {
+      "epoch": 2.4812260536398467,
+      "grad_norm": 0.22585122287273407,
+      "learning_rate": 2.9228726556599916e-06,
+      "loss": 0.2235992431640625,
+      "step": 1620
+    },
+    {
+      "epoch": 2.496551724137931,
+      "grad_norm": 0.21266688406467438,
+      "learning_rate": 2.495459487485119e-06,
+      "loss": 0.22575080394744873,
+      "step": 1630
+    },
+    {
+      "epoch": 2.5118773946360156,
+      "grad_norm": 0.19549226760864258,
+      "learning_rate": 2.1014225143654143e-06,
+      "loss": 0.21721582412719725,
+      "step": 1640
+    },
+    {
+      "epoch": 2.5272030651340995,
+      "grad_norm": 0.22203820943832397,
+      "learning_rate": 1.7408966167362317e-06,
+      "loss": 0.22829241752624513,
+      "step": 1650
+    },
+    {
+      "epoch": 2.542528735632184,
+      "grad_norm": 0.19951409101486206,
+      "learning_rate": 1.4140052040574891e-06,
+      "loss": 0.21612203121185303,
+      "step": 1660
+    },
+    {
+      "epoch": 2.557854406130268,
+      "grad_norm": 0.23988863825798035,
+      "learning_rate": 1.1208601725700374e-06,
+      "loss": 0.22502026557922364,
+      "step": 1670
+    },
+    {
+      "epoch": 2.5731800766283524,
+      "grad_norm": 0.23238494992256165,
+      "learning_rate": 8.615618669931991e-07,
+      "loss": 0.22191386222839354,
+      "step": 1680
+    },
+    {
+      "epoch": 2.5885057471264368,
+      "grad_norm": 0.26193344593048096,
+      "learning_rate": 6.361990461763667e-07,
+      "loss": 0.22765371799468995,
+      "step": 1690
+    },
+    {
+      "epoch": 2.603831417624521,
+      "grad_norm": 0.18539129197597504,
+      "learning_rate": 4.4484885271641743e-07,
+      "loss": 0.22877717018127441,
+      "step": 1700
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5793775679257395e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1700/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a0dace2cc4eb22cc895e26540e9207a0c24ec0150b8e0768b062a4fcc440ba
+size 5201

checkpoint-1750/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.21.0

checkpoint-1750/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoint-1750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35013cd0735cf2635d1d3b5e58b19417211fb610c11e92ceb933dd5185ffcfde
+size 73911112

checkpoint-1750/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- 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-1750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd342df41303482187acf524c4b2bf6e0755b150f90ea7f730b12775a55ecfc
+size 148048187

checkpoint-1750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75ec60611c390425b2963ce0fced16da5700638ba362f3f5ad6e274cf98217b
+size 14645

checkpoint-1750/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f9facd156f274d558585c8beffeda844e22f840dd0b18f6d2c35abbad24bd0
+size 1383

checkpoint-1750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108f9587151f10ab7a967643ea41448326236a3e9e555d134061f22d4fb0377b
+size 1465

checkpoint-1750/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f55e63353d3d978b390d346bae531be8b83bc9532c0be500d62b7253aa4c595
+size 11421991

checkpoint-1750/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1750/trainer_state.json

@@ -0,0 +1,1259 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6804597701149424,
+  "eval_steps": 500,
+  "global_step": 1750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01532567049808429,
+      "grad_norm": 1.7315932512283325,
+      "learning_rate": 3.461538461538462e-05,
+      "loss": 1.2715375900268555,
+      "step": 10
+    },
+    {
+      "epoch": 0.03065134099616858,
+      "grad_norm": 0.8982687592506409,
+      "learning_rate": 7.307692307692307e-05,
+      "loss": 0.7381579399108886,
+      "step": 20
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.30448803305625916,
+      "learning_rate": 0.00011153846153846154,
+      "loss": 0.3694685220718384,
+      "step": 30
+    },
+    {
+      "epoch": 0.06130268199233716,
+      "grad_norm": 0.235411137342453,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.33196756839752195,
+      "step": 40
+    },
+    {
+      "epoch": 0.07662835249042145,
+      "grad_norm": 0.24934549629688263,
+      "learning_rate": 0.00018846153846153847,
+      "loss": 0.36157524585723877,
+      "step": 50
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.23371638357639313,
+      "learning_rate": 0.0001999916134297838,
+      "loss": 0.3544674634933472,
+      "step": 60
+    },
+    {
+      "epoch": 0.10727969348659004,
+      "grad_norm": 0.25476178526878357,
+      "learning_rate": 0.00019995053973750825,
+      "loss": 0.3414992570877075,
+      "step": 70
+    },
+    {
+      "epoch": 0.12260536398467432,
+      "grad_norm": 0.25480854511260986,
+      "learning_rate": 0.00019987525257483818,
+      "loss": 0.3117872476577759,
+      "step": 80
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.2153773307800293,
+      "learning_rate": 0.00019976577771287128,
+      "loss": 0.319127631187439,
+      "step": 90
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "grad_norm": 0.2098936140537262,
+      "learning_rate": 0.00019962215262529155,
+      "loss": 0.3204960823059082,
+      "step": 100
+    },
+    {
+      "epoch": 0.1685823754789272,
+      "grad_norm": 0.24129652976989746,
+      "learning_rate": 0.0001994444264755422,
+      "loss": 0.30017311573028566,
+      "step": 110
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.20696483552455902,
+      "learning_rate": 0.0001992326600999967,
+      "loss": 0.31872761249542236,
+      "step": 120
+    },
+    {
+      "epoch": 0.19923371647509577,
+      "grad_norm": 0.2713371813297272,
+      "learning_rate": 0.0001989869259871342,
+      "loss": 0.30037286281585696,
+      "step": 130
+    },
+    {
+      "epoch": 0.21455938697318008,
+      "grad_norm": 0.1990661919116974,
+      "learning_rate": 0.0001987073082527266,
+      "loss": 0.3093862771987915,
+      "step": 140
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.25070610642433167,
+      "learning_rate": 0.00019839390261104515,
+      "loss": 0.31338260173797605,
+      "step": 150
+    },
+    {
+      "epoch": 0.24521072796934865,
+      "grad_norm": 0.25297442078590393,
+      "learning_rate": 0.00019804681634209725,
+      "loss": 0.3277841329574585,
+      "step": 160
+    },
+    {
+      "epoch": 0.26053639846743293,
+      "grad_norm": 0.20755986869335175,
+      "learning_rate": 0.00019766616825490408,
+      "loss": 0.30395307540893557,
+      "step": 170
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.26024317741394043,
+      "learning_rate": 0.00019725208864683166,
+      "loss": 0.3044783592224121,
+      "step": 180
+    },
+    {
+      "epoch": 0.29118773946360155,
+      "grad_norm": 0.19299627840518951,
+      "learning_rate": 0.0001968047192589896,
+      "loss": 0.3172396898269653,
+      "step": 190
+    },
+    {
+      "epoch": 0.3065134099616858,
+      "grad_norm": 0.2235356867313385,
+      "learning_rate": 0.00019632421322771264,
+      "loss": 0.30823068618774413,
+      "step": 200
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.22727671265602112,
+      "learning_rate": 0.00019581073503214128,
+      "loss": 0.3229329586029053,
+      "step": 210
+    },
+    {
+      "epoch": 0.3371647509578544,
+      "grad_norm": 0.20518285036087036,
+      "learning_rate": 0.0001952644604379202,
+      "loss": 0.30754120349884034,
+      "step": 220
+    },
+    {
+      "epoch": 0.3524904214559387,
+      "grad_norm": 0.18881909549236298,
+      "learning_rate": 0.0001946855764370326,
+      "loss": 0.3070927619934082,
+      "step": 230
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.1794276088476181,
+      "learning_rate": 0.0001940742811837924,
+      "loss": 0.2929072380065918,
+      "step": 240
+    },
+    {
+      "epoch": 0.3831417624521073,
+      "grad_norm": 0.21480266749858856,
+      "learning_rate": 0.00019343078392701512,
+      "loss": 0.3045187473297119,
+      "step": 250
+    },
+    {
+      "epoch": 0.39846743295019155,
+      "grad_norm": 0.20736214518547058,
+      "learning_rate": 0.00019275530493839118,
+      "loss": 0.2853532791137695,
+      "step": 260
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.2377932071685791,
+      "learning_rate": 0.00019204807543708597,
+      "loss": 0.31055545806884766,
+      "step": 270
+    },
+    {
+      "epoch": 0.42911877394636017,
+      "grad_norm": 0.2220766693353653,
+      "learning_rate": 0.0001913093375105926,
+      "loss": 0.30534508228302004,
+      "step": 280
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.1769602745771408,
+      "learning_rate": 0.00019053934403186448,
+      "loss": 0.3000555276870728,
+      "step": 290
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.1880396157503128,
+      "learning_rate": 0.00018973835857275586,
+      "loss": 0.2925630331039429,
+      "step": 300
+    },
+    {
+      "epoch": 0.47509578544061304,
+      "grad_norm": 0.20192766189575195,
+      "learning_rate": 0.00018890665531380007,
+      "loss": 0.30003533363342283,
+      "step": 310
+    },
+    {
+      "epoch": 0.4904214559386973,
+      "grad_norm": 0.18706700205802917,
+      "learning_rate": 0.00018804451895035643,
+      "loss": 0.3043027639389038,
+      "step": 320
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.24098548293113708,
+      "learning_rate": 0.00018715224459515796,
+      "loss": 0.2952123641967773,
+      "step": 330
+    },
+    {
+      "epoch": 0.5210727969348659,
+      "grad_norm": 0.18655002117156982,
+      "learning_rate": 0.00018623013767729303,
+      "loss": 0.2932705879211426,
+      "step": 340
+    },
+    {
+      "epoch": 0.5363984674329502,
+      "grad_norm": 0.19691458344459534,
+      "learning_rate": 0.00018527851383765578,
+      "loss": 0.31863603591918943,
+      "step": 350
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.18485110998153687,
+      "learning_rate": 0.00018429769882090104,
+      "loss": 0.2955839395523071,
+      "step": 360
+    },
+    {
+      "epoch": 0.5670498084291188,
+      "grad_norm": 0.23259525001049042,
+      "learning_rate": 0.00018328802836394055,
+      "loss": 0.3062273979187012,
+      "step": 370
+    },
+    {
+      "epoch": 0.5823754789272031,
+      "grad_norm": 0.1704971045255661,
+      "learning_rate": 0.00018224984808101887,
+      "loss": 0.28621697425842285,
+      "step": 380
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.206704780459404,
+      "learning_rate": 0.00018118351334540833,
+      "loss": 0.28846466541290283,
+      "step": 390
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "grad_norm": 0.20759014785289764,
+      "learning_rate": 0.00018008938916776323,
+      "loss": 0.30964126586914065,
+      "step": 400
+    },
+    {
+      "epoch": 0.6283524904214559,
+      "grad_norm": 0.1952156275510788,
+      "learning_rate": 0.00017896785007117524,
+      "loss": 0.306485652923584,
+      "step": 410
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.16880711913108826,
+      "learning_rate": 0.0001778192799629727,
+      "loss": 0.3217456579208374,
+      "step": 420
+    },
+    {
+      "epoch": 0.6590038314176245,
+      "grad_norm": 0.2303844839334488,
+      "learning_rate": 0.00017664407200330767,
+      "loss": 0.28161351680755614,
+      "step": 430
+    },
+    {
+      "epoch": 0.6743295019157088,
+      "grad_norm": 0.2218875139951706,
+      "learning_rate": 0.00017544262847057532,
+      "loss": 0.2977366209030151,
+      "step": 440
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.20623792707920074,
+      "learning_rate": 0.00017421536062371286,
+      "loss": 0.29798321723937987,
+      "step": 450
+    },
+    {
+      "epoch": 0.7049808429118773,
+      "grad_norm": 0.22805136442184448,
+      "learning_rate": 0.00017296268856142365,
+      "loss": 0.2869698524475098,
+      "step": 460
+    },
+    {
+      "epoch": 0.7203065134099617,
+      "grad_norm": 0.19344043731689453,
+      "learning_rate": 0.00017168504107837582,
+      "loss": 0.2964784145355225,
+      "step": 470
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.2286471724510193,
+      "learning_rate": 0.00017038285551842412,
+      "loss": 0.302842903137207,
+      "step": 480
+    },
+    {
+      "epoch": 0.7509578544061303,
+      "grad_norm": 0.19522379338741302,
+      "learning_rate": 0.00016905657762490548,
+      "loss": 0.3244823694229126,
+      "step": 490
+    },
+    {
+      "epoch": 0.7662835249042146,
+      "grad_norm": 0.1601998209953308,
+      "learning_rate": 0.00016770666138805904,
+      "loss": 0.2811170816421509,
+      "step": 500
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.16715656220912933,
+      "learning_rate": 0.0001663335688896237,
+      "loss": 0.2751513719558716,
+      "step": 510
+    },
+    {
+      "epoch": 0.7969348659003831,
+      "grad_norm": 0.19661696255207062,
+      "learning_rate": 0.00016493777014466563,
+      "loss": 0.3170422077178955,
+      "step": 520
+    },
+    {
+      "epoch": 0.8122605363984674,
+      "grad_norm": 0.18826834857463837,
+      "learning_rate": 0.0001635197429406901,
+      "loss": 0.2818011283874512,
+      "step": 530
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.18041561543941498,
+      "learning_rate": 0.00016207997267409313,
+      "loss": 0.30449423789978025,
+      "step": 540
+    },
+    {
+      "epoch": 0.842911877394636,
+      "grad_norm": 0.1955738365650177,
+      "learning_rate": 0.00016061895218400806,
+      "loss": 0.2753497362136841,
+      "step": 550
+    },
+    {
+      "epoch": 0.8582375478927203,
+      "grad_norm": 0.19417400658130646,
+      "learning_rate": 0.0001591371815836051,
+      "loss": 0.28362064361572265,
+      "step": 560
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.1948927491903305,
+      "learning_rate": 0.00015763516808890024,
+      "loss": 0.2855699062347412,
+      "step": 570
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.18820644915103912,
+      "learning_rate": 0.00015611342584513342,
+      "loss": 0.28289546966552737,
+      "step": 580
+    },
+    {
+      "epoch": 0.9042145593869731,
+      "grad_norm": 0.18016715347766876,
+      "learning_rate": 0.00015457247575077445,
+      "loss": 0.29960951805114744,
+      "step": 590
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.22913143038749695,
+      "learning_rate": 0.0001530128452792174,
+      "loss": 0.28281118869781496,
+      "step": 600
+    },
+    {
+      "epoch": 0.9348659003831418,
+      "grad_norm": 0.20966900885105133,
+      "learning_rate": 0.00015143506829822426,
+      "loss": 0.30697131156921387,
+      "step": 610
+    },
+    {
+      "epoch": 0.9501915708812261,
+      "grad_norm": 0.2458924800157547,
+      "learning_rate": 0.00014983968488718006,
+      "loss": 0.30470201969146726,
+      "step": 620
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.18874205648899078,
+      "learning_rate": 0.00014822724115222128,
+      "loss": 0.30251691341400144,
+      "step": 630
+    },
+    {
+      "epoch": 0.9808429118773946,
+      "grad_norm": 0.22530531883239746,
+      "learning_rate": 0.00014659828903930178,
+      "loss": 0.29744977951049806,
+      "step": 640
+    },
+    {
+      "epoch": 0.9961685823754789,
+      "grad_norm": 0.20111751556396484,
+      "learning_rate": 0.00014495338614525926,
+      "loss": 0.28247039318084716,
+      "step": 650
+    },
+    {
+      "epoch": 1.010727969348659,
+      "grad_norm": 0.17702056467533112,
+      "learning_rate": 0.00014329309552694783,
+      "loss": 0.2753941774368286,
+      "step": 660
+    },
+    {
+      "epoch": 1.0260536398467432,
+      "grad_norm": 0.17669467628002167,
+      "learning_rate": 0.00014161798550850124,
+      "loss": 0.2545931816101074,
+      "step": 670
+    },
+    {
+      "epoch": 1.0413793103448277,
+      "grad_norm": 0.1835271567106247,
+      "learning_rate": 0.00013992862948679333,
+      "loss": 0.24901304244995118,
+      "step": 680
+    },
+    {
+      "epoch": 1.0567049808429119,
+      "grad_norm": 0.19968923926353455,
+      "learning_rate": 0.00013822560573516194,
+      "loss": 0.27475411891937257,
+      "step": 690
+    },
+    {
+      "epoch": 1.072030651340996,
+      "grad_norm": 0.17976751923561096,
+      "learning_rate": 0.00013650949720546372,
+      "loss": 0.2584954023361206,
+      "step": 700
+    },
+    {
+      "epoch": 1.0873563218390805,
+      "grad_norm": 0.19866906106472015,
+      "learning_rate": 0.00013478089132852716,
+      "loss": 0.26185197830200196,
+      "step": 710
+    },
+    {
+      "epoch": 1.1026819923371647,
+      "grad_norm": 0.2139822244644165,
+      "learning_rate": 0.0001330403798130729,
+      "loss": 0.2664598226547241,
+      "step": 720
+    },
+    {
+      "epoch": 1.118007662835249,
+      "grad_norm": 0.1918357014656067,
+      "learning_rate": 0.00013128855844316944,
+      "loss": 0.26914339065551757,
+      "step": 730
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.21598224341869354,
+      "learning_rate": 0.00012952602687429362,
+      "loss": 0.24881536960601808,
+      "step": 740
+    },
+    {
+      "epoch": 1.1486590038314177,
+      "grad_norm": 0.16682575643062592,
+      "learning_rate": 0.00012775338842806647,
+      "loss": 0.2527227163314819,
+      "step": 750
+    },
+    {
+      "epoch": 1.163984674329502,
+      "grad_norm": 0.18836885690689087,
+      "learning_rate": 0.00012597124988573353,
+      "loss": 0.2735306739807129,
+      "step": 760
+    },
+    {
+      "epoch": 1.1793103448275861,
+      "grad_norm": 0.20422716438770294,
+      "learning_rate": 0.00012418022128046142,
+      "loss": 0.2547746181488037,
+      "step": 770
+    },
+    {
+      "epoch": 1.1946360153256705,
+      "grad_norm": 0.18123748898506165,
+      "learning_rate": 0.00012238091568852086,
+      "loss": 0.2550168037414551,
+      "step": 780
+    },
+    {
+      "epoch": 1.2099616858237547,
+      "grad_norm": 0.1850244104862213,
+      "learning_rate": 0.00012057394901942834,
+      "loss": 0.2556851148605347,
+      "step": 790
+    },
+    {
+      "epoch": 1.2252873563218392,
+      "grad_norm": 0.18734942376613617,
+      "learning_rate": 0.00011875993980511773,
+      "loss": 0.25217125415802,
+      "step": 800
+    },
+    {
+      "epoch": 1.2406130268199234,
+      "grad_norm": 0.25744232535362244,
+      "learning_rate": 0.00011693950898821442,
+      "loss": 0.25321738719940184,
+      "step": 810
+    },
+    {
+      "epoch": 1.2559386973180078,
+      "grad_norm": 0.24140717089176178,
+      "learning_rate": 0.00011511327970948398,
+      "loss": 0.2695934295654297,
+      "step": 820
+    },
+    {
+      "epoch": 1.271264367816092,
+      "grad_norm": 0.19622239470481873,
+      "learning_rate": 0.00011328187709452884,
+      "loss": 0.25709664821624756,
+      "step": 830
+    },
+    {
+      "epoch": 1.2865900383141762,
+      "grad_norm": 0.18637792766094208,
+      "learning_rate": 0.00011144592803980507,
+      "loss": 0.25869600772857665,
+      "step": 840
+    },
+    {
+      "epoch": 1.3019157088122606,
+      "grad_norm": 0.19393154978752136,
+      "learning_rate": 0.00010960606099803339,
+      "loss": 0.2554497003555298,
+      "step": 850
+    },
+    {
+      "epoch": 1.3172413793103448,
+      "grad_norm": 0.2453709989786148,
+      "learning_rate": 0.0001077629057630771,
+      "loss": 0.26648812294006347,
+      "step": 860
+    },
+    {
+      "epoch": 1.332567049808429,
+      "grad_norm": 0.25964638590812683,
+      "learning_rate": 0.00010591709325436123,
+      "loss": 0.26240499019622804,
+      "step": 870
+    },
+    {
+      "epoch": 1.3478927203065134,
+      "grad_norm": 0.21236255764961243,
+      "learning_rate": 0.00010406925530090625,
+      "loss": 0.26952788829803465,
+      "step": 880
+    },
+    {
+      "epoch": 1.3632183908045978,
+      "grad_norm": 0.20102430880069733,
+      "learning_rate": 0.00010222002442505056,
+      "loss": 0.2485269546508789,
+      "step": 890
+    },
+    {
+      "epoch": 1.378544061302682,
+      "grad_norm": 0.23220829665660858,
+      "learning_rate": 0.00010037003362593544,
+      "loss": 0.2720418214797974,
+      "step": 900
+    },
+    {
+      "epoch": 1.3938697318007662,
+      "grad_norm": 0.21482332050800323,
+      "learning_rate": 9.85199161628269e-05,
+      "loss": 0.24709177017211914,
+      "step": 910
+    },
+    {
+      "epoch": 1.4091954022988507,
+      "grad_norm": 0.24010054767131805,
+      "learning_rate": 9.667030533834862e-05,
+      "loss": 0.25513901710510256,
+      "step": 920
+    },
+    {
+      "epoch": 1.4245210727969349,
+      "grad_norm": 0.19649599492549896,
+      "learning_rate": 9.482183428169975e-05,
+      "loss": 0.2543267965316772,
+      "step": 930
+    },
+    {
+      "epoch": 1.439846743295019,
+      "grad_norm": 0.217982679605484,
+      "learning_rate": 9.297513573193246e-05,
+      "loss": 0.256868314743042,
+      "step": 940
+    },
+    {
+      "epoch": 1.4551724137931035,
+      "grad_norm": 0.24914859235286713,
+      "learning_rate": 9.113084182136266e-05,
+      "loss": 0.24767658710479737,
+      "step": 950
+    },
+    {
+      "epoch": 1.4704980842911877,
+      "grad_norm": 0.2257557511329651,
+      "learning_rate": 8.928958385918855e-05,
+      "loss": 0.2683919668197632,
+      "step": 960
+    },
+    {
+      "epoch": 1.485823754789272,
+      "grad_norm": 0.21158252656459808,
+      "learning_rate": 8.745199211539117e-05,
+      "loss": 0.24358506202697755,
+      "step": 970
+    },
+    {
+      "epoch": 1.5011494252873563,
+      "grad_norm": 0.20610959827899933,
+      "learning_rate": 8.561869560499016e-05,
+      "loss": 0.27091827392578127,
+      "step": 980
+    },
+    {
+      "epoch": 1.5164750957854407,
+      "grad_norm": 0.17570218443870544,
+      "learning_rate": 8.379032187272968e-05,
+      "loss": 0.2440960168838501,
+      "step": 990
+    },
+    {
+      "epoch": 1.531800766283525,
+      "grad_norm": 0.18110089004039764,
+      "learning_rate": 8.196749677826713e-05,
+      "loss": 0.2696054935455322,
+      "step": 1000
+    },
+    {
+      "epoch": 1.547126436781609,
+      "grad_norm": 0.19731608033180237,
+      "learning_rate": 8.015084428193895e-05,
+      "loss": 0.26104373931884767,
+      "step": 1010
+    },
+    {
+      "epoch": 1.5624521072796935,
+      "grad_norm": 0.20462389290332794,
+      "learning_rate": 7.834098623117652e-05,
+      "loss": 0.2606567144393921,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5777777777777777,
+      "grad_norm": 0.21685872972011566,
+      "learning_rate": 7.65385421476453e-05,
+      "loss": 0.26782615184783937,
+      "step": 1030
+    },
+    {
+      "epoch": 1.593103448275862,
+      "grad_norm": 0.20966307818889618,
+      "learning_rate": 7.474412901517997e-05,
+      "loss": 0.26112306118011475,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6084291187739463,
+      "grad_norm": 0.19245949387550354,
+      "learning_rate": 7.295836106858854e-05,
+      "loss": 0.2425548553466797,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6237547892720308,
+      "grad_norm": 0.207347109913826,
+      "learning_rate": 7.118184958339713e-05,
+      "loss": 0.2567357301712036,
+      "step": 1060
+    },
+    {
+      "epoch": 1.639080459770115,
+      "grad_norm": 0.20875895023345947,
+      "learning_rate": 6.941520266660818e-05,
+      "loss": 0.26581392288208006,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6544061302681992,
+      "grad_norm": 0.20320458710193634,
+      "learning_rate": 6.765902504854276e-05,
+      "loss": 0.25880563259124756,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6697318007662836,
+      "grad_norm": 0.2191975712776184,
+      "learning_rate": 6.59139178758389e-05,
+      "loss": 0.2446974515914917,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6850574712643678,
+      "grad_norm": 0.19045910239219666,
+      "learning_rate": 6.418047850567699e-05,
+      "loss": 0.2456514596939087,
+      "step": 1100
+    },
+    {
+      "epoch": 1.700383141762452,
+      "grad_norm": 0.2059805542230606,
+      "learning_rate": 6.24593003013018e-05,
+      "loss": 0.25358903408050537,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7157088122605364,
+      "grad_norm": 0.22913187742233276,
+      "learning_rate": 6.075097242891179e-05,
+      "loss": 0.2545517921447754,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7310344827586208,
+      "grad_norm": 0.21482746303081512,
+      "learning_rate": 5.905607965598542e-05,
+      "loss": 0.26140122413635253,
+      "step": 1130
+    },
+    {
+      "epoch": 1.746360153256705,
+      "grad_norm": 0.17455799877643585,
+      "learning_rate": 5.737520215111256e-05,
+      "loss": 0.2500907897949219,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7616858237547892,
+      "grad_norm": 0.19934211671352386,
+      "learning_rate": 5.5708915285400934e-05,
+      "loss": 0.2561262369155884,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7770114942528736,
+      "grad_norm": 0.22233599424362183,
+      "learning_rate": 5.4057789435523734e-05,
+      "loss": 0.27218654155731203,
+      "step": 1160
+    },
+    {
+      "epoch": 1.7923371647509578,
+      "grad_norm": 0.19874989986419678,
+      "learning_rate": 5.242238978847772e-05,
+      "loss": 0.25201215744018557,
+      "step": 1170
+    },
+    {
+      "epoch": 1.807662835249042,
+      "grad_norm": 0.20110537111759186,
+      "learning_rate": 5.080327614811746e-05,
+      "loss": 0.24972200393676758,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8229885057471265,
+      "grad_norm": 0.18864119052886963,
+      "learning_rate": 4.920100274353218e-05,
+      "loss": 0.2667801856994629,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8383141762452109,
+      "grad_norm": 0.20197594165802002,
+      "learning_rate": 4.761611803933072e-05,
+      "loss": 0.2678064823150635,
+      "step": 1200
+    },
+    {
+      "epoch": 1.853639846743295,
+      "grad_norm": 0.1802796870470047,
+      "learning_rate": 4.604916454790027e-05,
+      "loss": 0.25614442825317385,
+      "step": 1210
+    },
+    {
+      "epoch": 1.8689655172413793,
+      "grad_norm": 0.26386988162994385,
+      "learning_rate": 4.450067864370187e-05,
+      "loss": 0.24004197120666504,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8842911877394637,
+      "grad_norm": 0.19681376218795776,
+      "learning_rate": 4.297119037966755e-05,
+      "loss": 0.2666898488998413,
+      "step": 1230
+    },
+    {
+      "epoch": 1.899616858237548,
+      "grad_norm": 0.21600529551506042,
+      "learning_rate": 4.146122330576087e-05,
+      "loss": 0.2697048902511597,
+      "step": 1240
+    },
+    {
+      "epoch": 1.914942528735632,
+      "grad_norm": 0.2030036747455597,
+      "learning_rate": 3.997129428976374e-05,
+      "loss": 0.2609272003173828,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9302681992337165,
+      "grad_norm": 0.22189973294734955,
+      "learning_rate": 3.8501913340350625e-05,
+      "loss": 0.2639767169952393,
+      "step": 1260
+    },
+    {
+      "epoch": 1.945593869731801,
+      "grad_norm": 0.2469155639410019,
+      "learning_rate": 3.7053583432510406e-05,
+      "loss": 0.26217553615570066,
+      "step": 1270
+    },
+    {
+      "epoch": 1.960919540229885,
+      "grad_norm": 0.23733453452587128,
+      "learning_rate": 3.5626800335375976e-05,
+      "loss": 0.26022138595581057,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9762452107279693,
+      "grad_norm": 0.1800413727760315,
+      "learning_rate": 3.422205244252067e-05,
+      "loss": 0.2549219369888306,
+      "step": 1290
+    },
+    {
+      "epoch": 1.9915708812260537,
+      "grad_norm": 0.21898971498012543,
+      "learning_rate": 3.283982060477895e-05,
+      "loss": 0.2534105062484741,
+      "step": 1300
+    },
+    {
+      "epoch": 2.0061302681992337,
+      "grad_norm": 0.19016309082508087,
+      "learning_rate": 3.148057796564944e-05,
+      "loss": 0.25081026554107666,
+      "step": 1310
+    },
+    {
+      "epoch": 2.021455938697318,
+      "grad_norm": 0.18190482258796692,
+      "learning_rate": 3.014478979933595e-05,
+      "loss": 0.2276550054550171,
+      "step": 1320
+    },
+    {
+      "epoch": 2.036781609195402,
+      "grad_norm": 0.1764170229434967,
+      "learning_rate": 2.8832913351482148e-05,
+      "loss": 0.22775135040283204,
+      "step": 1330
+    },
+    {
+      "epoch": 2.0521072796934865,
+      "grad_norm": 0.20627553761005402,
+      "learning_rate": 2.7545397682654695e-05,
+      "loss": 0.2405186414718628,
+      "step": 1340
+    },
+    {
+      "epoch": 2.067432950191571,
+      "grad_norm": 0.17293164134025574,
+      "learning_rate": 2.628268351462785e-05,
+      "loss": 0.23299973011016845,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0827586206896553,
+      "grad_norm": 0.21754054725170135,
+      "learning_rate": 2.5045203079522862e-05,
+      "loss": 0.22688329219818115,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0980842911877393,
+      "grad_norm": 0.17403560876846313,
+      "learning_rate": 2.3833379971852987e-05,
+      "loss": 0.2133577823638916,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1134099616858237,
+      "grad_norm": 0.2100820094347,
+      "learning_rate": 2.2647629003525428e-05,
+      "loss": 0.22004613876342774,
+      "step": 1380
+    },
+    {
+      "epoch": 2.128735632183908,
+      "grad_norm": 0.23395074903964996,
+      "learning_rate": 2.1488356061849636e-05,
+      "loss": 0.22840588092803954,
+      "step": 1390
+    },
+    {
+      "epoch": 2.144061302681992,
+      "grad_norm": 0.2112017124891281,
+      "learning_rate": 2.0355957970600403e-05,
+      "loss": 0.23168041706085205,
+      "step": 1400
+    },
+    {
+      "epoch": 2.1593869731800766,
+      "grad_norm": 0.21420609951019287,
+      "learning_rate": 1.925082235418346e-05,
+      "loss": 0.22593750953674316,
+      "step": 1410
+    },
+    {
+      "epoch": 2.174712643678161,
+      "grad_norm": 0.19721633195877075,
+      "learning_rate": 1.817332750495012e-05,
+      "loss": 0.2368011951446533,
+      "step": 1420
+    },
+    {
+      "epoch": 2.1900383141762454,
+      "grad_norm": 0.22296306490898132,
+      "learning_rate": 1.7123842253706302e-05,
+      "loss": 0.22809298038482667,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2053639846743294,
+      "grad_norm": 0.2142433077096939,
+      "learning_rate": 1.6102725843460277e-05,
+      "loss": 0.22773525714874268,
+      "step": 1440
+    },
+    {
+      "epoch": 2.220689655172414,
+      "grad_norm": 0.2203645557165146,
+      "learning_rate": 1.5110327806452362e-05,
+      "loss": 0.23412787914276123,
+      "step": 1450
+    },
+    {
+      "epoch": 2.236015325670498,
+      "grad_norm": 0.23082444071769714,
+      "learning_rate": 1.4146987844508508e-05,
+      "loss": 0.2073367118835449,
+      "step": 1460
+    },
+    {
+      "epoch": 2.251340996168582,
+      "grad_norm": 0.22913500666618347,
+      "learning_rate": 1.321303571275917e-05,
+      "loss": 0.21699509620666504,
+      "step": 1470
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.20030102133750916,
+      "learning_rate": 1.2308791106762718e-05,
+      "loss": 0.21742606163024902,
+      "step": 1480
+    },
+    {
+      "epoch": 2.281992337164751,
+      "grad_norm": 0.2148463875055313,
+      "learning_rate": 1.143456355307233e-05,
+      "loss": 0.2208996295928955,
+      "step": 1490
+    },
+    {
+      "epoch": 2.2973180076628354,
+      "grad_norm": 0.2605825662612915,
+      "learning_rate": 1.0590652303283932e-05,
+      "loss": 0.2229763984680176,
+      "step": 1500
+    },
+    {
+      "epoch": 2.3126436781609194,
+      "grad_norm": 0.228949174284935,
+      "learning_rate": 9.777346231601037e-06,
+      "loss": 0.22366030216217042,
+      "step": 1510
+    },
+    {
+      "epoch": 2.327969348659004,
+      "grad_norm": 0.23017998039722443,
+      "learning_rate": 8.994923735952032e-06,
+      "loss": 0.22504253387451173,
+      "step": 1520
+    },
+    {
+      "epoch": 2.3432950191570883,
+      "grad_norm": 0.20919591188430786,
+      "learning_rate": 8.243652642693478e-06,
+      "loss": 0.22776470184326172,
+      "step": 1530
+    },
+    {
+      "epoch": 2.3586206896551722,
+      "grad_norm": 0.203067809343338,
+      "learning_rate": 7.523790114931961e-06,
+      "loss": 0.2204723358154297,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3739463601532567,
+      "grad_norm": 0.27626660466194153,
+      "learning_rate": 6.835582564496256e-06,
+      "loss": 0.24098660945892333,
+      "step": 1550
+    },
+    {
+      "epoch": 2.389272030651341,
+      "grad_norm": 0.2158137708902359,
+      "learning_rate": 6.179265567589509e-06,
+      "loss": 0.23224225044250488,
+      "step": 1560
+    },
+    {
+      "epoch": 2.4045977011494255,
+      "grad_norm": 0.22840788960456848,
+      "learning_rate": 5.5550637841505045e-06,
+      "loss": 0.24213042259216308,
+      "step": 1570
+    },
+    {
+      "epoch": 2.4199233716475095,
+      "grad_norm": 0.22339899837970734,
+      "learning_rate": 4.963190880951807e-06,
+      "loss": 0.2249614715576172,
+      "step": 1580
+    },
+    {
+      "epoch": 2.435249042145594,
+      "grad_norm": 0.23574717342853546,
+      "learning_rate": 4.403849458460629e-06,
+      "loss": 0.2342482328414917,
+      "step": 1590
+    },
+    {
+      "epoch": 2.4505747126436783,
+      "grad_norm": 0.20539292693138123,
+      "learning_rate": 3.877230981487934e-06,
+      "loss": 0.23070881366729737,
+      "step": 1600
+    },
+    {
+      "epoch": 2.4659003831417623,
+      "grad_norm": 0.2082466185092926,
+      "learning_rate": 3.3835157136493435e-06,
+      "loss": 0.22563157081604004,
+      "step": 1610
+    },
+    {
+      "epoch": 2.4812260536398467,
+      "grad_norm": 0.22585122287273407,
+      "learning_rate": 2.9228726556599916e-06,
+      "loss": 0.2235992431640625,
+      "step": 1620
+    },
+    {
+      "epoch": 2.496551724137931,
+      "grad_norm": 0.21266688406467438,
+      "learning_rate": 2.495459487485119e-06,
+      "loss": 0.22575080394744873,
+      "step": 1630
+    },
+    {
+      "epoch": 2.5118773946360156,
+      "grad_norm": 0.19549226760864258,
+      "learning_rate": 2.1014225143654143e-06,
+      "loss": 0.21721582412719725,
+      "step": 1640
+    },
+    {
+      "epoch": 2.5272030651340995,
+      "grad_norm": 0.22203820943832397,
+      "learning_rate": 1.7408966167362317e-06,
+      "loss": 0.22829241752624513,
+      "step": 1650
+    },
+    {
+      "epoch": 2.542528735632184,
+      "grad_norm": 0.19951409101486206,
+      "learning_rate": 1.4140052040574891e-06,
+      "loss": 0.21612203121185303,
+      "step": 1660
+    },
+    {
+      "epoch": 2.557854406130268,
+      "grad_norm": 0.23988863825798035,
+      "learning_rate": 1.1208601725700374e-06,
+      "loss": 0.22502026557922364,
+      "step": 1670
+    },
+    {
+      "epoch": 2.5731800766283524,
+      "grad_norm": 0.23238494992256165,
+      "learning_rate": 8.615618669931991e-07,
+      "loss": 0.22191386222839354,
+      "step": 1680
+    },
+    {
+      "epoch": 2.5885057471264368,
+      "grad_norm": 0.26193344593048096,
+      "learning_rate": 6.361990461763667e-07,
+      "loss": 0.22765371799468995,
+      "step": 1690
+    },
+    {
+      "epoch": 2.603831417624521,
+      "grad_norm": 0.18539129197597504,
+      "learning_rate": 4.4484885271641743e-07,
+      "loss": 0.22877717018127441,
+      "step": 1700
+    },
+    {
+      "epoch": 2.6191570881226056,
+      "grad_norm": 0.1966504156589508,
+      "learning_rate": 2.8757678655161324e-07,
+      "loss": 0.22611801624298095,
+      "step": 1710
+    },
+    {
+      "epoch": 2.6344827586206896,
+      "grad_norm": 0.22333666682243347,
+      "learning_rate": 1.6443668254059185e-07,
+      "loss": 0.22234044075012208,
+      "step": 1720
+    },
+    {
+      "epoch": 2.649808429118774,
+      "grad_norm": 0.23859316110610962,
+      "learning_rate": 7.54706920345738e-08,
+      "loss": 0.2371755838394165,
+      "step": 1730
+    },
+    {
+      "epoch": 2.665134099616858,
+      "grad_norm": 0.22455042600631714,
+      "learning_rate": 2.070926844869314e-08,
+      "loss": 0.2336733818054199,
+      "step": 1740
+    },
+    {
+      "epoch": 2.6804597701149424,
+      "grad_norm": 0.27831825613975525,
+      "learning_rate": 1.7115683776935953e-10,
+      "loss": 0.23413031101226806,
+      "step": 1750
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6266513605911757e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a0dace2cc4eb22cc895e26540e9207a0c24ec0150b8e0768b062a4fcc440ba
+size 5201

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e15eef7fad2e785ae60d98c1c8e9d44602ddba227f29df1c58475320ea045db7
+oid sha256:d0a0dace2cc4eb22cc895e26540e9207a0c24ec0150b8e0768b062a4fcc440ba
 size 5201