Add H100-trained Phi-4 model assets

README.md

@@ -1,202 +1,38 @@
 ---
 base_model: microsoft/phi-4
 library_name: peft
+model_name: peleke-phi-4
+tags:
+- base_model:adapter:microsoft/phi-4
+- lora
+- sft
+- transformers
+- trl
+licence: gpl-3
+pipeline_tag: text-generation
 ---
 
-# Model Card for Model ID
+# Model Card for peleke-phi-4
 
-<!-- Provide a quick summary of what the model is/does. -->
+This model is a fine-tuned version of [microsoft/phi-4](https://huggingface.co/microsoft/phi-4).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
+## Quick start
 
+```python
+# Coming Soon...
+```
 
-## Model Details
+## Training procedure
 
-### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+This model was trained with SFT.
 
-
-
-- **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 0.15.2
+- PEFT 0.17.0
+- TRL: 0.19.1
+- Transformers: 4.54.0
+- Pytorch: 2.7.1
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2

adapter_config.json

@@ -20,15 +20,18 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "qalora_group_size": 16,
   "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "qkv_proj"
+    "qkv_proj",
+    "o_proj"
   ],
+  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d6851a5df88091ca237b847c4659b23f98d16951db397593e87ced71c766a38
-size 2084824272
+oid sha256:20c0b64281bc70f776d92e118ff8db05bb2541587ffd1cb94d239632980b20f9
+size 2084803792

optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d488fe514b22a65589b90ffc1639497cc18bee6eac9bfb258ab143195cde3c2d
-size 59117259

rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5671e5814bc2b50e8ca672217a479b935e2e09221f419b16f33a4d73cf1ea4f2
-size 14645

scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc302c1ea6f8760b538d34aa63eb10e75b8051a0525238af5b340d810a2f312c
-size 1383

scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:76d499ff7f9713e6ce83515f64a51745b01dce3e0c41d165acffd8052e740f14
-size 1465

special_tokens_map.json

@@ -1,4 +1,20 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<epi>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</epi>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": true,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 800,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -866,6 +871,42 @@
       "rstrip": true,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 100352,
+      "content": "<epi>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 100353,
+      "content": "</epi>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 100354,
+      "content": "Antigen",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": false
+    },
+    {
+      "id": 100355,
+      "content": "Antibody",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": false
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -768,8 +768,44 @@
       "rstrip": true,
       "single_word": false,
       "special": true
+    },
+    "100352": {
+      "content": "<epi>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100353": {
+      "content": "</epi>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100354": {
+      "content": "Antigen",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100355": {
+      "content": "Antibody",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
+  "additional_special_tokens": [
+    "<epi>",
+    "</epi>"
+  ],
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",

trainer_state.json

@@ -1,1177 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "eval_steps": 500,
-  "global_step": 3177,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.023607176581680833,
-      "grad_norm": 0.8597469329833984,
-      "learning_rate": 0.00017600000000000002,
-      "loss": 4.9024,
-      "mean_token_accuracy": 0.2909739096462727,
-      "num_tokens": 86323.0,
-      "step": 25
-    },
-    {
-      "epoch": 0.047214353163361665,
-      "grad_norm": 0.7611781358718872,
-      "learning_rate": 0.0001986040609137056,
-      "loss": 4.3579,
-      "mean_token_accuracy": 0.3365874075889587,
-      "num_tokens": 170088.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.0708215297450425,
-      "grad_norm": 0.8384687900543213,
-      "learning_rate": 0.00019701776649746192,
-      "loss": 4.2579,
-      "mean_token_accuracy": 0.33202287018299104,
-      "num_tokens": 248841.0,
-      "step": 75
-    },
-    {
-      "epoch": 0.09442870632672333,
-      "grad_norm": 0.8371444940567017,
-      "learning_rate": 0.00019543147208121828,
-      "loss": 3.9475,
-      "mean_token_accuracy": 0.3752408367395401,
-      "num_tokens": 331838.0,
-      "step": 100
-    },
-    {
-      "epoch": 0.11803588290840415,
-      "grad_norm": 1.3010390996932983,
-      "learning_rate": 0.00019384517766497464,
-      "loss": 3.6464,
-      "mean_token_accuracy": 0.4282234400510788,
-      "num_tokens": 416982.0,
-      "step": 125
-    },
-    {
-      "epoch": 0.141643059490085,
-      "grad_norm": 1.102060079574585,
-      "learning_rate": 0.000192258883248731,
-      "loss": 3.6204,
-      "mean_token_accuracy": 0.42927508473396303,
-      "num_tokens": 501322.0,
-      "step": 150
-    },
-    {
-      "epoch": 0.1652502360717658,
-      "grad_norm": 1.1159696578979492,
-      "learning_rate": 0.00019067258883248732,
-      "loss": 3.5222,
-      "mean_token_accuracy": 0.4415357458591461,
-      "num_tokens": 591622.0,
-      "step": 175
-    },
-    {
-      "epoch": 0.18885741265344666,
-      "grad_norm": 3.7764205932617188,
-      "learning_rate": 0.00018908629441624365,
-      "loss": 3.6167,
-      "mean_token_accuracy": 0.42590244352817536,
-      "num_tokens": 681171.0,
-      "step": 200
-    },
-    {
-      "epoch": 0.21246458923512748,
-      "grad_norm": 1.3314100503921509,
-      "learning_rate": 0.0001875,
-      "loss": 3.7327,
-      "mean_token_accuracy": 0.4113136053085327,
-      "num_tokens": 762751.0,
-      "step": 225
-    },
-    {
-      "epoch": 0.2360717658168083,
-      "grad_norm": 1.455350637435913,
-      "learning_rate": 0.00018591370558375636,
-      "loss": 3.3504,
-      "mean_token_accuracy": 0.47106861472129824,
-      "num_tokens": 851051.0,
-      "step": 250
-    },
-    {
-      "epoch": 0.25967894239848915,
-      "grad_norm": 1.2478972673416138,
-      "learning_rate": 0.00018432741116751272,
-      "loss": 3.4177,
-      "mean_token_accuracy": 0.46144390881061553,
-      "num_tokens": 937834.0,
-      "step": 275
-    },
-    {
-      "epoch": 0.28328611898017,
-      "grad_norm": 1.6548963785171509,
-      "learning_rate": 0.00018274111675126904,
-      "loss": 3.4914,
-      "mean_token_accuracy": 0.450729478597641,
-      "num_tokens": 1017911.0,
-      "step": 300
-    },
-    {
-      "epoch": 0.3068932955618508,
-      "grad_norm": 1.7462213039398193,
-      "learning_rate": 0.0001811548223350254,
-      "loss": 3.2948,
-      "mean_token_accuracy": 0.4845814883708954,
-      "num_tokens": 1103573.0,
-      "step": 325
-    },
-    {
-      "epoch": 0.3305004721435316,
-      "grad_norm": 1.2442463636398315,
-      "learning_rate": 0.00017956852791878173,
-      "loss": 3.351,
-      "mean_token_accuracy": 0.473716744184494,
-      "num_tokens": 1190283.0,
-      "step": 350
-    },
-    {
-      "epoch": 0.35410764872521244,
-      "grad_norm": 0.9460684657096863,
-      "learning_rate": 0.00017798223350253808,
-      "loss": 3.3257,
-      "mean_token_accuracy": 0.48253663778305056,
-      "num_tokens": 1275756.0,
-      "step": 375
-    },
-    {
-      "epoch": 0.3777148253068933,
-      "grad_norm": 1.3959977626800537,
-      "learning_rate": 0.0001763959390862944,
-      "loss": 3.3016,
-      "mean_token_accuracy": 0.48651802659034726,
-      "num_tokens": 1359058.0,
-      "step": 400
-    },
-    {
-      "epoch": 0.40132200188857414,
-      "grad_norm": 1.5676658153533936,
-      "learning_rate": 0.00017480964467005077,
-      "loss": 3.0587,
-      "mean_token_accuracy": 0.5262654614448548,
-      "num_tokens": 1447793.0,
-      "step": 425
-    },
-    {
-      "epoch": 0.42492917847025496,
-      "grad_norm": 1.6668205261230469,
-      "learning_rate": 0.00017322335025380712,
-      "loss": 2.9721,
-      "mean_token_accuracy": 0.542415668964386,
-      "num_tokens": 1533910.0,
-      "step": 450
-    },
-    {
-      "epoch": 0.4485363550519358,
-      "grad_norm": 1.1585041284561157,
-      "learning_rate": 0.00017163705583756348,
-      "loss": 2.9116,
-      "mean_token_accuracy": 0.5552564060688019,
-      "num_tokens": 1620704.0,
-      "step": 475
-    },
-    {
-      "epoch": 0.4721435316336166,
-      "grad_norm": 1.7781224250793457,
-      "learning_rate": 0.0001700507614213198,
-      "loss": 2.9046,
-      "mean_token_accuracy": 0.5538024806976318,
-      "num_tokens": 1706296.0,
-      "step": 500
-    },
-    {
-      "epoch": 0.49575070821529743,
-      "grad_norm": 2.213106632232666,
-      "learning_rate": 0.00016846446700507614,
-      "loss": 3.0646,
-      "mean_token_accuracy": 0.5227190399169922,
-      "num_tokens": 1791100.0,
-      "step": 525
-    },
-    {
-      "epoch": 0.5193578847969783,
-      "grad_norm": 4.082686901092529,
-      "learning_rate": 0.0001668781725888325,
-      "loss": 3.081,
-      "mean_token_accuracy": 0.523969988822937,
-      "num_tokens": 1869553.0,
-      "step": 550
-    },
-    {
-      "epoch": 0.5429650613786591,
-      "grad_norm": 1.7952462434768677,
-      "learning_rate": 0.00016529187817258885,
-      "loss": 3.2597,
-      "mean_token_accuracy": 0.496154887676239,
-      "num_tokens": 1949366.0,
-      "step": 575
-    },
-    {
-      "epoch": 0.56657223796034,
-      "grad_norm": 1.9742423295974731,
-      "learning_rate": 0.0001637055837563452,
-      "loss": 3.0122,
-      "mean_token_accuracy": 0.5359121215343475,
-      "num_tokens": 2034686.0,
-      "step": 600
-    },
-    {
-      "epoch": 0.5901794145420207,
-      "grad_norm": 1.3130273818969727,
-      "learning_rate": 0.00016211928934010153,
-      "loss": 3.0088,
-      "mean_token_accuracy": 0.5349772965908051,
-      "num_tokens": 2121997.0,
-      "step": 625
-    },
-    {
-      "epoch": 0.6137865911237016,
-      "grad_norm": 1.7737120389938354,
-      "learning_rate": 0.00016053299492385786,
-      "loss": 2.8518,
-      "mean_token_accuracy": 0.5664570724964142,
-      "num_tokens": 2209709.0,
-      "step": 650
-    },
-    {
-      "epoch": 0.6373937677053825,
-      "grad_norm": 1.397939682006836,
-      "learning_rate": 0.00015894670050761421,
-      "loss": 2.7886,
-      "mean_token_accuracy": 0.5750785338878631,
-      "num_tokens": 2295052.0,
-      "step": 675
-    },
-    {
-      "epoch": 0.6610009442870632,
-      "grad_norm": 2.435749053955078,
-      "learning_rate": 0.00015736040609137057,
-      "loss": 3.0218,
-      "mean_token_accuracy": 0.5341324102878571,
-      "num_tokens": 2378262.0,
-      "step": 700
-    },
-    {
-      "epoch": 0.6846081208687441,
-      "grad_norm": 1.3271034955978394,
-      "learning_rate": 0.00015577411167512693,
-      "loss": 2.9578,
-      "mean_token_accuracy": 0.5410768449306488,
-      "num_tokens": 2463204.0,
-      "step": 725
-    },
-    {
-      "epoch": 0.7082152974504249,
-      "grad_norm": 1.8051323890686035,
-      "learning_rate": 0.00015418781725888325,
-      "loss": 2.9002,
-      "mean_token_accuracy": 0.5550252544879913,
-      "num_tokens": 2547027.0,
-      "step": 750
-    },
-    {
-      "epoch": 0.7318224740321058,
-      "grad_norm": 0.9294273257255554,
-      "learning_rate": 0.0001526015228426396,
-      "loss": 2.7967,
-      "mean_token_accuracy": 0.572112466096878,
-      "num_tokens": 2635107.0,
-      "step": 775
-    },
-    {
-      "epoch": 0.7554296506137866,
-      "grad_norm": 1.3318583965301514,
-      "learning_rate": 0.00015101522842639594,
-      "loss": 2.908,
-      "mean_token_accuracy": 0.5564561116695405,
-      "num_tokens": 2719167.0,
-      "step": 800
-    },
-    {
-      "epoch": 0.7790368271954674,
-      "grad_norm": 1.1354563236236572,
-      "learning_rate": 0.0001494289340101523,
-      "loss": 2.8887,
-      "mean_token_accuracy": 0.5594349646568298,
-      "num_tokens": 2805060.0,
-      "step": 825
-    },
-    {
-      "epoch": 0.8026440037771483,
-      "grad_norm": 3.2933058738708496,
-      "learning_rate": 0.00014784263959390862,
-      "loss": 2.8668,
-      "mean_token_accuracy": 0.5591881954669953,
-      "num_tokens": 2887082.0,
-      "step": 850
-    },
-    {
-      "epoch": 0.826251180358829,
-      "grad_norm": 1.8824466466903687,
-      "learning_rate": 0.00014625634517766498,
-      "loss": 2.834,
-      "mean_token_accuracy": 0.5663117682933807,
-      "num_tokens": 2973661.0,
-      "step": 875
-    },
-    {
-      "epoch": 0.8498583569405099,
-      "grad_norm": 1.2233247756958008,
-      "learning_rate": 0.00014467005076142133,
-      "loss": 2.7768,
-      "mean_token_accuracy": 0.5772299838066101,
-      "num_tokens": 3060750.0,
-      "step": 900
-    },
-    {
-      "epoch": 0.8734655335221907,
-      "grad_norm": 1.7638064622879028,
-      "learning_rate": 0.0001430837563451777,
-      "loss": 2.678,
-      "mean_token_accuracy": 0.5990130162239075,
-      "num_tokens": 3143868.0,
-      "step": 925
-    },
-    {
-      "epoch": 0.8970727101038716,
-      "grad_norm": 1.5392266511917114,
-      "learning_rate": 0.00014149746192893402,
-      "loss": 2.6573,
-      "mean_token_accuracy": 0.5954342544078827,
-      "num_tokens": 3231027.0,
-      "step": 950
-    },
-    {
-      "epoch": 0.9206798866855525,
-      "grad_norm": 1.8433501720428467,
-      "learning_rate": 0.00013991116751269035,
-      "loss": 2.9661,
-      "mean_token_accuracy": 0.5433392310142517,
-      "num_tokens": 3314925.0,
-      "step": 975
-    },
-    {
-      "epoch": 0.9442870632672332,
-      "grad_norm": 1.3953369855880737,
-      "learning_rate": 0.0001383248730964467,
-      "loss": 2.7778,
-      "mean_token_accuracy": 0.5806617629528046,
-      "num_tokens": 3398916.0,
-      "step": 1000
-    },
-    {
-      "epoch": 0.9678942398489141,
-      "grad_norm": 2.4013938903808594,
-      "learning_rate": 0.00013673857868020306,
-      "loss": 2.6282,
-      "mean_token_accuracy": 0.6033717966079712,
-      "num_tokens": 3486241.0,
-      "step": 1025
-    },
-    {
-      "epoch": 0.9915014164305949,
-      "grad_norm": 1.3695052862167358,
-      "learning_rate": 0.0001351522842639594,
-      "loss": 2.8629,
-      "mean_token_accuracy": 0.5644518744945526,
-      "num_tokens": 3569625.0,
-      "step": 1050
-    },
-    {
-      "epoch": 1.0151085930122756,
-      "grad_norm": 1.5885721445083618,
-      "learning_rate": 0.00013356598984771574,
-      "loss": 2.7245,
-      "mean_token_accuracy": 0.583740828037262,
-      "num_tokens": 3655264.0,
-      "step": 1075
-    },
-    {
-      "epoch": 1.0387157695939566,
-      "grad_norm": 1.957524299621582,
-      "learning_rate": 0.00013197969543147207,
-      "loss": 2.5976,
-      "mean_token_accuracy": 0.6069298982620239,
-      "num_tokens": 3740644.0,
-      "step": 1100
-    },
-    {
-      "epoch": 1.0623229461756374,
-      "grad_norm": 2.9976248741149902,
-      "learning_rate": 0.00013039340101522843,
-      "loss": 2.7362,
-      "mean_token_accuracy": 0.5855110836029053,
-      "num_tokens": 3825368.0,
-      "step": 1125
-    },
-    {
-      "epoch": 1.0859301227573182,
-      "grad_norm": 3.186262845993042,
-      "learning_rate": 0.00012880710659898478,
-      "loss": 2.8484,
-      "mean_token_accuracy": 0.5662666463851929,
-      "num_tokens": 3908678.0,
-      "step": 1150
-    },
-    {
-      "epoch": 1.1095372993389991,
-      "grad_norm": 1.8036489486694336,
-      "learning_rate": 0.00012722081218274114,
-      "loss": 2.67,
-      "mean_token_accuracy": 0.5938792788982391,
-      "num_tokens": 3996393.0,
-      "step": 1175
-    },
-    {
-      "epoch": 1.13314447592068,
-      "grad_norm": 2.489654779434204,
-      "learning_rate": 0.00012563451776649747,
-      "loss": 2.8123,
-      "mean_token_accuracy": 0.5695419406890869,
-      "num_tokens": 4080596.0,
-      "step": 1200
-    },
-    {
-      "epoch": 1.1567516525023607,
-      "grad_norm": 3.2093520164489746,
-      "learning_rate": 0.00012404822335025382,
-      "loss": 2.517,
-      "mean_token_accuracy": 0.6239076638221741,
-      "num_tokens": 4164481.0,
-      "step": 1225
-    },
-    {
-      "epoch": 1.1803588290840414,
-      "grad_norm": 3.1341941356658936,
-      "learning_rate": 0.00012246192893401015,
-      "loss": 2.5919,
-      "mean_token_accuracy": 0.6061871576309205,
-      "num_tokens": 4253278.0,
-      "step": 1250
-    },
-    {
-      "epoch": 1.2039660056657224,
-      "grad_norm": 1.433424711227417,
-      "learning_rate": 0.0001208756345177665,
-      "loss": 2.4236,
-      "mean_token_accuracy": 0.6387936723232269,
-      "num_tokens": 4338131.0,
-      "step": 1275
-    },
-    {
-      "epoch": 1.2275731822474032,
-      "grad_norm": 1.5914385318756104,
-      "learning_rate": 0.00011928934010152283,
-      "loss": 2.8934,
-      "mean_token_accuracy": 0.5650608110427856,
-      "num_tokens": 4418463.0,
-      "step": 1300
-    },
-    {
-      "epoch": 1.251180358829084,
-      "grad_norm": 1.8357518911361694,
-      "learning_rate": 0.00011770304568527919,
-      "loss": 2.5408,
-      "mean_token_accuracy": 0.6213865375518799,
-      "num_tokens": 4504100.0,
-      "step": 1325
-    },
-    {
-      "epoch": 1.274787535410765,
-      "grad_norm": 2.181213855743408,
-      "learning_rate": 0.00011611675126903555,
-      "loss": 2.4895,
-      "mean_token_accuracy": 0.6242103600502014,
-      "num_tokens": 4590236.0,
-      "step": 1350
-    },
-    {
-      "epoch": 1.2983947119924457,
-      "grad_norm": 2.054617404937744,
-      "learning_rate": 0.00011453045685279189,
-      "loss": 2.5319,
-      "mean_token_accuracy": 0.6264574217796326,
-      "num_tokens": 4673342.0,
-      "step": 1375
-    },
-    {
-      "epoch": 1.3220018885741265,
-      "grad_norm": 2.1715738773345947,
-      "learning_rate": 0.00011294416243654824,
-      "loss": 2.5042,
-      "mean_token_accuracy": 0.6200724172592164,
-      "num_tokens": 4760597.0,
-      "step": 1400
-    },
-    {
-      "epoch": 1.3456090651558075,
-      "grad_norm": 3.023545265197754,
-      "learning_rate": 0.00011135786802030457,
-      "loss": 2.763,
-      "mean_token_accuracy": 0.5873644530773163,
-      "num_tokens": 4842611.0,
-      "step": 1425
-    },
-    {
-      "epoch": 1.3692162417374882,
-      "grad_norm": 1.7163723707199097,
-      "learning_rate": 0.00010977157360406091,
-      "loss": 2.4856,
-      "mean_token_accuracy": 0.6349835538864136,
-      "num_tokens": 4924684.0,
-      "step": 1450
-    },
-    {
-      "epoch": 1.392823418319169,
-      "grad_norm": 2.5177738666534424,
-      "learning_rate": 0.00010818527918781727,
-      "loss": 2.6193,
-      "mean_token_accuracy": 0.6035743832588196,
-      "num_tokens": 5011388.0,
-      "step": 1475
-    },
-    {
-      "epoch": 1.41643059490085,
-      "grad_norm": 1.9504915475845337,
-      "learning_rate": 0.00010659898477157362,
-      "loss": 2.5341,
-      "mean_token_accuracy": 0.6178851091861725,
-      "num_tokens": 5104282.0,
-      "step": 1500
-    },
-    {
-      "epoch": 1.4400377714825308,
-      "grad_norm": 1.2298864126205444,
-      "learning_rate": 0.00010501269035532994,
-      "loss": 2.4975,
-      "mean_token_accuracy": 0.6323371386528015,
-      "num_tokens": 5186482.0,
-      "step": 1525
-    },
-    {
-      "epoch": 1.4636449480642115,
-      "grad_norm": 2.7627272605895996,
-      "learning_rate": 0.0001034263959390863,
-      "loss": 2.5773,
-      "mean_token_accuracy": 0.6132258200645446,
-      "num_tokens": 5267604.0,
-      "step": 1550
-    },
-    {
-      "epoch": 1.4872521246458923,
-      "grad_norm": 2.1530709266662598,
-      "learning_rate": 0.00010184010152284265,
-      "loss": 2.7489,
-      "mean_token_accuracy": 0.5849710512161255,
-      "num_tokens": 5345250.0,
-      "step": 1575
-    },
-    {
-      "epoch": 1.510859301227573,
-      "grad_norm": 3.3525829315185547,
-      "learning_rate": 0.00010025380710659899,
-      "loss": 2.3328,
-      "mean_token_accuracy": 0.6535279083251954,
-      "num_tokens": 5432188.0,
-      "step": 1600
-    },
-    {
-      "epoch": 1.534466477809254,
-      "grad_norm": 3.1491880416870117,
-      "learning_rate": 9.866751269035533e-05,
-      "loss": 2.4587,
-      "mean_token_accuracy": 0.6317604184150696,
-      "num_tokens": 5518949.0,
-      "step": 1625
-    },
-    {
-      "epoch": 1.5580736543909348,
-      "grad_norm": 3.790788412094116,
-      "learning_rate": 9.708121827411169e-05,
-      "loss": 2.5356,
-      "mean_token_accuracy": 0.6312965428829194,
-      "num_tokens": 5598790.0,
-      "step": 1650
-    },
-    {
-      "epoch": 1.5816808309726156,
-      "grad_norm": 2.399170160293579,
-      "learning_rate": 9.549492385786802e-05,
-      "loss": 2.4952,
-      "mean_token_accuracy": 0.6315456974506378,
-      "num_tokens": 5685520.0,
-      "step": 1675
-    },
-    {
-      "epoch": 1.6052880075542966,
-      "grad_norm": 1.783835530281067,
-      "learning_rate": 9.390862944162437e-05,
-      "loss": 2.5257,
-      "mean_token_accuracy": 0.629066880941391,
-      "num_tokens": 5764729.0,
-      "step": 1700
-    },
-    {
-      "epoch": 1.6288951841359773,
-      "grad_norm": 2.1746981143951416,
-      "learning_rate": 9.232233502538072e-05,
-      "loss": 2.3915,
-      "mean_token_accuracy": 0.6475781321525573,
-      "num_tokens": 5847096.0,
-      "step": 1725
-    },
-    {
-      "epoch": 1.652502360717658,
-      "grad_norm": 2.853606700897217,
-      "learning_rate": 9.073604060913706e-05,
-      "loss": 2.4254,
-      "mean_token_accuracy": 0.6364664602279663,
-      "num_tokens": 5929730.0,
-      "step": 1750
-    },
-    {
-      "epoch": 1.676109537299339,
-      "grad_norm": 2.6709866523742676,
-      "learning_rate": 8.91497461928934e-05,
-      "loss": 2.2418,
-      "mean_token_accuracy": 0.6732782328128815,
-      "num_tokens": 6021265.0,
-      "step": 1775
-    },
-    {
-      "epoch": 1.6997167138810199,
-      "grad_norm": 3.0063297748565674,
-      "learning_rate": 8.756345177664976e-05,
-      "loss": 2.441,
-      "mean_token_accuracy": 0.6447321319580078,
-      "num_tokens": 6102483.0,
-      "step": 1800
-    },
-    {
-      "epoch": 1.7233238904627006,
-      "grad_norm": 2.609477996826172,
-      "learning_rate": 8.597715736040608e-05,
-      "loss": 2.3247,
-      "mean_token_accuracy": 0.667446813583374,
-      "num_tokens": 6186450.0,
-      "step": 1825
-    },
-    {
-      "epoch": 1.7469310670443816,
-      "grad_norm": 1.4909838438034058,
-      "learning_rate": 8.439086294416244e-05,
-      "loss": 2.1653,
-      "mean_token_accuracy": 0.6888451766967774,
-      "num_tokens": 6272397.0,
-      "step": 1850
-    },
-    {
-      "epoch": 1.7705382436260622,
-      "grad_norm": 2.26397442817688,
-      "learning_rate": 8.28045685279188e-05,
-      "loss": 2.4152,
-      "mean_token_accuracy": 0.6488711929321289,
-      "num_tokens": 6353819.0,
-      "step": 1875
-    },
-    {
-      "epoch": 1.7941454202077431,
-      "grad_norm": 2.281494379043579,
-      "learning_rate": 8.121827411167512e-05,
-      "loss": 2.2089,
-      "mean_token_accuracy": 0.6806192409992218,
-      "num_tokens": 6439448.0,
-      "step": 1900
-    },
-    {
-      "epoch": 1.8177525967894241,
-      "grad_norm": 2.4258992671966553,
-      "learning_rate": 7.963197969543148e-05,
-      "loss": 2.5648,
-      "mean_token_accuracy": 0.6230374383926391,
-      "num_tokens": 6523821.0,
-      "step": 1925
-    },
-    {
-      "epoch": 1.8413597733711047,
-      "grad_norm": 2.492616653442383,
-      "learning_rate": 7.804568527918782e-05,
-      "loss": 2.4212,
-      "mean_token_accuracy": 0.643797037601471,
-      "num_tokens": 6609653.0,
-      "step": 1950
-    },
-    {
-      "epoch": 1.8649669499527857,
-      "grad_norm": 2.589484930038452,
-      "learning_rate": 7.645939086294416e-05,
-      "loss": 2.1783,
-      "mean_token_accuracy": 0.6852576458454132,
-      "num_tokens": 6697310.0,
-      "step": 1975
-    },
-    {
-      "epoch": 1.8885741265344664,
-      "grad_norm": 1.6886556148529053,
-      "learning_rate": 7.48730964467005e-05,
-      "loss": 2.2581,
-      "mean_token_accuracy": 0.6677005457878112,
-      "num_tokens": 6789851.0,
-      "step": 2000
-    },
-    {
-      "epoch": 1.9121813031161472,
-      "grad_norm": 3.7452311515808105,
-      "learning_rate": 7.328680203045686e-05,
-      "loss": 2.3258,
-      "mean_token_accuracy": 0.6635724091529847,
-      "num_tokens": 6877195.0,
-      "step": 2025
-    },
-    {
-      "epoch": 1.9357884796978282,
-      "grad_norm": 2.047663688659668,
-      "learning_rate": 7.170050761421319e-05,
-      "loss": 2.3441,
-      "mean_token_accuracy": 0.6537975025177002,
-      "num_tokens": 6963541.0,
-      "step": 2050
-    },
-    {
-      "epoch": 1.959395656279509,
-      "grad_norm": 3.105921506881714,
-      "learning_rate": 7.011421319796955e-05,
-      "loss": 2.2945,
-      "mean_token_accuracy": 0.6703400027751922,
-      "num_tokens": 7049829.0,
-      "step": 2075
-    },
-    {
-      "epoch": 1.9830028328611897,
-      "grad_norm": 2.07450532913208,
-      "learning_rate": 6.852791878172589e-05,
-      "loss": 2.4282,
-      "mean_token_accuracy": 0.6384662842750549,
-      "num_tokens": 7138596.0,
-      "step": 2100
-    },
-    {
-      "epoch": 2.0066100094428707,
-      "grad_norm": 3.5083131790161133,
-      "learning_rate": 6.694162436548223e-05,
-      "loss": 2.43,
-      "mean_token_accuracy": 0.640663161277771,
-      "num_tokens": 7223056.0,
-      "step": 2125
-    },
-    {
-      "epoch": 2.0302171860245513,
-      "grad_norm": 1.5466697216033936,
-      "learning_rate": 6.541878172588833e-05,
-      "loss": 2.4533,
-      "mean_token_accuracy": 0.6328469634056091,
-      "num_tokens": 7309998.0,
-      "step": 2150
-    },
-    {
-      "epoch": 2.0538243626062322,
-      "grad_norm": 1.704559087753296,
-      "learning_rate": 6.383248730964467e-05,
-      "loss": 2.31,
-      "mean_token_accuracy": 0.6707417845726014,
-      "num_tokens": 7390437.0,
-      "step": 2175
-    },
-    {
-      "epoch": 2.0774315391879132,
-      "grad_norm": 2.0818848609924316,
-      "learning_rate": 6.224619289340103e-05,
-      "loss": 2.4,
-      "mean_token_accuracy": 0.6547241771221161,
-      "num_tokens": 7472360.0,
-      "step": 2200
-    },
-    {
-      "epoch": 2.101038715769594,
-      "grad_norm": 2.9945547580718994,
-      "learning_rate": 6.065989847715736e-05,
-      "loss": 2.2873,
-      "mean_token_accuracy": 0.6657208549976349,
-      "num_tokens": 7555482.0,
-      "step": 2225
-    },
-    {
-      "epoch": 2.1246458923512748,
-      "grad_norm": 3.4089205265045166,
-      "learning_rate": 5.907360406091371e-05,
-      "loss": 2.2813,
-      "mean_token_accuracy": 0.6657274806499481,
-      "num_tokens": 7646453.0,
-      "step": 2250
-    },
-    {
-      "epoch": 2.1482530689329558,
-      "grad_norm": 3.965263605117798,
-      "learning_rate": 5.748730964467005e-05,
-      "loss": 2.2457,
-      "mean_token_accuracy": 0.6795996761322022,
-      "num_tokens": 7729020.0,
-      "step": 2275
-    },
-    {
-      "epoch": 2.1718602455146363,
-      "grad_norm": 3.042095899581909,
-      "learning_rate": 5.59010152284264e-05,
-      "loss": 2.2448,
-      "mean_token_accuracy": 0.6785978388786316,
-      "num_tokens": 7813751.0,
-      "step": 2300
-    },
-    {
-      "epoch": 2.1954674220963173,
-      "grad_norm": 2.43571400642395,
-      "learning_rate": 5.431472081218274e-05,
-      "loss": 2.3119,
-      "mean_token_accuracy": 0.6689464914798736,
-      "num_tokens": 7895366.0,
-      "step": 2325
-    },
-    {
-      "epoch": 2.2190745986779983,
-      "grad_norm": 1.749118685722351,
-      "learning_rate": 5.272842639593909e-05,
-      "loss": 2.4028,
-      "mean_token_accuracy": 0.6496596956253051,
-      "num_tokens": 7978864.0,
-      "step": 2350
-    },
-    {
-      "epoch": 2.242681775259679,
-      "grad_norm": 4.0993547439575195,
-      "learning_rate": 5.114213197969543e-05,
-      "loss": 2.0971,
-      "mean_token_accuracy": 0.702848870754242,
-      "num_tokens": 8066059.0,
-      "step": 2375
-    },
-    {
-      "epoch": 2.26628895184136,
-      "grad_norm": 2.478060007095337,
-      "learning_rate": 4.955583756345178e-05,
-      "loss": 2.3131,
-      "mean_token_accuracy": 0.6597225499153138,
-      "num_tokens": 8150324.0,
-      "step": 2400
-    },
-    {
-      "epoch": 2.289896128423041,
-      "grad_norm": 3.1821959018707275,
-      "learning_rate": 4.7969543147208126e-05,
-      "loss": 2.2792,
-      "mean_token_accuracy": 0.6698596668243408,
-      "num_tokens": 8237632.0,
-      "step": 2425
-    },
-    {
-      "epoch": 2.3135033050047213,
-      "grad_norm": 1.7894206047058105,
-      "learning_rate": 4.638324873096447e-05,
-      "loss": 2.1695,
-      "mean_token_accuracy": 0.687961802482605,
-      "num_tokens": 8324924.0,
-      "step": 2450
-    },
-    {
-      "epoch": 2.3371104815864023,
-      "grad_norm": 2.1389191150665283,
-      "learning_rate": 4.479695431472081e-05,
-      "loss": 2.0925,
-      "mean_token_accuracy": 0.7001671254634857,
-      "num_tokens": 8411403.0,
-      "step": 2475
-    },
-    {
-      "epoch": 2.360717658168083,
-      "grad_norm": 2.390141248703003,
-      "learning_rate": 4.321065989847716e-05,
-      "loss": 2.3656,
-      "mean_token_accuracy": 0.657674194574356,
-      "num_tokens": 8496536.0,
-      "step": 2500
-    },
-    {
-      "epoch": 2.384324834749764,
-      "grad_norm": 2.3317668437957764,
-      "learning_rate": 4.162436548223351e-05,
-      "loss": 1.9864,
-      "mean_token_accuracy": 0.7178370308876038,
-      "num_tokens": 8588032.0,
-      "step": 2525
-    },
-    {
-      "epoch": 2.407932011331445,
-      "grad_norm": 2.255056619644165,
-      "learning_rate": 4.003807106598985e-05,
-      "loss": 2.1131,
-      "mean_token_accuracy": 0.7006520819664002,
-      "num_tokens": 8672178.0,
-      "step": 2550
-    },
-    {
-      "epoch": 2.4315391879131254,
-      "grad_norm": 2.2023000717163086,
-      "learning_rate": 3.84517766497462e-05,
-      "loss": 2.0892,
-      "mean_token_accuracy": 0.7081982207298279,
-      "num_tokens": 8753494.0,
-      "step": 2575
-    },
-    {
-      "epoch": 2.4551463644948064,
-      "grad_norm": 3.6177306175231934,
-      "learning_rate": 3.686548223350254e-05,
-      "loss": 2.2059,
-      "mean_token_accuracy": 0.6876888346672058,
-      "num_tokens": 8836935.0,
-      "step": 2600
-    },
-    {
-      "epoch": 2.4787535410764874,
-      "grad_norm": 2.292860746383667,
-      "learning_rate": 3.527918781725888e-05,
-      "loss": 2.3883,
-      "mean_token_accuracy": 0.6509598207473755,
-      "num_tokens": 8921920.0,
-      "step": 2625
-    },
-    {
-      "epoch": 2.502360717658168,
-      "grad_norm": 2.749070167541504,
-      "learning_rate": 3.369289340101523e-05,
-      "loss": 2.3556,
-      "mean_token_accuracy": 0.6616550016403199,
-      "num_tokens": 9005311.0,
-      "step": 2650
-    },
-    {
-      "epoch": 2.525967894239849,
-      "grad_norm": 2.500455617904663,
-      "learning_rate": 3.210659898477157e-05,
-      "loss": 2.1479,
-      "mean_token_accuracy": 0.6956441640853882,
-      "num_tokens": 9089703.0,
-      "step": 2675
-    },
-    {
-      "epoch": 2.54957507082153,
-      "grad_norm": 1.5603734254837036,
-      "learning_rate": 3.052030456852792e-05,
-      "loss": 2.2351,
-      "mean_token_accuracy": 0.6813873088359833,
-      "num_tokens": 9177025.0,
-      "step": 2700
-    },
-    {
-      "epoch": 2.5731822474032104,
-      "grad_norm": 3.4635727405548096,
-      "learning_rate": 2.8934010152284264e-05,
-      "loss": 2.1598,
-      "mean_token_accuracy": 0.6917344307899476,
-      "num_tokens": 9261429.0,
-      "step": 2725
-    },
-    {
-      "epoch": 2.5967894239848914,
-      "grad_norm": 2.4915714263916016,
-      "learning_rate": 2.7347715736040606e-05,
-      "loss": 2.2634,
-      "mean_token_accuracy": 0.6734067058563232,
-      "num_tokens": 9348692.0,
-      "step": 2750
-    },
-    {
-      "epoch": 2.620396600566572,
-      "grad_norm": 2.7267868518829346,
-      "learning_rate": 2.576142131979696e-05,
-      "loss": 2.2268,
-      "mean_token_accuracy": 0.6815747046470642,
-      "num_tokens": 9432715.0,
-      "step": 2775
-    },
-    {
-      "epoch": 2.644003777148253,
-      "grad_norm": 3.085237503051758,
-      "learning_rate": 2.41751269035533e-05,
-      "loss": 2.1703,
-      "mean_token_accuracy": 0.6912525415420532,
-      "num_tokens": 9518928.0,
-      "step": 2800
-    },
-    {
-      "epoch": 2.667610953729934,
-      "grad_norm": 2.2934255599975586,
-      "learning_rate": 2.2588832487309646e-05,
-      "loss": 2.2124,
-      "mean_token_accuracy": 0.6754102325439453,
-      "num_tokens": 9606238.0,
-      "step": 2825
-    },
-    {
-      "epoch": 2.691218130311615,
-      "grad_norm": 3.9280519485473633,
-      "learning_rate": 2.100253807106599e-05,
-      "loss": 2.0278,
-      "mean_token_accuracy": 0.7123878049850464,
-      "num_tokens": 9693011.0,
-      "step": 2850
-    },
-    {
-      "epoch": 2.7148253068932955,
-      "grad_norm": 2.0387489795684814,
-      "learning_rate": 1.9416243654822337e-05,
-      "loss": 2.177,
-      "mean_token_accuracy": 0.6935857963562012,
-      "num_tokens": 9776929.0,
-      "step": 2875
-    },
-    {
-      "epoch": 2.7384324834749765,
-      "grad_norm": 2.9819560050964355,
-      "learning_rate": 1.782994923857868e-05,
-      "loss": 2.0651,
-      "mean_token_accuracy": 0.7067358446121216,
-      "num_tokens": 9862456.0,
-      "step": 2900
-    },
-    {
-      "epoch": 2.762039660056657,
-      "grad_norm": 2.204148054122925,
-      "learning_rate": 1.6243654822335024e-05,
-      "loss": 2.046,
-      "mean_token_accuracy": 0.707190637588501,
-      "num_tokens": 9952073.0,
-      "step": 2925
-    },
-    {
-      "epoch": 2.785646836638338,
-      "grad_norm": 3.0924429893493652,
-      "learning_rate": 1.4657360406091371e-05,
-      "loss": 2.209,
-      "mean_token_accuracy": 0.6862516689300537,
-      "num_tokens": 10037799.0,
-      "step": 2950
-    },
-    {
-      "epoch": 2.809254013220019,
-      "grad_norm": 2.6368651390075684,
-      "learning_rate": 1.3071065989847717e-05,
-      "loss": 2.2244,
-      "mean_token_accuracy": 0.6805661177635193,
-      "num_tokens": 10124423.0,
-      "step": 2975
-    },
-    {
-      "epoch": 2.8328611898017,
-      "grad_norm": 1.7311336994171143,
-      "learning_rate": 1.148477157360406e-05,
-      "loss": 2.1135,
-      "mean_token_accuracy": 0.7051725935935974,
-      "num_tokens": 10202586.0,
-      "step": 3000
-    },
-    {
-      "epoch": 2.8564683663833805,
-      "grad_norm": 2.4750070571899414,
-      "learning_rate": 9.898477157360408e-06,
-      "loss": 2.0525,
-      "mean_token_accuracy": 0.7098425531387329,
-      "num_tokens": 10288808.0,
-      "step": 3025
-    },
-    {
-      "epoch": 2.8800755429650615,
-      "grad_norm": 2.8913192749023438,
-      "learning_rate": 8.312182741116751e-06,
-      "loss": 1.7762,
-      "mean_token_accuracy": 0.7606491017341613,
-      "num_tokens": 10375567.0,
-      "step": 3050
-    },
-    {
-      "epoch": 2.903682719546742,
-      "grad_norm": 2.6616008281707764,
-      "learning_rate": 6.725888324873096e-06,
-      "loss": 2.064,
-      "mean_token_accuracy": 0.7075335788726806,
-      "num_tokens": 10462771.0,
-      "step": 3075
-    },
-    {
-      "epoch": 2.927289896128423,
-      "grad_norm": 2.2261228561401367,
-      "learning_rate": 5.139593908629442e-06,
-      "loss": 2.2238,
-      "mean_token_accuracy": 0.6874805259704589,
-      "num_tokens": 10542846.0,
-      "step": 3100
-    },
-    {
-      "epoch": 2.950897072710104,
-      "grad_norm": 2.295609712600708,
-      "learning_rate": 3.5532994923857873e-06,
-      "loss": 2.1835,
-      "mean_token_accuracy": 0.6867920517921448,
-      "num_tokens": 10625357.0,
-      "step": 3125
-    },
-    {
-      "epoch": 2.9745042492917846,
-      "grad_norm": 1.7816609144210815,
-      "learning_rate": 1.967005076142132e-06,
-      "loss": 2.3207,
-      "mean_token_accuracy": 0.6663406753540039,
-      "num_tokens": 10706184.0,
-      "step": 3150
-    },
-    {
-      "epoch": 2.9981114258734656,
-      "grad_norm": 2.8482465744018555,
-      "learning_rate": 3.807106598984772e-07,
-      "loss": 2.1249,
-      "mean_token_accuracy": 0.6941254138946533,
-      "num_tokens": 10793477.0,
-      "step": 3175
-    }
-  ],
-  "logging_steps": 25,
-  "max_steps": 3177,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.6851959205842534e+18,
-  "train_batch_size": 9,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27be49042add3dc0d0be39c1a676fe5900e3b7cd0b1ac58cd0800c00a999270
+oid sha256:1cf3a3cf49d10705b84367db680227f45497b70bf105d033348f9c874d1a31e3
 size 6161