Training in progress, epoch 20, checkpoint

checkpoint-71980/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-1.3b-base
+library_name: peft
+---
+
+# 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 0.14.0

checkpoint-71980/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-71980/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a26bbf98f0fa5e61681166e3214519c07ea53d9feb9c897cc09e5bafe30d97
+size 268636736

checkpoint-71980/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f35bbdfbf23f631b5416d769bc579ac4f0684573526a91ae3b94545d0dc242
+size 12663802

checkpoint-71980/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67fb23764b167838af1cc32cf9dd92b671799e550c08564589b16ba00ac8dec
+size 15984

checkpoint-71980/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdeac1af309aad489c2cbd9868c95f36d454d8bc0479d645d375231ca0f93d72
+size 15984

checkpoint-71980/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8714e549b1d06db5198043a626e9a827480f4f394b7c6fe6c8ebcae3a3390d50
+size 15984

checkpoint-71980/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f27f4564577b8706e3f9bc1a1120e4911df78803a054006369157d9f925e12f
+size 15984

checkpoint-71980/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c5720ff245cbedfbd4030a7c03d456199b18163ac39a218ea3aecc1ee25acc
+size 15984

checkpoint-71980/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e154394f81dfeef7a2718ac43da8ad49cb3df0718472abd1b2b60c74782124
+size 15984

checkpoint-71980/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e79c0da67e194e5831bba8e2e6acde0cf80d927d855f3fd91c4b5d6f920874
+size 15984

checkpoint-71980/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb378a2d54265a579dfa5e509956c9b1e5672f3dadc29306b30d650bc111f45
+size 15984

checkpoint-71980/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702f83b39a4438c5699f065584d4b59f7d9eeab8552019fb8cb9d2fda386ccc9
+size 1064

checkpoint-71980/trainer_state.json

@@ -0,0 +1,1426 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 1440,
+  "global_step": 71980,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13892747985551543,
+      "grad_norm": 0.9003118872642517,
+      "learning_rate": 0.000795387607668797,
+      "loss": 0.4296,
+      "step": 500
+    },
+    {
+      "epoch": 0.27785495971103086,
+      "grad_norm": 2.5679404735565186,
+      "learning_rate": 0.0007907566916736131,
+      "loss": 0.3243,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4001111419838844,
+      "eval_loss": 0.2947143018245697,
+      "eval_runtime": 5.7176,
+      "eval_samples_per_second": 87.449,
+      "eval_steps_per_second": 5.597,
+      "step": 1440
+    },
+    {
+      "epoch": 0.41678243956654626,
+      "grad_norm": 0.6454382538795471,
+      "learning_rate": 0.0007861257756784293,
+      "loss": 0.2985,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5557099194220617,
+      "grad_norm": 0.6851354837417603,
+      "learning_rate": 0.0007815041215152357,
+      "loss": 0.2829,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6946373992775771,
+      "grad_norm": 0.7469644546508789,
+      "learning_rate": 0.0007768732055200519,
+      "loss": 0.2737,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8002222839677688,
+      "eval_loss": 0.2755357623100281,
+      "eval_runtime": 5.6548,
+      "eval_samples_per_second": 88.421,
+      "eval_steps_per_second": 5.659,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8335648791330925,
+      "grad_norm": 0.6683129072189331,
+      "learning_rate": 0.0007722422895248681,
+      "loss": 0.2653,
+      "step": 3000
+    },
+    {
+      "epoch": 0.972492358988608,
+      "grad_norm": 0.7536308169364929,
+      "learning_rate": 0.0007676113735296843,
+      "loss": 0.2628,
+      "step": 3500
+    },
+    {
+      "epoch": 1.1114198388441234,
+      "grad_norm": 0.6173604726791382,
+      "learning_rate": 0.0007629804575345004,
+      "loss": 0.2463,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2003334259516532,
+      "eval_loss": 0.2620045840740204,
+      "eval_runtime": 5.6897,
+      "eval_samples_per_second": 87.877,
+      "eval_steps_per_second": 5.624,
+      "step": 4320
+    },
+    {
+      "epoch": 1.2503473186996388,
+      "grad_norm": 0.9441823363304138,
+      "learning_rate": 0.0007583495415393165,
+      "loss": 0.2476,
+      "step": 4500
+    },
+    {
+      "epoch": 1.3892747985551543,
+      "grad_norm": 1.179303526878357,
+      "learning_rate": 0.0007537186255441327,
+      "loss": 0.2448,
+      "step": 5000
+    },
+    {
+      "epoch": 1.5282022784106695,
+      "grad_norm": 0.9045144319534302,
+      "learning_rate": 0.0007490877095489488,
+      "loss": 0.2389,
+      "step": 5500
+    },
+    {
+      "epoch": 1.6004445679355377,
+      "eval_loss": 0.25695353746414185,
+      "eval_runtime": 5.6542,
+      "eval_samples_per_second": 88.43,
+      "eval_steps_per_second": 5.66,
+      "step": 5760
+    },
+    {
+      "epoch": 1.667129758266185,
+      "grad_norm": 0.6623045206069946,
+      "learning_rate": 0.0007444660553857554,
+      "loss": 0.2409,
+      "step": 6000
+    },
+    {
+      "epoch": 1.8060572381217006,
+      "grad_norm": 0.6902622580528259,
+      "learning_rate": 0.0007398351393905715,
+      "loss": 0.234,
+      "step": 6500
+    },
+    {
+      "epoch": 1.9449847179772157,
+      "grad_norm": 0.7465945482254028,
+      "learning_rate": 0.0007352042233953876,
+      "loss": 0.2342,
+      "step": 7000
+    },
+    {
+      "epoch": 2.000555709919422,
+      "eval_loss": 0.25181135535240173,
+      "eval_runtime": 5.6993,
+      "eval_samples_per_second": 87.731,
+      "eval_steps_per_second": 5.615,
+      "step": 7200
+    },
+    {
+      "epoch": 2.0839121978327313,
+      "grad_norm": 0.7666770219802856,
+      "learning_rate": 0.0007305825692321942,
+      "loss": 0.226,
+      "step": 7500
+    },
+    {
+      "epoch": 2.222839677688247,
+      "grad_norm": 0.6436336636543274,
+      "learning_rate": 0.0007259516532370103,
+      "loss": 0.2247,
+      "step": 8000
+    },
+    {
+      "epoch": 2.361767157543762,
+      "grad_norm": 0.6064488291740417,
+      "learning_rate": 0.0007213207372418264,
+      "loss": 0.2237,
+      "step": 8500
+    },
+    {
+      "epoch": 2.4006668519033063,
+      "eval_loss": 0.24924051761627197,
+      "eval_runtime": 5.9651,
+      "eval_samples_per_second": 83.821,
+      "eval_steps_per_second": 5.365,
+      "step": 8640
+    },
+    {
+      "epoch": 2.5006946373992776,
+      "grad_norm": 1.0091792345046997,
+      "learning_rate": 0.0007166898212466426,
+      "loss": 0.2203,
+      "step": 9000
+    },
+    {
+      "epoch": 2.639622117254793,
+      "grad_norm": 0.8089786767959595,
+      "learning_rate": 0.0007120589052514588,
+      "loss": 0.2196,
+      "step": 9500
+    },
+    {
+      "epoch": 2.7785495971103087,
+      "grad_norm": 0.5441291928291321,
+      "learning_rate": 0.0007074372510882653,
+      "loss": 0.2216,
+      "step": 10000
+    },
+    {
+      "epoch": 2.800777993887191,
+      "eval_loss": 0.2379860281944275,
+      "eval_runtime": 5.6823,
+      "eval_samples_per_second": 87.992,
+      "eval_steps_per_second": 5.632,
+      "step": 10080
+    },
+    {
+      "epoch": 2.917477076965824,
+      "grad_norm": 0.5629907250404358,
+      "learning_rate": 0.0007028063350930814,
+      "loss": 0.2209,
+      "step": 10500
+    },
+    {
+      "epoch": 3.0564045568213394,
+      "grad_norm": 0.7793105840682983,
+      "learning_rate": 0.0006981754190978975,
+      "loss": 0.2153,
+      "step": 11000
+    },
+    {
+      "epoch": 3.1953320366768545,
+      "grad_norm": 0.5668399333953857,
+      "learning_rate": 0.0006935445031027137,
+      "loss": 0.2104,
+      "step": 11500
+    },
+    {
+      "epoch": 3.2008891358710754,
+      "eval_loss": 0.23175135254859924,
+      "eval_runtime": 5.6868,
+      "eval_samples_per_second": 87.922,
+      "eval_steps_per_second": 5.627,
+      "step": 11520
+    },
+    {
+      "epoch": 3.33425951653237,
+      "grad_norm": 0.8093000650405884,
+      "learning_rate": 0.0006889228489395203,
+      "loss": 0.2136,
+      "step": 12000
+    },
+    {
+      "epoch": 3.4731869963878856,
+      "grad_norm": 0.9104741215705872,
+      "learning_rate": 0.0006842919329443364,
+      "loss": 0.2076,
+      "step": 12500
+    },
+    {
+      "epoch": 3.6010002778549595,
+      "eval_loss": 0.22807475924491882,
+      "eval_runtime": 5.7081,
+      "eval_samples_per_second": 87.595,
+      "eval_steps_per_second": 5.606,
+      "step": 12960
+    },
+    {
+      "epoch": 3.612114476243401,
+      "grad_norm": 0.688875675201416,
+      "learning_rate": 0.0006796610169491525,
+      "loss": 0.2109,
+      "step": 13000
+    },
+    {
+      "epoch": 3.7510419560989163,
+      "grad_norm": 0.985016405582428,
+      "learning_rate": 0.0006750301009539687,
+      "loss": 0.209,
+      "step": 13500
+    },
+    {
+      "epoch": 3.889969435954432,
+      "grad_norm": 0.792914628982544,
+      "learning_rate": 0.0006703991849587848,
+      "loss": 0.2087,
+      "step": 14000
+    },
+    {
+      "epoch": 4.001111419838844,
+      "eval_loss": 0.2299247533082962,
+      "eval_runtime": 5.9644,
+      "eval_samples_per_second": 83.831,
+      "eval_steps_per_second": 5.365,
+      "step": 14400
+    },
+    {
+      "epoch": 4.0288969158099475,
+      "grad_norm": 0.8050146698951721,
+      "learning_rate": 0.000665768268963601,
+      "loss": 0.2043,
+      "step": 14500
+    },
+    {
+      "epoch": 4.167824395665463,
+      "grad_norm": 0.6686243414878845,
+      "learning_rate": 0.0006611373529684172,
+      "loss": 0.1997,
+      "step": 15000
+    },
+    {
+      "epoch": 4.306751875520978,
+      "grad_norm": 0.5832377076148987,
+      "learning_rate": 0.0006565064369732334,
+      "loss": 0.2011,
+      "step": 15500
+    },
+    {
+      "epoch": 4.4012225618227285,
+      "eval_loss": 0.22105582058429718,
+      "eval_runtime": 5.6811,
+      "eval_samples_per_second": 88.011,
+      "eval_steps_per_second": 5.633,
+      "step": 15840
+    },
+    {
+      "epoch": 4.445679355376494,
+      "grad_norm": 0.5768308639526367,
+      "learning_rate": 0.0006518847828100398,
+      "loss": 0.2029,
+      "step": 16000
+    },
+    {
+      "epoch": 4.584606835232009,
+      "grad_norm": 0.7500970959663391,
+      "learning_rate": 0.000647253866814856,
+      "loss": 0.1985,
+      "step": 16500
+    },
+    {
+      "epoch": 4.723534315087524,
+      "grad_norm": 0.7904524207115173,
+      "learning_rate": 0.0006426322126516625,
+      "loss": 0.199,
+      "step": 17000
+    },
+    {
+      "epoch": 4.801333703806613,
+      "eval_loss": 0.2192094475030899,
+      "eval_runtime": 5.6808,
+      "eval_samples_per_second": 88.016,
+      "eval_steps_per_second": 5.633,
+      "step": 17280
+    },
+    {
+      "epoch": 4.86246179494304,
+      "grad_norm": 0.539150059223175,
+      "learning_rate": 0.0006380012966564787,
+      "loss": 0.2009,
+      "step": 17500
+    },
+    {
+      "epoch": 5.001389274798555,
+      "grad_norm": 0.8565651178359985,
+      "learning_rate": 0.0006333703806612948,
+      "loss": 0.1971,
+      "step": 18000
+    },
+    {
+      "epoch": 5.14031675465407,
+      "grad_norm": 0.7713454365730286,
+      "learning_rate": 0.0006287394646661109,
+      "loss": 0.1893,
+      "step": 18500
+    },
+    {
+      "epoch": 5.201444845790498,
+      "eval_loss": 0.21168488264083862,
+      "eval_runtime": 5.6835,
+      "eval_samples_per_second": 87.974,
+      "eval_steps_per_second": 5.63,
+      "step": 18720
+    },
+    {
+      "epoch": 5.279244234509586,
+      "grad_norm": 0.6991382241249084,
+      "learning_rate": 0.0006241085486709271,
+      "loss": 0.1893,
+      "step": 19000
+    },
+    {
+      "epoch": 5.418171714365101,
+      "grad_norm": 0.8312591314315796,
+      "learning_rate": 0.0006194776326757433,
+      "loss": 0.1922,
+      "step": 19500
+    },
+    {
+      "epoch": 5.5570991942206165,
+      "grad_norm": 0.5211935043334961,
+      "learning_rate": 0.0006148467166805595,
+      "loss": 0.1935,
+      "step": 20000
+    },
+    {
+      "epoch": 5.601555987774382,
+      "eval_loss": 0.21850116550922394,
+      "eval_runtime": 5.755,
+      "eval_samples_per_second": 86.881,
+      "eval_steps_per_second": 5.56,
+      "step": 20160
+    },
+    {
+      "epoch": 5.6960266740761325,
+      "grad_norm": 0.6599379777908325,
+      "learning_rate": 0.000610225062517366,
+      "loss": 0.1926,
+      "step": 20500
+    },
+    {
+      "epoch": 5.834954153931648,
+      "grad_norm": 0.5970427393913269,
+      "learning_rate": 0.0006055941465221821,
+      "loss": 0.1909,
+      "step": 21000
+    },
+    {
+      "epoch": 5.973881633787163,
+      "grad_norm": 1.023311734199524,
+      "learning_rate": 0.0006009632305269982,
+      "loss": 0.1895,
+      "step": 21500
+    },
+    {
+      "epoch": 6.001667129758266,
+      "eval_loss": 0.207980215549469,
+      "eval_runtime": 5.7482,
+      "eval_samples_per_second": 86.984,
+      "eval_steps_per_second": 5.567,
+      "step": 21600
+    },
+    {
+      "epoch": 6.112809113642679,
+      "grad_norm": 0.91774582862854,
+      "learning_rate": 0.0005963323145318144,
+      "loss": 0.1816,
+      "step": 22000
+    },
+    {
+      "epoch": 6.251736593498194,
+      "grad_norm": 1.0004245042800903,
+      "learning_rate": 0.0005917013985366306,
+      "loss": 0.1851,
+      "step": 22500
+    },
+    {
+      "epoch": 6.390664073353709,
+      "grad_norm": 0.662783145904541,
+      "learning_rate": 0.0005870704825414468,
+      "loss": 0.1841,
+      "step": 23000
+    },
+    {
+      "epoch": 6.401778271742151,
+      "eval_loss": 0.20145055651664734,
+      "eval_runtime": 5.7129,
+      "eval_samples_per_second": 87.521,
+      "eval_steps_per_second": 5.601,
+      "step": 23040
+    },
+    {
+      "epoch": 6.529591553209225,
+      "grad_norm": 0.7809537053108215,
+      "learning_rate": 0.0005824395665462628,
+      "loss": 0.1818,
+      "step": 23500
+    },
+    {
+      "epoch": 6.66851903306474,
+      "grad_norm": 0.7120875120162964,
+      "learning_rate": 0.000577808650551079,
+      "loss": 0.184,
+      "step": 24000
+    },
+    {
+      "epoch": 6.801889413726035,
+      "eval_loss": 0.20286568999290466,
+      "eval_runtime": 5.6944,
+      "eval_samples_per_second": 87.805,
+      "eval_steps_per_second": 5.62,
+      "step": 24480
+    },
+    {
+      "epoch": 6.807446512920255,
+      "grad_norm": 0.6878994107246399,
+      "learning_rate": 0.0005731869963878856,
+      "loss": 0.1837,
+      "step": 24500
+    },
+    {
+      "epoch": 6.946373992775771,
+      "grad_norm": 1.3410155773162842,
+      "learning_rate": 0.0005685560803927017,
+      "loss": 0.181,
+      "step": 25000
+    },
+    {
+      "epoch": 7.085301472631286,
+      "grad_norm": 0.7791838049888611,
+      "learning_rate": 0.0005639344262295083,
+      "loss": 0.1755,
+      "step": 25500
+    },
+    {
+      "epoch": 7.20200055570992,
+      "eval_loss": 0.2010478526353836,
+      "eval_runtime": 5.7186,
+      "eval_samples_per_second": 87.434,
+      "eval_steps_per_second": 5.596,
+      "step": 25920
+    },
+    {
+      "epoch": 7.2242289524868015,
+      "grad_norm": 1.0793170928955078,
+      "learning_rate": 0.0005593035102343244,
+      "loss": 0.1728,
+      "step": 26000
+    },
+    {
+      "epoch": 7.3631564323423175,
+      "grad_norm": 0.901263415813446,
+      "learning_rate": 0.0005546725942391405,
+      "loss": 0.1761,
+      "step": 26500
+    },
+    {
+      "epoch": 7.502083912197833,
+      "grad_norm": 0.5980243682861328,
+      "learning_rate": 0.0005500416782439567,
+      "loss": 0.1762,
+      "step": 27000
+    },
+    {
+      "epoch": 7.602111697693804,
+      "eval_loss": 0.2034424990415573,
+      "eval_runtime": 5.7241,
+      "eval_samples_per_second": 87.35,
+      "eval_steps_per_second": 5.59,
+      "step": 27360
+    },
+    {
+      "epoch": 7.641011392053348,
+      "grad_norm": 0.7678053975105286,
+      "learning_rate": 0.0005454200240807632,
+      "loss": 0.1754,
+      "step": 27500
+    },
+    {
+      "epoch": 7.779938871908864,
+      "grad_norm": 0.626030683517456,
+      "learning_rate": 0.0005407891080855794,
+      "loss": 0.1741,
+      "step": 28000
+    },
+    {
+      "epoch": 7.918866351764379,
+      "grad_norm": 0.6907975673675537,
+      "learning_rate": 0.0005361581920903956,
+      "loss": 0.1775,
+      "step": 28500
+    },
+    {
+      "epoch": 8.002222839677689,
+      "eval_loss": 0.19579829275608063,
+      "eval_runtime": 5.7531,
+      "eval_samples_per_second": 86.91,
+      "eval_steps_per_second": 5.562,
+      "step": 28800
+    },
+    {
+      "epoch": 8.057793831619895,
+      "grad_norm": 0.8500244617462158,
+      "learning_rate": 0.000531536537927202,
+      "loss": 0.1707,
+      "step": 29000
+    },
+    {
+      "epoch": 8.19672131147541,
+      "grad_norm": 1.2416728734970093,
+      "learning_rate": 0.0005269056219320182,
+      "loss": 0.1674,
+      "step": 29500
+    },
+    {
+      "epoch": 8.335648791330925,
+      "grad_norm": 0.7363243103027344,
+      "learning_rate": 0.0005222747059368344,
+      "loss": 0.1666,
+      "step": 30000
+    },
+    {
+      "epoch": 8.402333981661572,
+      "eval_loss": 0.19788900017738342,
+      "eval_runtime": 5.7008,
+      "eval_samples_per_second": 87.706,
+      "eval_steps_per_second": 5.613,
+      "step": 30240
+    },
+    {
+      "epoch": 8.474576271186441,
+      "grad_norm": 0.8667612671852112,
+      "learning_rate": 0.0005176437899416505,
+      "loss": 0.1681,
+      "step": 30500
+    },
+    {
+      "epoch": 8.613503751041955,
+      "grad_norm": 0.7073860168457031,
+      "learning_rate": 0.0005130128739464667,
+      "loss": 0.1706,
+      "step": 31000
+    },
+    {
+      "epoch": 8.752431230897471,
+      "grad_norm": 0.813298761844635,
+      "learning_rate": 0.0005083819579512828,
+      "loss": 0.1673,
+      "step": 31500
+    },
+    {
+      "epoch": 8.802445123645457,
+      "eval_loss": 0.2012454718351364,
+      "eval_runtime": 6.7505,
+      "eval_samples_per_second": 74.068,
+      "eval_steps_per_second": 4.74,
+      "step": 31680
+    },
+    {
+      "epoch": 8.891358710752987,
+      "grad_norm": 0.8721699118614197,
+      "learning_rate": 0.000503751041956099,
+      "loss": 0.1683,
+      "step": 32000
+    },
+    {
+      "epoch": 9.030286190608502,
+      "grad_norm": 0.7278200387954712,
+      "learning_rate": 0.000499120125960915,
+      "loss": 0.1661,
+      "step": 32500
+    },
+    {
+      "epoch": 9.169213670464018,
+      "grad_norm": 0.9835706949234009,
+      "learning_rate": 0.0004944984717977217,
+      "loss": 0.1606,
+      "step": 33000
+    },
+    {
+      "epoch": 9.202556265629342,
+      "eval_loss": 0.19326406717300415,
+      "eval_runtime": 5.7204,
+      "eval_samples_per_second": 87.406,
+      "eval_steps_per_second": 5.594,
+      "step": 33120
+    },
+    {
+      "epoch": 9.308141150319534,
+      "grad_norm": 0.7659234404563904,
+      "learning_rate": 0.0004898675558025378,
+      "loss": 0.1592,
+      "step": 33500
+    },
+    {
+      "epoch": 9.447068630175048,
+      "grad_norm": 0.8680823445320129,
+      "learning_rate": 0.00048523663980735385,
+      "loss": 0.1609,
+      "step": 34000
+    },
+    {
+      "epoch": 9.585996110030564,
+      "grad_norm": 0.7252190709114075,
+      "learning_rate": 0.00048060572381217003,
+      "loss": 0.1629,
+      "step": 34500
+    },
+    {
+      "epoch": 9.602667407613225,
+      "eval_loss": 0.18949145078659058,
+      "eval_runtime": 5.6933,
+      "eval_samples_per_second": 87.822,
+      "eval_steps_per_second": 5.621,
+      "step": 34560
+    },
+    {
+      "epoch": 9.72492358988608,
+      "grad_norm": 0.787493884563446,
+      "learning_rate": 0.0004759748078169862,
+      "loss": 0.162,
+      "step": 35000
+    },
+    {
+      "epoch": 9.863851069741594,
+      "grad_norm": 0.7298120856285095,
+      "learning_rate": 0.0004713438918218024,
+      "loss": 0.1628,
+      "step": 35500
+    },
+    {
+      "epoch": 10.00277854959711,
+      "grad_norm": 0.9931182861328125,
+      "learning_rate": 0.00046672223765860887,
+      "loss": 0.1596,
+      "step": 36000
+    },
+    {
+      "epoch": 10.00277854959711,
+      "eval_loss": 0.1884983777999878,
+      "eval_runtime": 5.7787,
+      "eval_samples_per_second": 86.525,
+      "eval_steps_per_second": 5.538,
+      "step": 36000
+    },
+    {
+      "epoch": 10.141706029452626,
+      "grad_norm": 0.8843297958374023,
+      "learning_rate": 0.00046209132166342504,
+      "loss": 0.1509,
+      "step": 36500
+    },
+    {
+      "epoch": 10.28063350930814,
+      "grad_norm": 0.6324813961982727,
+      "learning_rate": 0.00045746040566824116,
+      "loss": 0.1526,
+      "step": 37000
+    },
+    {
+      "epoch": 10.402889691580995,
+      "eval_loss": 0.1883215308189392,
+      "eval_runtime": 5.7012,
+      "eval_samples_per_second": 87.701,
+      "eval_steps_per_second": 5.613,
+      "step": 37440
+    },
+    {
+      "epoch": 10.419560989163656,
+      "grad_norm": 0.7793643474578857,
+      "learning_rate": 0.00045282948967305734,
+      "loss": 0.1548,
+      "step": 37500
+    },
+    {
+      "epoch": 10.558488469019172,
+      "grad_norm": 0.7698658108711243,
+      "learning_rate": 0.0004481985736778735,
+      "loss": 0.1528,
+      "step": 38000
+    },
+    {
+      "epoch": 10.697415948874687,
+      "grad_norm": 0.8198125958442688,
+      "learning_rate": 0.0004435676576826897,
+      "loss": 0.1545,
+      "step": 38500
+    },
+    {
+      "epoch": 10.803000833564878,
+      "eval_loss": 0.18633407354354858,
+      "eval_runtime": 5.7061,
+      "eval_samples_per_second": 87.626,
+      "eval_steps_per_second": 5.608,
+      "step": 38880
+    },
+    {
+      "epoch": 10.836343428730203,
+      "grad_norm": 0.6395444273948669,
+      "learning_rate": 0.0004389367416875058,
+      "loss": 0.1565,
+      "step": 39000
+    },
+    {
+      "epoch": 10.975270908585719,
+      "grad_norm": 0.6487806439399719,
+      "learning_rate": 0.000434305825692322,
+      "loss": 0.1553,
+      "step": 39500
+    },
+    {
+      "epoch": 11.114198388441233,
+      "grad_norm": 0.8223088383674622,
+      "learning_rate": 0.00042967490969713815,
+      "loss": 0.1454,
+      "step": 40000
+    },
+    {
+      "epoch": 11.203111975548763,
+      "eval_loss": 0.18568813800811768,
+      "eval_runtime": 5.7105,
+      "eval_samples_per_second": 87.558,
+      "eval_steps_per_second": 5.604,
+      "step": 40320
+    },
+    {
+      "epoch": 11.253125868296749,
+      "grad_norm": 0.5098241567611694,
+      "learning_rate": 0.00042505325553394464,
+      "loss": 0.147,
+      "step": 40500
+    },
+    {
+      "epoch": 11.392053348152265,
+      "grad_norm": 0.7084653377532959,
+      "learning_rate": 0.0004204223395387608,
+      "loss": 0.148,
+      "step": 41000
+    },
+    {
+      "epoch": 11.53098082800778,
+      "grad_norm": 0.6648092269897461,
+      "learning_rate": 0.00041579142354357694,
+      "loss": 0.146,
+      "step": 41500
+    },
+    {
+      "epoch": 11.603223117532648,
+      "eval_loss": 0.1823151409626007,
+      "eval_runtime": 5.7015,
+      "eval_samples_per_second": 87.696,
+      "eval_steps_per_second": 5.613,
+      "step": 41760
+    },
+    {
+      "epoch": 11.669908307863295,
+      "grad_norm": 0.7884602546691895,
+      "learning_rate": 0.0004111605075483931,
+      "loss": 0.1461,
+      "step": 42000
+    },
+    {
+      "epoch": 11.808835787718811,
+      "grad_norm": 0.6522942185401917,
+      "learning_rate": 0.0004065388533851996,
+      "loss": 0.1485,
+      "step": 42500
+    },
+    {
+      "epoch": 11.947763267574325,
+      "grad_norm": 0.8539688587188721,
+      "learning_rate": 0.0004019079373900158,
+      "loss": 0.1491,
+      "step": 43000
+    },
+    {
+      "epoch": 12.003334259516532,
+      "eval_loss": 0.17908716201782227,
+      "eval_runtime": 5.7458,
+      "eval_samples_per_second": 87.021,
+      "eval_steps_per_second": 5.569,
+      "step": 43200
+    },
+    {
+      "epoch": 12.086690747429842,
+      "grad_norm": 0.7807750701904297,
+      "learning_rate": 0.00039728628322682226,
+      "loss": 0.1401,
+      "step": 43500
+    },
+    {
+      "epoch": 12.225618227285358,
+      "grad_norm": 0.9898711442947388,
+      "learning_rate": 0.00039265536723163844,
+      "loss": 0.1368,
+      "step": 44000
+    },
+    {
+      "epoch": 12.364545707140872,
+      "grad_norm": 0.6105939149856567,
+      "learning_rate": 0.0003880244512364546,
+      "loss": 0.1395,
+      "step": 44500
+    },
+    {
+      "epoch": 12.403445401500417,
+      "eval_loss": 0.1828669160604477,
+      "eval_runtime": 5.7589,
+      "eval_samples_per_second": 86.822,
+      "eval_steps_per_second": 5.557,
+      "step": 44640
+    },
+    {
+      "epoch": 12.503473186996388,
+      "grad_norm": 0.659959077835083,
+      "learning_rate": 0.00038339353524127073,
+      "loss": 0.1437,
+      "step": 45000
+    },
+    {
+      "epoch": 12.642400666851904,
+      "grad_norm": 0.8805100321769714,
+      "learning_rate": 0.0003787626192460869,
+      "loss": 0.1414,
+      "step": 45500
+    },
+    {
+      "epoch": 12.781328146707418,
+      "grad_norm": 1.0838948488235474,
+      "learning_rate": 0.000374131703250903,
+      "loss": 0.142,
+      "step": 46000
+    },
+    {
+      "epoch": 12.803556543484301,
+      "eval_loss": 0.17811129987239838,
+      "eval_runtime": 5.7271,
+      "eval_samples_per_second": 87.304,
+      "eval_steps_per_second": 5.587,
+      "step": 46080
+    },
+    {
+      "epoch": 12.920255626562934,
+      "grad_norm": 0.5533807277679443,
+      "learning_rate": 0.0003695007872557192,
+      "loss": 0.1417,
+      "step": 46500
+    },
+    {
+      "epoch": 13.05918310641845,
+      "grad_norm": 0.6328546404838562,
+      "learning_rate": 0.0003648698712605354,
+      "loss": 0.1363,
+      "step": 47000
+    },
+    {
+      "epoch": 13.198110586273964,
+      "grad_norm": 0.8364810347557068,
+      "learning_rate": 0.0003602389552653515,
+      "loss": 0.131,
+      "step": 47500
+    },
+    {
+      "epoch": 13.203667685468186,
+      "eval_loss": 0.17920471727848053,
+      "eval_runtime": 5.6832,
+      "eval_samples_per_second": 87.979,
+      "eval_steps_per_second": 5.631,
+      "step": 47520
+    },
+    {
+      "epoch": 13.33703806612948,
+      "grad_norm": 0.754403829574585,
+      "learning_rate": 0.0003556080392701676,
+      "loss": 0.1334,
+      "step": 48000
+    },
+    {
+      "epoch": 13.475965545984996,
+      "grad_norm": 0.7372345924377441,
+      "learning_rate": 0.0003509771232749838,
+      "loss": 0.1323,
+      "step": 48500
+    },
+    {
+      "epoch": 13.60377882745207,
+      "eval_loss": 0.18234029412269592,
+      "eval_runtime": 5.692,
+      "eval_samples_per_second": 87.843,
+      "eval_steps_per_second": 5.622,
+      "step": 48960
+    },
+    {
+      "epoch": 13.61489302584051,
+      "grad_norm": 0.5553024411201477,
+      "learning_rate": 0.00034635546911179033,
+      "loss": 0.1345,
+      "step": 49000
+    },
+    {
+      "epoch": 13.753820505696027,
+      "grad_norm": 0.6826585531234741,
+      "learning_rate": 0.0003417245531166065,
+      "loss": 0.1329,
+      "step": 49500
+    },
+    {
+      "epoch": 13.892747985551543,
+      "grad_norm": 0.622280478477478,
+      "learning_rate": 0.00033709363712142263,
+      "loss": 0.1339,
+      "step": 50000
+    },
+    {
+      "epoch": 14.003889969435955,
+      "eval_loss": 0.1794731467962265,
+      "eval_runtime": 5.7345,
+      "eval_samples_per_second": 87.192,
+      "eval_steps_per_second": 5.58,
+      "step": 50400
+    },
+    {
+      "epoch": 14.031675465407057,
+      "grad_norm": 0.7773860692977905,
+      "learning_rate": 0.00033246272112623875,
+      "loss": 0.1324,
+      "step": 50500
+    },
+    {
+      "epoch": 14.170602945262573,
+      "grad_norm": 0.6761751174926758,
+      "learning_rate": 0.0003278410669630453,
+      "loss": 0.1225,
+      "step": 51000
+    },
+    {
+      "epoch": 14.309530425118089,
+      "grad_norm": 0.6650680303573608,
+      "learning_rate": 0.00032321015096786147,
+      "loss": 0.1261,
+      "step": 51500
+    },
+    {
+      "epoch": 14.40400111141984,
+      "eval_loss": 0.17374251782894135,
+      "eval_runtime": 5.7241,
+      "eval_samples_per_second": 87.351,
+      "eval_steps_per_second": 5.59,
+      "step": 51840
+    },
+    {
+      "epoch": 14.448457904973603,
+      "grad_norm": 0.8033860921859741,
+      "learning_rate": 0.00031857923497267764,
+      "loss": 0.1264,
+      "step": 52000
+    },
+    {
+      "epoch": 14.587385384829119,
+      "grad_norm": 1.125452995300293,
+      "learning_rate": 0.00031394831897749376,
+      "loss": 0.1283,
+      "step": 52500
+    },
+    {
+      "epoch": 14.726312864684635,
+      "grad_norm": 0.7282013297080994,
+      "learning_rate": 0.00030931740298230994,
+      "loss": 0.1279,
+      "step": 53000
+    },
+    {
+      "epoch": 14.804112253403723,
+      "eval_loss": 0.17884068191051483,
+      "eval_runtime": 5.7161,
+      "eval_samples_per_second": 87.473,
+      "eval_steps_per_second": 5.598,
+      "step": 53280
+    },
+    {
+      "epoch": 14.86524034454015,
+      "grad_norm": 0.763498842716217,
+      "learning_rate": 0.0003046957488191164,
+      "loss": 0.1272,
+      "step": 53500
+    },
+    {
+      "epoch": 15.004167824395665,
+      "grad_norm": 0.5262055993080139,
+      "learning_rate": 0.0003000648328239326,
+      "loss": 0.1263,
+      "step": 54000
+    },
+    {
+      "epoch": 15.143095304251181,
+      "grad_norm": 0.6095721125602722,
+      "learning_rate": 0.0002954339168287487,
+      "loss": 0.1168,
+      "step": 54500
+    },
+    {
+      "epoch": 15.204223395387608,
+      "eval_loss": 0.17539146542549133,
+      "eval_runtime": 5.7056,
+      "eval_samples_per_second": 87.634,
+      "eval_steps_per_second": 5.609,
+      "step": 54720
+    },
+    {
+      "epoch": 15.282022784106696,
+      "grad_norm": 0.7185012698173523,
+      "learning_rate": 0.0002908030008335649,
+      "loss": 0.1194,
+      "step": 55000
+    },
+    {
+      "epoch": 15.420950263962212,
+      "grad_norm": 0.8502697944641113,
+      "learning_rate": 0.00028617208483838107,
+      "loss": 0.1172,
+      "step": 55500
+    },
+    {
+      "epoch": 15.559877743817728,
+      "grad_norm": 0.7366784811019897,
+      "learning_rate": 0.0002815411688431972,
+      "loss": 0.1199,
+      "step": 56000
+    },
+    {
+      "epoch": 15.604334537371493,
+      "eval_loss": 0.174043670296669,
+      "eval_runtime": 5.6949,
+      "eval_samples_per_second": 87.798,
+      "eval_steps_per_second": 5.619,
+      "step": 56160
+    },
+    {
+      "epoch": 15.698805223673242,
+      "grad_norm": 0.7937948703765869,
+      "learning_rate": 0.0002769102528480133,
+      "loss": 0.1216,
+      "step": 56500
+    },
+    {
+      "epoch": 15.837732703528758,
+      "grad_norm": 0.6836448311805725,
+      "learning_rate": 0.0002722793368528295,
+      "loss": 0.1201,
+      "step": 57000
+    },
+    {
+      "epoch": 15.976660183384274,
+      "grad_norm": 0.8301613330841064,
+      "learning_rate": 0.0002676669445216264,
+      "loss": 0.121,
+      "step": 57500
+    },
+    {
+      "epoch": 16.004445679355378,
+      "eval_loss": 0.17525814473628998,
+      "eval_runtime": 5.7223,
+      "eval_samples_per_second": 87.378,
+      "eval_steps_per_second": 5.592,
+      "step": 57600
+    },
+    {
+      "epoch": 16.11558766323979,
+      "grad_norm": 0.801866352558136,
+      "learning_rate": 0.00026303602852644257,
+      "loss": 0.1109,
+      "step": 58000
+    },
+    {
+      "epoch": 16.254515143095304,
+      "grad_norm": 0.7740326523780823,
+      "learning_rate": 0.0002584051125312587,
+      "loss": 0.1102,
+      "step": 58500
+    },
+    {
+      "epoch": 16.39344262295082,
+      "grad_norm": 0.6305615305900574,
+      "learning_rate": 0.00025377419653607486,
+      "loss": 0.1125,
+      "step": 59000
+    },
+    {
+      "epoch": 16.40455682133926,
+      "eval_loss": 0.17229421436786652,
+      "eval_runtime": 5.7155,
+      "eval_samples_per_second": 87.482,
+      "eval_steps_per_second": 5.599,
+      "step": 59040
+    },
+    {
+      "epoch": 16.532370102806336,
+      "grad_norm": 0.8209009766578674,
+      "learning_rate": 0.000249143280540891,
+      "loss": 0.1139,
+      "step": 59500
+    },
+    {
+      "epoch": 16.67129758266185,
+      "grad_norm": 1.0618516206741333,
+      "learning_rate": 0.00024451236454570716,
+      "loss": 0.1151,
+      "step": 60000
+    },
+    {
+      "epoch": 16.804667963323144,
+      "eval_loss": 0.17186084389686584,
+      "eval_runtime": 5.724,
+      "eval_samples_per_second": 87.352,
+      "eval_steps_per_second": 5.591,
+      "step": 60480
+    },
+    {
+      "epoch": 16.810225062517365,
+      "grad_norm": 1.1203557252883911,
+      "learning_rate": 0.0002398907103825137,
+      "loss": 0.1127,
+      "step": 60500
+    },
+    {
+      "epoch": 16.949152542372882,
+      "grad_norm": 0.9507138729095459,
+      "learning_rate": 0.00023525979438732982,
+      "loss": 0.1138,
+      "step": 61000
+    },
+    {
+      "epoch": 17.088080022228397,
+      "grad_norm": 0.50418621301651,
+      "learning_rate": 0.00023062887839214597,
+      "loss": 0.1053,
+      "step": 61500
+    },
+    {
+      "epoch": 17.20477910530703,
+      "eval_loss": 0.17183047533035278,
+      "eval_runtime": 5.7075,
+      "eval_samples_per_second": 87.604,
+      "eval_steps_per_second": 5.607,
+      "step": 61920
+    },
+    {
+      "epoch": 17.22700750208391,
+      "grad_norm": 0.8892719149589539,
+      "learning_rate": 0.00022599796239696214,
+      "loss": 0.1053,
+      "step": 62000
+    },
+    {
+      "epoch": 17.36593498193943,
+      "grad_norm": 0.4419918358325958,
+      "learning_rate": 0.00022137630823376866,
+      "loss": 0.1055,
+      "step": 62500
+    },
+    {
+      "epoch": 17.504862461794943,
+      "grad_norm": 0.7942801117897034,
+      "learning_rate": 0.00021674539223858478,
+      "loss": 0.106,
+      "step": 63000
+    },
+    {
+      "epoch": 17.604890247290914,
+      "eval_loss": 0.16908669471740723,
+      "eval_runtime": 5.6994,
+      "eval_samples_per_second": 87.728,
+      "eval_steps_per_second": 5.615,
+      "step": 63360
+    },
+    {
+      "epoch": 17.643789941650457,
+      "grad_norm": 0.72785884141922,
+      "learning_rate": 0.00021211447624340095,
+      "loss": 0.1061,
+      "step": 63500
+    },
+    {
+      "epoch": 17.782717421505975,
+      "grad_norm": 0.6169493198394775,
+      "learning_rate": 0.0002074835602482171,
+      "loss": 0.105,
+      "step": 64000
+    },
+    {
+      "epoch": 17.92164490136149,
+      "grad_norm": 0.6713001132011414,
+      "learning_rate": 0.00020285264425303328,
+      "loss": 0.1073,
+      "step": 64500
+    },
+    {
+      "epoch": 18.0050013892748,
+      "eval_loss": 0.17229732871055603,
+      "eval_runtime": 5.7663,
+      "eval_samples_per_second": 86.711,
+      "eval_steps_per_second": 5.55,
+      "step": 64800
+    },
+    {
+      "epoch": 18.060572381217003,
+      "grad_norm": 0.5809840559959412,
+      "learning_rate": 0.00019822172825784942,
+      "loss": 0.1034,
+      "step": 65000
+    },
+    {
+      "epoch": 18.19949986107252,
+      "grad_norm": 0.5985963344573975,
+      "learning_rate": 0.00019359081226266554,
+      "loss": 0.097,
+      "step": 65500
+    },
+    {
+      "epoch": 18.338427340928035,
+      "grad_norm": 0.8002266883850098,
+      "learning_rate": 0.00018895989626748172,
+      "loss": 0.0973,
+      "step": 66000
+    },
+    {
+      "epoch": 18.405112531258684,
+      "eval_loss": 0.16905440390110016,
+      "eval_runtime": 5.6988,
+      "eval_samples_per_second": 87.738,
+      "eval_steps_per_second": 5.615,
+      "step": 66240
+    },
+    {
+      "epoch": 18.47735482078355,
+      "grad_norm": 0.841440737247467,
+      "learning_rate": 0.0001843289802722979,
+      "loss": 0.0992,
+      "step": 66500
+    },
+    {
+      "epoch": 18.616282300639067,
+      "grad_norm": 0.8495504260063171,
+      "learning_rate": 0.000179698064277114,
+      "loss": 0.1002,
+      "step": 67000
+    },
+    {
+      "epoch": 18.75520978049458,
+      "grad_norm": 0.6956267952919006,
+      "learning_rate": 0.00017507641011392055,
+      "loss": 0.1009,
+      "step": 67500
+    },
+    {
+      "epoch": 18.80522367324257,
+      "eval_loss": 0.1660514622926712,
+      "eval_runtime": 5.719,
+      "eval_samples_per_second": 87.428,
+      "eval_steps_per_second": 5.595,
+      "step": 67680
+    },
+    {
+      "epoch": 18.894137260350096,
+      "grad_norm": 0.6415526270866394,
+      "learning_rate": 0.0001704454941187367,
+      "loss": 0.1011,
+      "step": 68000
+    },
+    {
+      "epoch": 19.033064740205614,
+      "grad_norm": 0.6368350982666016,
+      "learning_rate": 0.00016581457812355285,
+      "loss": 0.0989,
+      "step": 68500
+    },
+    {
+      "epoch": 19.171992220061128,
+      "grad_norm": 0.9284315705299377,
+      "learning_rate": 0.000161183662128369,
+      "loss": 0.0908,
+      "step": 69000
+    },
+    {
+      "epoch": 19.20533481522645,
+      "eval_loss": 0.17813153564929962,
+      "eval_runtime": 5.7094,
+      "eval_samples_per_second": 87.574,
+      "eval_steps_per_second": 5.605,
+      "step": 69120
+    },
+    {
+      "epoch": 19.310919699916642,
+      "grad_norm": 0.905992329120636,
+      "learning_rate": 0.00015655274613318515,
+      "loss": 0.0924,
+      "step": 69500
+    },
+    {
+      "epoch": 19.44984717977216,
+      "grad_norm": 0.6849103569984436,
+      "learning_rate": 0.0001519218301380013,
+      "loss": 0.0935,
+      "step": 70000
+    },
+    {
+      "epoch": 19.588774659627674,
+      "grad_norm": 1.106966495513916,
+      "learning_rate": 0.00014729091414281747,
+      "loss": 0.0926,
+      "step": 70500
+    },
+    {
+      "epoch": 19.605445957210335,
+      "eval_loss": 0.1741752326488495,
+      "eval_runtime": 5.7045,
+      "eval_samples_per_second": 87.651,
+      "eval_steps_per_second": 5.61,
+      "step": 70560
+    },
+    {
+      "epoch": 19.72770213948319,
+      "grad_norm": 0.8819716572761536,
+      "learning_rate": 0.0001426599981476336,
+      "loss": 0.0941,
+      "step": 71000
+    },
+    {
+      "epoch": 19.866629619338706,
+      "grad_norm": 0.7679275870323181,
+      "learning_rate": 0.00013803834398444013,
+      "loss": 0.0934,
+      "step": 71500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 86376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 24,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.5998916700798976e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-71980/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f04554acd1689dfcf765ddfc83593c217e6ad8c0837409b2e0544a3f5759a0
+size 5496