Training in progress, epoch 11, checkpoint

checkpoint-39589/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-39589/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-39589/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e074e647343498f39d82410c3f278eda452a6ba9e9a23787ab2223f49d1c1d
+size 268636736

checkpoint-39589/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab91f64f7158ac326bf4815b3fc5b79af43acbfb3a426fbae37dec98551f278
+size 12663802

checkpoint-39589/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7841518c40c21fea37708001b5c31e3a6bb3e7f75e0399397168fe68f761cd5
+size 15984

checkpoint-39589/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39b427dbde51d64a0e582f4a63b4b2199f483b67b2e27af806e3f029a36e103
+size 15984

checkpoint-39589/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c8349cd885aa52f701e7528e06ea3c77ef78859689dabbeb471836f6b36814
+size 15984

checkpoint-39589/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56b5e3f8e07afee6efad436b347d518c1ea19b858eca483a55e51c4548a419ef
+size 15984

checkpoint-39589/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bfc055d1318e081a1b031ee8541389d2517985b696ab40ea8ed695dc1ca6ad
+size 15984

checkpoint-39589/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0c4333c9c20672209f568207954fb04c156b845421f2f4090a09d1bc69c37e
+size 15984

checkpoint-39589/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26eb2d075388e5731f1011b5aa369439b80db46ee8572837f422a63e384b8d4
+size 15984

checkpoint-39589/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4896d0121d3e1f03500463afb926d162d189ac30e205f041064a50b5936c7f
+size 15984

checkpoint-39589/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40124b9fa44a8244e95010ca63836f5b429b4f1eb0e7177107593c42c91210b1
+size 1064

checkpoint-39589/trainer_state.json

@@ -0,0 +1,1018 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.0,
+  "eval_steps": 720,
+  "global_step": 39589,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13892747985551543,
+      "grad_norm": 1.1198960542678833,
+      "learning_rate": 0.0007907752153375939,
+      "loss": 0.637,
+      "step": 500
+    },
+    {
+      "epoch": 0.2000555709919422,
+      "eval_loss": 0.5050423741340637,
+      "eval_runtime": 3.7601,
+      "eval_samples_per_second": 132.977,
+      "eval_steps_per_second": 8.511,
+      "step": 720
+    },
+    {
+      "epoch": 0.27785495971103086,
+      "grad_norm": 0.9483360052108765,
+      "learning_rate": 0.0007815319070112068,
+      "loss": 0.5002,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4001111419838844,
+      "eval_loss": 0.46449729800224304,
+      "eval_runtime": 3.8072,
+      "eval_samples_per_second": 131.331,
+      "eval_steps_per_second": 8.405,
+      "step": 1440
+    },
+    {
+      "epoch": 0.41678243956654626,
+      "grad_norm": 1.063967227935791,
+      "learning_rate": 0.0007722700750208392,
+      "loss": 0.4557,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5557099194220617,
+      "grad_norm": 0.9635094404220581,
+      "learning_rate": 0.0007630082430304714,
+      "loss": 0.4345,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6001667129758266,
+      "eval_loss": 0.43028712272644043,
+      "eval_runtime": 3.8043,
+      "eval_samples_per_second": 131.43,
+      "eval_steps_per_second": 8.412,
+      "step": 2160
+    },
+    {
+      "epoch": 0.6946373992775771,
+      "grad_norm": 0.9948890209197998,
+      "learning_rate": 0.0007537464110401038,
+      "loss": 0.4164,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8002222839677688,
+      "eval_loss": 0.4203771948814392,
+      "eval_runtime": 3.7908,
+      "eval_samples_per_second": 131.898,
+      "eval_steps_per_second": 8.442,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8335648791330925,
+      "grad_norm": 1.4267702102661133,
+      "learning_rate": 0.000744484579049736,
+      "loss": 0.3981,
+      "step": 3000
+    },
+    {
+      "epoch": 0.972492358988608,
+      "grad_norm": 1.177148461341858,
+      "learning_rate": 0.0007352227470593684,
+      "loss": 0.3958,
+      "step": 3500
+    },
+    {
+      "epoch": 1.000277854959711,
+      "eval_loss": 0.39980679750442505,
+      "eval_runtime": 3.8941,
+      "eval_samples_per_second": 128.4,
+      "eval_steps_per_second": 8.218,
+      "step": 3600
+    },
+    {
+      "epoch": 1.1114198388441234,
+      "grad_norm": 1.0571914911270142,
+      "learning_rate": 0.0007259609150690007,
+      "loss": 0.3615,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2003334259516532,
+      "eval_loss": 0.3898833692073822,
+      "eval_runtime": 3.8575,
+      "eval_samples_per_second": 129.618,
+      "eval_steps_per_second": 8.296,
+      "step": 4320
+    },
+    {
+      "epoch": 1.2503473186996388,
+      "grad_norm": 1.0240044593811035,
+      "learning_rate": 0.000716699083078633,
+      "loss": 0.3594,
+      "step": 4500
+    },
+    {
+      "epoch": 1.3892747985551543,
+      "grad_norm": 1.240479588508606,
+      "learning_rate": 0.0007074742984162268,
+      "loss": 0.3575,
+      "step": 5000
+    },
+    {
+      "epoch": 1.4003889969435954,
+      "eval_loss": 0.37695348262786865,
+      "eval_runtime": 4.625,
+      "eval_samples_per_second": 108.108,
+      "eval_steps_per_second": 6.919,
+      "step": 5040
+    },
+    {
+      "epoch": 1.5282022784106695,
+      "grad_norm": 1.1636780500411987,
+      "learning_rate": 0.000698212466425859,
+      "loss": 0.3529,
+      "step": 5500
+    },
+    {
+      "epoch": 1.6004445679355377,
+      "eval_loss": 0.37476062774658203,
+      "eval_runtime": 3.7919,
+      "eval_samples_per_second": 131.859,
+      "eval_steps_per_second": 8.439,
+      "step": 5760
+    },
+    {
+      "epoch": 1.667129758266185,
+      "grad_norm": 0.9645657539367676,
+      "learning_rate": 0.0006889506344354914,
+      "loss": 0.35,
+      "step": 6000
+    },
+    {
+      "epoch": 1.8005001389274797,
+      "eval_loss": 0.3607681393623352,
+      "eval_runtime": 3.8,
+      "eval_samples_per_second": 131.579,
+      "eval_steps_per_second": 8.421,
+      "step": 6480
+    },
+    {
+      "epoch": 1.8060572381217006,
+      "grad_norm": 1.0501099824905396,
+      "learning_rate": 0.0006796888024451237,
+      "loss": 0.3423,
+      "step": 6500
+    },
+    {
+      "epoch": 1.9449847179772157,
+      "grad_norm": 0.9878831505775452,
+      "learning_rate": 0.0006704269704547561,
+      "loss": 0.3449,
+      "step": 7000
+    },
+    {
+      "epoch": 2.000555709919422,
+      "eval_loss": 0.35729101300239563,
+      "eval_runtime": 3.9554,
+      "eval_samples_per_second": 126.41,
+      "eval_steps_per_second": 8.09,
+      "step": 7200
+    },
+    {
+      "epoch": 2.0839121978327313,
+      "grad_norm": 1.2939465045928955,
+      "learning_rate": 0.000661183662128369,
+      "loss": 0.3238,
+      "step": 7500
+    },
+    {
+      "epoch": 2.2006112809113643,
+      "eval_loss": 0.35569658875465393,
+      "eval_runtime": 3.8225,
+      "eval_samples_per_second": 130.803,
+      "eval_steps_per_second": 8.371,
+      "step": 7920
+    },
+    {
+      "epoch": 2.222839677688247,
+      "grad_norm": 1.2539418935775757,
+      "learning_rate": 0.0006519218301380013,
+      "loss": 0.3166,
+      "step": 8000
+    },
+    {
+      "epoch": 2.361767157543762,
+      "grad_norm": 1.2524042129516602,
+      "learning_rate": 0.0006426599981476336,
+      "loss": 0.3181,
+      "step": 8500
+    },
+    {
+      "epoch": 2.4006668519033063,
+      "eval_loss": 0.349068820476532,
+      "eval_runtime": 3.8105,
+      "eval_samples_per_second": 131.218,
+      "eval_steps_per_second": 8.398,
+      "step": 8640
+    },
+    {
+      "epoch": 2.5006946373992776,
+      "grad_norm": 1.388472318649292,
+      "learning_rate": 0.000633398166157266,
+      "loss": 0.3131,
+      "step": 9000
+    },
+    {
+      "epoch": 2.600722422895249,
+      "eval_loss": 0.3446434438228607,
+      "eval_runtime": 3.8521,
+      "eval_samples_per_second": 129.8,
+      "eval_steps_per_second": 8.307,
+      "step": 9360
+    },
+    {
+      "epoch": 2.639622117254793,
+      "grad_norm": 1.244354486465454,
+      "learning_rate": 0.000624154857830879,
+      "loss": 0.3143,
+      "step": 9500
+    },
+    {
+      "epoch": 2.7785495971103087,
+      "grad_norm": 0.7853448987007141,
+      "learning_rate": 0.0006148930258405113,
+      "loss": 0.3114,
+      "step": 10000
+    },
+    {
+      "epoch": 2.800777993887191,
+      "eval_loss": 0.33502963185310364,
+      "eval_runtime": 4.0683,
+      "eval_samples_per_second": 122.902,
+      "eval_steps_per_second": 7.866,
+      "step": 10080
+    },
+    {
+      "epoch": 2.917477076965824,
+      "grad_norm": 0.8103400468826294,
+      "learning_rate": 0.0006056311938501436,
+      "loss": 0.3125,
+      "step": 10500
+    },
+    {
+      "epoch": 3.000833564879133,
+      "eval_loss": 0.33597758412361145,
+      "eval_runtime": 3.7986,
+      "eval_samples_per_second": 131.628,
+      "eval_steps_per_second": 8.424,
+      "step": 10800
+    },
+    {
+      "epoch": 3.0564045568213394,
+      "grad_norm": 0.9693534970283508,
+      "learning_rate": 0.0005963878855237566,
+      "loss": 0.2984,
+      "step": 11000
+    },
+    {
+      "epoch": 3.1953320366768545,
+      "grad_norm": 0.8575369715690613,
+      "learning_rate": 0.0005871260535333889,
+      "loss": 0.286,
+      "step": 11500
+    },
+    {
+      "epoch": 3.2008891358710754,
+      "eval_loss": 0.3322838842868805,
+      "eval_runtime": 3.8858,
+      "eval_samples_per_second": 128.675,
+      "eval_steps_per_second": 8.235,
+      "step": 11520
+    },
+    {
+      "epoch": 3.33425951653237,
+      "grad_norm": 0.8576149940490723,
+      "learning_rate": 0.0005778642215430212,
+      "loss": 0.2892,
+      "step": 12000
+    },
+    {
+      "epoch": 3.4009447068630174,
+      "eval_loss": 0.32555091381073,
+      "eval_runtime": 3.7706,
+      "eval_samples_per_second": 132.606,
+      "eval_steps_per_second": 8.487,
+      "step": 12240
+    },
+    {
+      "epoch": 3.4731869963878856,
+      "grad_norm": 1.3117287158966064,
+      "learning_rate": 0.0005686023895526536,
+      "loss": 0.2873,
+      "step": 12500
+    },
+    {
+      "epoch": 3.6010002778549595,
+      "eval_loss": 0.3197897970676422,
+      "eval_runtime": 3.8882,
+      "eval_samples_per_second": 128.594,
+      "eval_steps_per_second": 8.23,
+      "step": 12960
+    },
+    {
+      "epoch": 3.612114476243401,
+      "grad_norm": 1.0069260597229004,
+      "learning_rate": 0.0005593405575622859,
+      "loss": 0.2912,
+      "step": 13000
+    },
+    {
+      "epoch": 3.7510419560989163,
+      "grad_norm": 1.4077204465866089,
+      "learning_rate": 0.0005500787255719182,
+      "loss": 0.2845,
+      "step": 13500
+    },
+    {
+      "epoch": 3.801055848846902,
+      "eval_loss": 0.32024767994880676,
+      "eval_runtime": 3.7838,
+      "eval_samples_per_second": 132.144,
+      "eval_steps_per_second": 8.457,
+      "step": 13680
+    },
+    {
+      "epoch": 3.889969435954432,
+      "grad_norm": 1.086256980895996,
+      "learning_rate": 0.0005408168935815504,
+      "loss": 0.2874,
+      "step": 14000
+    },
+    {
+      "epoch": 4.001111419838844,
+      "eval_loss": 0.310783326625824,
+      "eval_runtime": 3.8395,
+      "eval_samples_per_second": 130.225,
+      "eval_steps_per_second": 8.334,
+      "step": 14400
+    },
+    {
+      "epoch": 4.0288969158099475,
+      "grad_norm": 1.1111361980438232,
+      "learning_rate": 0.0005315550615911827,
+      "loss": 0.2773,
+      "step": 14500
+    },
+    {
+      "epoch": 4.167824395665463,
+      "grad_norm": 1.456834316253662,
+      "learning_rate": 0.0005222932296008151,
+      "loss": 0.2591,
+      "step": 15000
+    },
+    {
+      "epoch": 4.201166990830786,
+      "eval_loss": 0.32236987352371216,
+      "eval_runtime": 3.8241,
+      "eval_samples_per_second": 130.751,
+      "eval_steps_per_second": 8.368,
+      "step": 15120
+    },
+    {
+      "epoch": 4.306751875520978,
+      "grad_norm": 1.0425251722335815,
+      "learning_rate": 0.0005130499212744282,
+      "loss": 0.2663,
+      "step": 15500
+    },
+    {
+      "epoch": 4.4012225618227285,
+      "eval_loss": 0.3159812390804291,
+      "eval_runtime": 3.8272,
+      "eval_samples_per_second": 130.644,
+      "eval_steps_per_second": 8.361,
+      "step": 15840
+    },
+    {
+      "epoch": 4.445679355376494,
+      "grad_norm": 1.142910122871399,
+      "learning_rate": 0.0005038066129480412,
+      "loss": 0.2665,
+      "step": 16000
+    },
+    {
+      "epoch": 4.584606835232009,
+      "grad_norm": 0.8589379191398621,
+      "learning_rate": 0.0004945447809576734,
+      "loss": 0.2617,
+      "step": 16500
+    },
+    {
+      "epoch": 4.601278132814671,
+      "eval_loss": 0.31165239214897156,
+      "eval_runtime": 3.9058,
+      "eval_samples_per_second": 128.014,
+      "eval_steps_per_second": 8.193,
+      "step": 16560
+    },
+    {
+      "epoch": 4.723534315087524,
+      "grad_norm": 1.43936026096344,
+      "learning_rate": 0.0004852829489673058,
+      "loss": 0.2688,
+      "step": 17000
+    },
+    {
+      "epoch": 4.801333703806613,
+      "eval_loss": 0.30395612120628357,
+      "eval_runtime": 3.8056,
+      "eval_samples_per_second": 131.385,
+      "eval_steps_per_second": 8.409,
+      "step": 17280
+    },
+    {
+      "epoch": 4.86246179494304,
+      "grad_norm": 0.8109529614448547,
+      "learning_rate": 0.0004760211169769381,
+      "loss": 0.2655,
+      "step": 17500
+    },
+    {
+      "epoch": 5.001389274798555,
+      "grad_norm": 1.0239903926849365,
+      "learning_rate": 0.00046675928498657033,
+      "loss": 0.2603,
+      "step": 18000
+    },
+    {
+      "epoch": 5.001389274798555,
+      "eval_loss": 0.3051631450653076,
+      "eval_runtime": 3.8213,
+      "eval_samples_per_second": 130.845,
+      "eval_steps_per_second": 8.374,
+      "step": 18000
+    },
+    {
+      "epoch": 5.14031675465407,
+      "grad_norm": 0.9971492290496826,
+      "learning_rate": 0.0004574974529962027,
+      "loss": 0.2401,
+      "step": 18500
+    },
+    {
+      "epoch": 5.201444845790498,
+      "eval_loss": 0.3025811016559601,
+      "eval_runtime": 4.1633,
+      "eval_samples_per_second": 120.096,
+      "eval_steps_per_second": 7.686,
+      "step": 18720
+    },
+    {
+      "epoch": 5.279244234509586,
+      "grad_norm": 0.9720182418823242,
+      "learning_rate": 0.000448235621005835,
+      "loss": 0.2403,
+      "step": 19000
+    },
+    {
+      "epoch": 5.401500416782439,
+      "eval_loss": 0.299972265958786,
+      "eval_runtime": 4.655,
+      "eval_samples_per_second": 107.411,
+      "eval_steps_per_second": 6.874,
+      "step": 19440
+    },
+    {
+      "epoch": 5.418171714365101,
+      "grad_norm": 1.4856421947479248,
+      "learning_rate": 0.00043899231267944806,
+      "loss": 0.2421,
+      "step": 19500
+    },
+    {
+      "epoch": 5.5570991942206165,
+      "grad_norm": 1.0803531408309937,
+      "learning_rate": 0.0004297304806890803,
+      "loss": 0.2424,
+      "step": 20000
+    },
+    {
+      "epoch": 5.601555987774382,
+      "eval_loss": 0.29013943672180176,
+      "eval_runtime": 3.8417,
+      "eval_samples_per_second": 130.15,
+      "eval_steps_per_second": 8.33,
+      "step": 20160
+    },
+    {
+      "epoch": 5.6960266740761325,
+      "grad_norm": 1.2330774068832397,
+      "learning_rate": 0.0004204686486987126,
+      "loss": 0.2429,
+      "step": 20500
+    },
+    {
+      "epoch": 5.801611558766324,
+      "eval_loss": 0.2877044677734375,
+      "eval_runtime": 4.5536,
+      "eval_samples_per_second": 109.803,
+      "eval_steps_per_second": 7.027,
+      "step": 20880
+    },
+    {
+      "epoch": 5.834954153931648,
+      "grad_norm": 0.753556489944458,
+      "learning_rate": 0.00041120681670834495,
+      "loss": 0.2399,
+      "step": 21000
+    },
+    {
+      "epoch": 5.973881633787163,
+      "grad_norm": 1.157812237739563,
+      "learning_rate": 0.00040194498471797724,
+      "loss": 0.2396,
+      "step": 21500
+    },
+    {
+      "epoch": 6.001667129758266,
+      "eval_loss": 0.28767964243888855,
+      "eval_runtime": 3.835,
+      "eval_samples_per_second": 130.379,
+      "eval_steps_per_second": 8.344,
+      "step": 21600
+    },
+    {
+      "epoch": 6.112809113642679,
+      "grad_norm": 1.0191729068756104,
+      "learning_rate": 0.00039268315272760954,
+      "loss": 0.2204,
+      "step": 22000
+    },
+    {
+      "epoch": 6.201722700750208,
+      "eval_loss": 0.2886238396167755,
+      "eval_runtime": 3.8094,
+      "eval_samples_per_second": 131.255,
+      "eval_steps_per_second": 8.4,
+      "step": 22320
+    },
+    {
+      "epoch": 6.251736593498194,
+      "grad_norm": 0.9320778846740723,
+      "learning_rate": 0.00038343984440122257,
+      "loss": 0.2188,
+      "step": 22500
+    },
+    {
+      "epoch": 6.390664073353709,
+      "grad_norm": 1.2492601871490479,
+      "learning_rate": 0.00037417801241085486,
+      "loss": 0.2234,
+      "step": 23000
+    },
+    {
+      "epoch": 6.401778271742151,
+      "eval_loss": 0.28561460971832275,
+      "eval_runtime": 3.9577,
+      "eval_samples_per_second": 126.337,
+      "eval_steps_per_second": 8.086,
+      "step": 23040
+    },
+    {
+      "epoch": 6.529591553209225,
+      "grad_norm": 1.1227470636367798,
+      "learning_rate": 0.0003649161804204872,
+      "loss": 0.2215,
+      "step": 23500
+    },
+    {
+      "epoch": 6.601833842734093,
+      "eval_loss": 0.28328219056129456,
+      "eval_runtime": 3.7863,
+      "eval_samples_per_second": 132.054,
+      "eval_steps_per_second": 8.451,
+      "step": 23760
+    },
+    {
+      "epoch": 6.66851903306474,
+      "grad_norm": 1.1865583658218384,
+      "learning_rate": 0.0003556543484301195,
+      "loss": 0.2198,
+      "step": 24000
+    },
+    {
+      "epoch": 6.801889413726035,
+      "eval_loss": 0.27882036566734314,
+      "eval_runtime": 4.0423,
+      "eval_samples_per_second": 123.693,
+      "eval_steps_per_second": 7.916,
+      "step": 24480
+    },
+    {
+      "epoch": 6.807446512920255,
+      "grad_norm": 0.7896998524665833,
+      "learning_rate": 0.0003463925164397518,
+      "loss": 0.2213,
+      "step": 24500
+    },
+    {
+      "epoch": 6.946373992775771,
+      "grad_norm": 1.0713887214660645,
+      "learning_rate": 0.0003371306844493841,
+      "loss": 0.2202,
+      "step": 25000
+    },
+    {
+      "epoch": 7.001944984717977,
+      "eval_loss": 0.2714787721633911,
+      "eval_runtime": 3.8612,
+      "eval_samples_per_second": 129.493,
+      "eval_steps_per_second": 8.288,
+      "step": 25200
+    },
+    {
+      "epoch": 7.085301472631286,
+      "grad_norm": 1.208331823348999,
+      "learning_rate": 0.0003278688524590164,
+      "loss": 0.2027,
+      "step": 25500
+    },
+    {
+      "epoch": 7.20200055570992,
+      "eval_loss": 0.2782404124736786,
+      "eval_runtime": 4.0927,
+      "eval_samples_per_second": 122.168,
+      "eval_steps_per_second": 7.819,
+      "step": 25920
+    },
+    {
+      "epoch": 7.2242289524868015,
+      "grad_norm": 0.8780717849731445,
+      "learning_rate": 0.0003186070204686487,
+      "loss": 0.1964,
+      "step": 26000
+    },
+    {
+      "epoch": 7.3631564323423175,
+      "grad_norm": 0.7576518058776855,
+      "learning_rate": 0.00030934518847828104,
+      "loss": 0.1995,
+      "step": 26500
+    },
+    {
+      "epoch": 7.402056126701861,
+      "eval_loss": 0.28228145837783813,
+      "eval_runtime": 3.8237,
+      "eval_samples_per_second": 130.762,
+      "eval_steps_per_second": 8.369,
+      "step": 26640
+    },
+    {
+      "epoch": 7.502083912197833,
+      "grad_norm": 0.7847643494606018,
+      "learning_rate": 0.0003000833564879133,
+      "loss": 0.199,
+      "step": 27000
+    },
+    {
+      "epoch": 7.602111697693804,
+      "eval_loss": 0.2756829261779785,
+      "eval_runtime": 3.8249,
+      "eval_samples_per_second": 130.723,
+      "eval_steps_per_second": 8.366,
+      "step": 27360
+    },
+    {
+      "epoch": 7.641011392053348,
+      "grad_norm": 1.0473297834396362,
+      "learning_rate": 0.00029082152449754563,
+      "loss": 0.1997,
+      "step": 27500
+    },
+    {
+      "epoch": 7.779938871908864,
+      "grad_norm": 1.0194053649902344,
+      "learning_rate": 0.000281559692507178,
+      "loss": 0.199,
+      "step": 28000
+    },
+    {
+      "epoch": 7.802167268685746,
+      "eval_loss": 0.27072572708129883,
+      "eval_runtime": 3.8542,
+      "eval_samples_per_second": 129.728,
+      "eval_steps_per_second": 8.303,
+      "step": 28080
+    },
+    {
+      "epoch": 7.918866351764379,
+      "grad_norm": 1.0758508443832397,
+      "learning_rate": 0.0002722978605168102,
+      "loss": 0.2037,
+      "step": 28500
+    },
+    {
+      "epoch": 8.002222839677689,
+      "eval_loss": 0.2647857666015625,
+      "eval_runtime": 3.9624,
+      "eval_samples_per_second": 126.187,
+      "eval_steps_per_second": 8.076,
+      "step": 28800
+    },
+    {
+      "epoch": 8.057793831619895,
+      "grad_norm": 1.5225253105163574,
+      "learning_rate": 0.000263073075854404,
+      "loss": 0.1894,
+      "step": 29000
+    },
+    {
+      "epoch": 8.19672131147541,
+      "grad_norm": 1.2376328706741333,
+      "learning_rate": 0.00025381124386403633,
+      "loss": 0.1802,
+      "step": 29500
+    },
+    {
+      "epoch": 8.20227841066963,
+      "eval_loss": 0.2687641680240631,
+      "eval_runtime": 3.8687,
+      "eval_samples_per_second": 129.244,
+      "eval_steps_per_second": 8.272,
+      "step": 29520
+    },
+    {
+      "epoch": 8.335648791330925,
+      "grad_norm": 0.9780922532081604,
+      "learning_rate": 0.0002445494118736686,
+      "loss": 0.1772,
+      "step": 30000
+    },
+    {
+      "epoch": 8.402333981661572,
+      "eval_loss": 0.26946747303009033,
+      "eval_runtime": 3.847,
+      "eval_samples_per_second": 129.971,
+      "eval_steps_per_second": 8.318,
+      "step": 30240
+    },
+    {
+      "epoch": 8.474576271186441,
+      "grad_norm": 0.9798265099525452,
+      "learning_rate": 0.00023528757988330092,
+      "loss": 0.1809,
+      "step": 30500
+    },
+    {
+      "epoch": 8.602389552653515,
+      "eval_loss": 0.2680206894874573,
+      "eval_runtime": 3.8328,
+      "eval_samples_per_second": 130.451,
+      "eval_steps_per_second": 8.349,
+      "step": 30960
+    },
+    {
+      "epoch": 8.613503751041955,
+      "grad_norm": 1.158241868019104,
+      "learning_rate": 0.00022602574789293324,
+      "loss": 0.181,
+      "step": 31000
+    },
+    {
+      "epoch": 8.752431230897471,
+      "grad_norm": 1.3428902626037598,
+      "learning_rate": 0.00021676391590256554,
+      "loss": 0.1783,
+      "step": 31500
+    },
+    {
+      "epoch": 8.802445123645457,
+      "eval_loss": 0.26235222816467285,
+      "eval_runtime": 3.7848,
+      "eval_samples_per_second": 132.107,
+      "eval_steps_per_second": 8.455,
+      "step": 31680
+    },
+    {
+      "epoch": 8.891358710752987,
+      "grad_norm": 1.0836312770843506,
+      "learning_rate": 0.00020750208391219786,
+      "loss": 0.181,
+      "step": 32000
+    },
+    {
+      "epoch": 9.0025006946374,
+      "eval_loss": 0.25675147771835327,
+      "eval_runtime": 3.933,
+      "eval_samples_per_second": 127.129,
+      "eval_steps_per_second": 8.136,
+      "step": 32400
+    },
+    {
+      "epoch": 9.030286190608502,
+      "grad_norm": 0.9676462411880493,
+      "learning_rate": 0.00019825877558581086,
+      "loss": 0.1741,
+      "step": 32500
+    },
+    {
+      "epoch": 9.169213670464018,
+      "grad_norm": 0.8916613459587097,
+      "learning_rate": 0.0001889969435954432,
+      "loss": 0.1577,
+      "step": 33000
+    },
+    {
+      "epoch": 9.202556265629342,
+      "eval_loss": 0.26385390758514404,
+      "eval_runtime": 3.7947,
+      "eval_samples_per_second": 131.764,
+      "eval_steps_per_second": 8.433,
+      "step": 33120
+    },
+    {
+      "epoch": 9.308141150319534,
+      "grad_norm": 0.7243923544883728,
+      "learning_rate": 0.0001797351116050755,
+      "loss": 0.1577,
+      "step": 33500
+    },
+    {
+      "epoch": 9.402611836621285,
+      "eval_loss": 0.25913867354393005,
+      "eval_runtime": 3.8547,
+      "eval_samples_per_second": 129.712,
+      "eval_steps_per_second": 8.302,
+      "step": 33840
+    },
+    {
+      "epoch": 9.447068630175048,
+      "grad_norm": 0.9483500123023987,
+      "learning_rate": 0.0001704732796147078,
+      "loss": 0.1591,
+      "step": 34000
+    },
+    {
+      "epoch": 9.585996110030564,
+      "grad_norm": 0.7762231826782227,
+      "learning_rate": 0.0001612114476243401,
+      "loss": 0.1616,
+      "step": 34500
+    },
+    {
+      "epoch": 9.602667407613225,
+      "eval_loss": 0.2610129714012146,
+      "eval_runtime": 3.8149,
+      "eval_samples_per_second": 131.065,
+      "eval_steps_per_second": 8.388,
+      "step": 34560
+    },
+    {
+      "epoch": 9.72492358988608,
+      "grad_norm": 0.7880794405937195,
+      "learning_rate": 0.00015194961563397242,
+      "loss": 0.1602,
+      "step": 35000
+    },
+    {
+      "epoch": 9.802722978605168,
+      "eval_loss": 0.2549179196357727,
+      "eval_runtime": 3.8234,
+      "eval_samples_per_second": 130.775,
+      "eval_steps_per_second": 8.37,
+      "step": 35280
+    },
+    {
+      "epoch": 9.863851069741594,
+      "grad_norm": 1.144584059715271,
+      "learning_rate": 0.00014268778364360472,
+      "loss": 0.1616,
+      "step": 35500
+    },
+    {
+      "epoch": 10.00277854959711,
+      "grad_norm": 0.5802558064460754,
+      "learning_rate": 0.000133425951653237,
+      "loss": 0.158,
+      "step": 36000
+    },
+    {
+      "epoch": 10.00277854959711,
+      "eval_loss": 0.25472626090049744,
+      "eval_runtime": 3.8668,
+      "eval_samples_per_second": 129.307,
+      "eval_steps_per_second": 8.276,
+      "step": 36000
+    },
+    {
+      "epoch": 10.141706029452626,
+      "grad_norm": 0.8255568146705627,
+      "learning_rate": 0.0001241641196628693,
+      "loss": 0.1399,
+      "step": 36500
+    },
+    {
+      "epoch": 10.202834120589053,
+      "eval_loss": 0.26079797744750977,
+      "eval_runtime": 3.8601,
+      "eval_samples_per_second": 129.53,
+      "eval_steps_per_second": 8.29,
+      "step": 36720
+    },
+    {
+      "epoch": 10.28063350930814,
+      "grad_norm": 1.0500853061676025,
+      "learning_rate": 0.00011492081133648236,
+      "loss": 0.1394,
+      "step": 37000
+    },
+    {
+      "epoch": 10.402889691580995,
+      "eval_loss": 0.26099085807800293,
+      "eval_runtime": 4.0256,
+      "eval_samples_per_second": 124.205,
+      "eval_steps_per_second": 7.949,
+      "step": 37440
+    },
+    {
+      "epoch": 10.419560989163656,
+      "grad_norm": 0.7501422166824341,
+      "learning_rate": 0.00010565897934611466,
+      "loss": 0.1415,
+      "step": 37500
+    },
+    {
+      "epoch": 10.558488469019172,
+      "grad_norm": 1.162443995475769,
+      "learning_rate": 9.639714735574698e-05,
+      "loss": 0.1405,
+      "step": 38000
+    },
+    {
+      "epoch": 10.602945262572938,
+      "eval_loss": 0.25570982694625854,
+      "eval_runtime": 3.7987,
+      "eval_samples_per_second": 131.625,
+      "eval_steps_per_second": 8.424,
+      "step": 38160
+    },
+    {
+      "epoch": 10.697415948874687,
+      "grad_norm": 0.9860718846321106,
+      "learning_rate": 8.713531536537928e-05,
+      "loss": 0.1404,
+      "step": 38500
+    },
+    {
+      "epoch": 10.803000833564878,
+      "eval_loss": 0.2561904788017273,
+      "eval_runtime": 3.7731,
+      "eval_samples_per_second": 132.516,
+      "eval_steps_per_second": 8.481,
+      "step": 38880
+    },
+    {
+      "epoch": 10.836343428730203,
+      "grad_norm": 0.8580673933029175,
+      "learning_rate": 7.787348337501159e-05,
+      "loss": 0.1415,
+      "step": 39000
+    },
+    {
+      "epoch": 10.975270908585719,
+      "grad_norm": 1.089052438735962,
+      "learning_rate": 6.864869871260535e-05,
+      "loss": 0.1415,
+      "step": 39500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 43188,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0381972027463434e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-39589/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4669a05861aa2cabf994a5ebd88703de5bbf517c7397322a1d3bcb4cfa01bfa7
+size 5496