Training in progress, epoch 12, checkpoint

checkpoint-43188/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-43188/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-43188/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7326693750fa50975c81b369aca581be2348482cc9560006afada23d0ec7fc33
+size 268636736

checkpoint-43188/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ef8e905b27c0e66466d5abf8bc421ca5154efb8eec5a7ecc704a5793275278
+size 12663802

checkpoint-43188/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e878ce523e35215671d3578f42551376a38f77805ac5c4da6148e81f5212d465
+size 15984

checkpoint-43188/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b31b978dc291cb7f6bb815bfb2ad324464846b4598173b9dbd43276cb4aacca9
+size 15984

checkpoint-43188/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816b515a23e20d18317f517c214108c0e7eb1a61e470ba588eb73e82a165a836
+size 15984

checkpoint-43188/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae6f0d83d269c4f32ccec3233687cbd9350dfd7bb81fc2c43f46686ebcad09c
+size 15984

checkpoint-43188/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc0b343bca351c1bc9ded25723319d5758ec9e2029588029368a22b915b4ea7
+size 15984

checkpoint-43188/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165eb22b0c96e766de650176f82e201fbf2c943c3f2e1dd4039abcbbfa859bad
+size 15984

checkpoint-43188/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b7b0d54c6cb2f80287af0d058fc21e8a031173a2418ab4c03b3a3085ab4794
+size 15984

checkpoint-43188/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f38f90c6ccba14bd8b1f786d2fa7cb9fd128a491d6746daf5a204e9f7d2f05d
+size 15984

checkpoint-43188/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3001dbfb164af8d6bfeeefcdea1e5231197b1fe2bef6aad08ca061fe7aee33dd
+size 1064

checkpoint-43188/trainer_state.json

@@ -0,0 +1,1107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "eval_steps": 720,
+  "global_step": 43188,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13892747985551543,
+      "grad_norm": 0.889398455619812,
+      "learning_rate": 0.0007907752153375939,
+      "loss": 0.3895,
+      "step": 500
+    },
+    {
+      "epoch": 0.2000555709919422,
+      "eval_loss": 0.2990996241569519,
+      "eval_runtime": 6.0564,
+      "eval_samples_per_second": 82.558,
+      "eval_steps_per_second": 5.284,
+      "step": 720
+    },
+    {
+      "epoch": 0.27785495971103086,
+      "grad_norm": 0.5278475880622864,
+      "learning_rate": 0.0007815133833472261,
+      "loss": 0.2897,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4001111419838844,
+      "eval_loss": 0.2636842131614685,
+      "eval_runtime": 6.0156,
+      "eval_samples_per_second": 83.118,
+      "eval_steps_per_second": 5.32,
+      "step": 1440
+    },
+    {
+      "epoch": 0.41678243956654626,
+      "grad_norm": 1.208860158920288,
+      "learning_rate": 0.0007722515513568584,
+      "loss": 0.2681,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5557099194220617,
+      "grad_norm": 0.7001394629478455,
+      "learning_rate": 0.0007629897193664907,
+      "loss": 0.2536,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6001667129758266,
+      "eval_loss": 0.25593382120132446,
+      "eval_runtime": 6.0644,
+      "eval_samples_per_second": 82.449,
+      "eval_steps_per_second": 5.277,
+      "step": 2160
+    },
+    {
+      "epoch": 0.6946373992775771,
+      "grad_norm": 0.7066700458526611,
+      "learning_rate": 0.000753727887376123,
+      "loss": 0.2453,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8002222839677688,
+      "eval_loss": 0.24263954162597656,
+      "eval_runtime": 6.2582,
+      "eval_samples_per_second": 79.896,
+      "eval_steps_per_second": 5.113,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8335648791330925,
+      "grad_norm": 0.8669331073760986,
+      "learning_rate": 0.000744484579049736,
+      "loss": 0.2378,
+      "step": 3000
+    },
+    {
+      "epoch": 0.972492358988608,
+      "grad_norm": 0.752050518989563,
+      "learning_rate": 0.0007352412707233491,
+      "loss": 0.2335,
+      "step": 3500
+    },
+    {
+      "epoch": 1.000277854959711,
+      "eval_loss": 0.24230095744132996,
+      "eval_runtime": 6.2445,
+      "eval_samples_per_second": 80.07,
+      "eval_steps_per_second": 5.124,
+      "step": 3600
+    },
+    {
+      "epoch": 1.1114198388441234,
+      "grad_norm": 0.5285800695419312,
+      "learning_rate": 0.0007259794387329814,
+      "loss": 0.2214,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2003334259516532,
+      "eval_loss": 0.23442834615707397,
+      "eval_runtime": 6.0486,
+      "eval_samples_per_second": 82.664,
+      "eval_steps_per_second": 5.291,
+      "step": 4320
+    },
+    {
+      "epoch": 1.2503473186996388,
+      "grad_norm": 0.7171725630760193,
+      "learning_rate": 0.0007167176067426138,
+      "loss": 0.2204,
+      "step": 4500
+    },
+    {
+      "epoch": 1.3892747985551543,
+      "grad_norm": 0.6683080792427063,
+      "learning_rate": 0.000707455774752246,
+      "loss": 0.217,
+      "step": 5000
+    },
+    {
+      "epoch": 1.4003889969435954,
+      "eval_loss": 0.2214350551366806,
+      "eval_runtime": 6.0608,
+      "eval_samples_per_second": 82.498,
+      "eval_steps_per_second": 5.28,
+      "step": 5040
+    },
+    {
+      "epoch": 1.5282022784106695,
+      "grad_norm": 0.8774034380912781,
+      "learning_rate": 0.0006981939427618783,
+      "loss": 0.2154,
+      "step": 5500
+    },
+    {
+      "epoch": 1.6004445679355377,
+      "eval_loss": 0.2222467064857483,
+      "eval_runtime": 6.2569,
+      "eval_samples_per_second": 79.912,
+      "eval_steps_per_second": 5.114,
+      "step": 5760
+    },
+    {
+      "epoch": 1.667129758266185,
+      "grad_norm": 0.6040942668914795,
+      "learning_rate": 0.0006889506344354914,
+      "loss": 0.2133,
+      "step": 6000
+    },
+    {
+      "epoch": 1.8005001389274797,
+      "eval_loss": 0.2248920053243637,
+      "eval_runtime": 6.2381,
+      "eval_samples_per_second": 80.153,
+      "eval_steps_per_second": 5.13,
+      "step": 6480
+    },
+    {
+      "epoch": 1.8060572381217006,
+      "grad_norm": 0.8217343688011169,
+      "learning_rate": 0.0006796888024451237,
+      "loss": 0.2108,
+      "step": 6500
+    },
+    {
+      "epoch": 1.9449847179772157,
+      "grad_norm": 0.6363208889961243,
+      "learning_rate": 0.0006704269704547561,
+      "loss": 0.2095,
+      "step": 7000
+    },
+    {
+      "epoch": 2.000555709919422,
+      "eval_loss": 0.2111140936613083,
+      "eval_runtime": 6.4306,
+      "eval_samples_per_second": 77.753,
+      "eval_steps_per_second": 4.976,
+      "step": 7200
+    },
+    {
+      "epoch": 2.0839121978327313,
+      "grad_norm": 0.5115044116973877,
+      "learning_rate": 0.0006611651384643883,
+      "loss": 0.1984,
+      "step": 7500
+    },
+    {
+      "epoch": 2.2006112809113643,
+      "eval_loss": 0.21921053528785706,
+      "eval_runtime": 6.2111,
+      "eval_samples_per_second": 80.501,
+      "eval_steps_per_second": 5.152,
+      "step": 7920
+    },
+    {
+      "epoch": 2.222839677688247,
+      "grad_norm": 0.7524166703224182,
+      "learning_rate": 0.0006519218301380013,
+      "loss": 0.1981,
+      "step": 8000
+    },
+    {
+      "epoch": 2.361767157543762,
+      "grad_norm": 0.7301591038703918,
+      "learning_rate": 0.0006426599981476336,
+      "loss": 0.1973,
+      "step": 8500
+    },
+    {
+      "epoch": 2.4006668519033063,
+      "eval_loss": 0.2109183967113495,
+      "eval_runtime": 6.2385,
+      "eval_samples_per_second": 80.147,
+      "eval_steps_per_second": 5.129,
+      "step": 8640
+    },
+    {
+      "epoch": 2.5006946373992776,
+      "grad_norm": 0.6623874306678772,
+      "learning_rate": 0.000633398166157266,
+      "loss": 0.1938,
+      "step": 9000
+    },
+    {
+      "epoch": 2.600722422895249,
+      "eval_loss": 0.19926229119300842,
+      "eval_runtime": 6.2567,
+      "eval_samples_per_second": 79.914,
+      "eval_steps_per_second": 5.115,
+      "step": 9360
+    },
+    {
+      "epoch": 2.639622117254793,
+      "grad_norm": 0.5896228551864624,
+      "learning_rate": 0.0006241363341668982,
+      "loss": 0.1917,
+      "step": 9500
+    },
+    {
+      "epoch": 2.7785495971103087,
+      "grad_norm": 0.5303069353103638,
+      "learning_rate": 0.0006148745021765306,
+      "loss": 0.1941,
+      "step": 10000
+    },
+    {
+      "epoch": 2.800777993887191,
+      "eval_loss": 0.20040422677993774,
+      "eval_runtime": 6.445,
+      "eval_samples_per_second": 77.58,
+      "eval_steps_per_second": 4.965,
+      "step": 10080
+    },
+    {
+      "epoch": 2.917477076965824,
+      "grad_norm": 0.5772528052330017,
+      "learning_rate": 0.0006056126701861628,
+      "loss": 0.1962,
+      "step": 10500
+    },
+    {
+      "epoch": 3.000833564879133,
+      "eval_loss": 0.19769687950611115,
+      "eval_runtime": 6.251,
+      "eval_samples_per_second": 79.987,
+      "eval_steps_per_second": 5.119,
+      "step": 10800
+    },
+    {
+      "epoch": 3.0564045568213394,
+      "grad_norm": 0.8229184746742249,
+      "learning_rate": 0.0005963508381957952,
+      "loss": 0.1868,
+      "step": 11000
+    },
+    {
+      "epoch": 3.1953320366768545,
+      "grad_norm": 0.6219042539596558,
+      "learning_rate": 0.0005871075298694081,
+      "loss": 0.1813,
+      "step": 11500
+    },
+    {
+      "epoch": 3.2008891358710754,
+      "eval_loss": 0.20137149095535278,
+      "eval_runtime": 6.1829,
+      "eval_samples_per_second": 80.868,
+      "eval_steps_per_second": 5.176,
+      "step": 11520
+    },
+    {
+      "epoch": 3.33425951653237,
+      "grad_norm": 0.6010075807571411,
+      "learning_rate": 0.0005778456978790405,
+      "loss": 0.1822,
+      "step": 12000
+    },
+    {
+      "epoch": 3.4009447068630174,
+      "eval_loss": 0.20252275466918945,
+      "eval_runtime": 6.2359,
+      "eval_samples_per_second": 80.181,
+      "eval_steps_per_second": 5.132,
+      "step": 12240
+    },
+    {
+      "epoch": 3.4731869963878856,
+      "grad_norm": 0.6477861404418945,
+      "learning_rate": 0.0005685838658886728,
+      "loss": 0.1814,
+      "step": 12500
+    },
+    {
+      "epoch": 3.6010002778549595,
+      "eval_loss": 0.19002339243888855,
+      "eval_runtime": 6.0426,
+      "eval_samples_per_second": 82.745,
+      "eval_steps_per_second": 5.296,
+      "step": 12960
+    },
+    {
+      "epoch": 3.612114476243401,
+      "grad_norm": 0.6676946878433228,
+      "learning_rate": 0.0005593220338983052,
+      "loss": 0.1808,
+      "step": 13000
+    },
+    {
+      "epoch": 3.7510419560989163,
+      "grad_norm": 1.1407862901687622,
+      "learning_rate": 0.0005500602019079374,
+      "loss": 0.1788,
+      "step": 13500
+    },
+    {
+      "epoch": 3.801055848846902,
+      "eval_loss": 0.18976138532161713,
+      "eval_runtime": 6.3955,
+      "eval_samples_per_second": 78.18,
+      "eval_steps_per_second": 5.004,
+      "step": 13680
+    },
+    {
+      "epoch": 3.889969435954432,
+      "grad_norm": 0.818808913230896,
+      "learning_rate": 0.0005407983699175697,
+      "loss": 0.1795,
+      "step": 14000
+    },
+    {
+      "epoch": 4.001111419838844,
+      "eval_loss": 0.18558593094348907,
+      "eval_runtime": 6.8949,
+      "eval_samples_per_second": 72.517,
+      "eval_steps_per_second": 4.641,
+      "step": 14400
+    },
+    {
+      "epoch": 4.0288969158099475,
+      "grad_norm": 0.5338103771209717,
+      "learning_rate": 0.000531536537927202,
+      "loss": 0.1732,
+      "step": 14500
+    },
+    {
+      "epoch": 4.167824395665463,
+      "grad_norm": 0.6316047310829163,
+      "learning_rate": 0.0005222747059368344,
+      "loss": 0.1678,
+      "step": 15000
+    },
+    {
+      "epoch": 4.201166990830786,
+      "eval_loss": 0.19053161144256592,
+      "eval_runtime": 6.4789,
+      "eval_samples_per_second": 77.173,
+      "eval_steps_per_second": 4.939,
+      "step": 15120
+    },
+    {
+      "epoch": 4.306751875520978,
+      "grad_norm": 0.9015474319458008,
+      "learning_rate": 0.0005130313976104474,
+      "loss": 0.1693,
+      "step": 15500
+    },
+    {
+      "epoch": 4.4012225618227285,
+      "eval_loss": 0.19033345580101013,
+      "eval_runtime": 6.2453,
+      "eval_samples_per_second": 80.061,
+      "eval_steps_per_second": 5.124,
+      "step": 15840
+    },
+    {
+      "epoch": 4.445679355376494,
+      "grad_norm": 0.5398434400558472,
+      "learning_rate": 0.0005037695656200797,
+      "loss": 0.1705,
+      "step": 16000
+    },
+    {
+      "epoch": 4.584606835232009,
+      "grad_norm": 0.6211907863616943,
+      "learning_rate": 0.0004945077336297119,
+      "loss": 0.1675,
+      "step": 16500
+    },
+    {
+      "epoch": 4.601278132814671,
+      "eval_loss": 0.1857684701681137,
+      "eval_runtime": 6.2063,
+      "eval_samples_per_second": 80.563,
+      "eval_steps_per_second": 5.156,
+      "step": 16560
+    },
+    {
+      "epoch": 4.723534315087524,
+      "grad_norm": 0.6166074872016907,
+      "learning_rate": 0.0004852459016393443,
+      "loss": 0.1681,
+      "step": 17000
+    },
+    {
+      "epoch": 4.801333703806613,
+      "eval_loss": 0.18442219495773315,
+      "eval_runtime": 6.2555,
+      "eval_samples_per_second": 79.93,
+      "eval_steps_per_second": 5.116,
+      "step": 17280
+    },
+    {
+      "epoch": 4.86246179494304,
+      "grad_norm": 0.5619335174560547,
+      "learning_rate": 0.00047600259331295736,
+      "loss": 0.1687,
+      "step": 17500
+    },
+    {
+      "epoch": 5.001389274798555,
+      "grad_norm": 0.7084242701530457,
+      "learning_rate": 0.0004667407613225896,
+      "loss": 0.1635,
+      "step": 18000
+    },
+    {
+      "epoch": 5.001389274798555,
+      "eval_loss": 0.1823691427707672,
+      "eval_runtime": 6.4719,
+      "eval_samples_per_second": 77.257,
+      "eval_steps_per_second": 4.944,
+      "step": 18000
+    },
+    {
+      "epoch": 5.14031675465407,
+      "grad_norm": 0.6466693878173828,
+      "learning_rate": 0.0004574789293322219,
+      "loss": 0.1537,
+      "step": 18500
+    },
+    {
+      "epoch": 5.201444845790498,
+      "eval_loss": 0.18211981654167175,
+      "eval_runtime": 6.28,
+      "eval_samples_per_second": 79.618,
+      "eval_steps_per_second": 5.096,
+      "step": 18720
+    },
+    {
+      "epoch": 5.279244234509586,
+      "grad_norm": 0.760137677192688,
+      "learning_rate": 0.00044821709734185424,
+      "loss": 0.155,
+      "step": 19000
+    },
+    {
+      "epoch": 5.401500416782439,
+      "eval_loss": 0.17618674039840698,
+      "eval_runtime": 6.2993,
+      "eval_samples_per_second": 79.374,
+      "eval_steps_per_second": 5.08,
+      "step": 19440
+    },
+    {
+      "epoch": 5.418171714365101,
+      "grad_norm": 0.6954505443572998,
+      "learning_rate": 0.00043897378901546733,
+      "loss": 0.155,
+      "step": 19500
+    },
+    {
+      "epoch": 5.5570991942206165,
+      "grad_norm": 0.5655320882797241,
+      "learning_rate": 0.00042971195702509957,
+      "loss": 0.1559,
+      "step": 20000
+    },
+    {
+      "epoch": 5.601555987774382,
+      "eval_loss": 0.18366502225399017,
+      "eval_runtime": 6.3293,
+      "eval_samples_per_second": 78.998,
+      "eval_steps_per_second": 5.056,
+      "step": 20160
+    },
+    {
+      "epoch": 5.6960266740761325,
+      "grad_norm": 0.5522324442863464,
+      "learning_rate": 0.00042045012503473186,
+      "loss": 0.1565,
+      "step": 20500
+    },
+    {
+      "epoch": 5.801611558766324,
+      "eval_loss": 0.1724882870912552,
+      "eval_runtime": 6.3076,
+      "eval_samples_per_second": 79.269,
+      "eval_steps_per_second": 5.073,
+      "step": 20880
+    },
+    {
+      "epoch": 5.834954153931648,
+      "grad_norm": 0.5771639347076416,
+      "learning_rate": 0.0004111882930443642,
+      "loss": 0.1548,
+      "step": 21000
+    },
+    {
+      "epoch": 5.973881633787163,
+      "grad_norm": 0.7794287204742432,
+      "learning_rate": 0.0004019264610539965,
+      "loss": 0.151,
+      "step": 21500
+    },
+    {
+      "epoch": 6.001667129758266,
+      "eval_loss": 0.17095144093036652,
+      "eval_runtime": 6.2425,
+      "eval_samples_per_second": 80.096,
+      "eval_steps_per_second": 5.126,
+      "step": 21600
+    },
+    {
+      "epoch": 6.112809113642679,
+      "grad_norm": 0.755778968334198,
+      "learning_rate": 0.0003926646290636288,
+      "loss": 0.1444,
+      "step": 22000
+    },
+    {
+      "epoch": 6.201722700750208,
+      "eval_loss": 0.1705874651670456,
+      "eval_runtime": 6.3293,
+      "eval_samples_per_second": 78.998,
+      "eval_steps_per_second": 5.056,
+      "step": 22320
+    },
+    {
+      "epoch": 6.251736593498194,
+      "grad_norm": 0.5752654671669006,
+      "learning_rate": 0.0003834027970732611,
+      "loss": 0.1423,
+      "step": 22500
+    },
+    {
+      "epoch": 6.390664073353709,
+      "grad_norm": 0.5828496217727661,
+      "learning_rate": 0.0003741409650828934,
+      "loss": 0.1447,
+      "step": 23000
+    },
+    {
+      "epoch": 6.401778271742151,
+      "eval_loss": 0.1719101518392563,
+      "eval_runtime": 6.3021,
+      "eval_samples_per_second": 79.339,
+      "eval_steps_per_second": 5.078,
+      "step": 23040
+    },
+    {
+      "epoch": 6.529591553209225,
+      "grad_norm": 0.5708982944488525,
+      "learning_rate": 0.0003648976567565065,
+      "loss": 0.1429,
+      "step": 23500
+    },
+    {
+      "epoch": 6.601833842734093,
+      "eval_loss": 0.17164455354213715,
+      "eval_runtime": 6.3252,
+      "eval_samples_per_second": 79.048,
+      "eval_steps_per_second": 5.059,
+      "step": 23760
+    },
+    {
+      "epoch": 6.66851903306474,
+      "grad_norm": 0.6801475286483765,
+      "learning_rate": 0.0003556358247661388,
+      "loss": 0.1428,
+      "step": 24000
+    },
+    {
+      "epoch": 6.801889413726035,
+      "eval_loss": 0.16734325885772705,
+      "eval_runtime": 6.4095,
+      "eval_samples_per_second": 78.01,
+      "eval_steps_per_second": 4.993,
+      "step": 24480
+    },
+    {
+      "epoch": 6.807446512920255,
+      "grad_norm": 0.5865324139595032,
+      "learning_rate": 0.00034637399277577107,
+      "loss": 0.1424,
+      "step": 24500
+    },
+    {
+      "epoch": 6.946373992775771,
+      "grad_norm": 0.7098519206047058,
+      "learning_rate": 0.00033711216078540336,
+      "loss": 0.1407,
+      "step": 25000
+    },
+    {
+      "epoch": 7.001944984717977,
+      "eval_loss": 0.16686856746673584,
+      "eval_runtime": 6.4894,
+      "eval_samples_per_second": 77.049,
+      "eval_steps_per_second": 4.931,
+      "step": 25200
+    },
+    {
+      "epoch": 7.085301472631286,
+      "grad_norm": 0.8402431607246399,
+      "learning_rate": 0.00032785032879503566,
+      "loss": 0.1335,
+      "step": 25500
+    },
+    {
+      "epoch": 7.20200055570992,
+      "eval_loss": 0.16496331989765167,
+      "eval_runtime": 6.166,
+      "eval_samples_per_second": 81.09,
+      "eval_steps_per_second": 5.19,
+      "step": 25920
+    },
+    {
+      "epoch": 7.2242289524868015,
+      "grad_norm": 0.8292597532272339,
+      "learning_rate": 0.0003186070204686487,
+      "loss": 0.1297,
+      "step": 26000
+    },
+    {
+      "epoch": 7.3631564323423175,
+      "grad_norm": 0.8218772411346436,
+      "learning_rate": 0.00030934518847828104,
+      "loss": 0.131,
+      "step": 26500
+    },
+    {
+      "epoch": 7.402056126701861,
+      "eval_loss": 0.1669527292251587,
+      "eval_runtime": 6.3072,
+      "eval_samples_per_second": 79.274,
+      "eval_steps_per_second": 5.074,
+      "step": 26640
+    },
+    {
+      "epoch": 7.502083912197833,
+      "grad_norm": 0.39585080742836,
+      "learning_rate": 0.0003000833564879133,
+      "loss": 0.1314,
+      "step": 27000
+    },
+    {
+      "epoch": 7.602111697693804,
+      "eval_loss": 0.1617124080657959,
+      "eval_runtime": 6.4904,
+      "eval_samples_per_second": 77.037,
+      "eval_steps_per_second": 4.93,
+      "step": 27360
+    },
+    {
+      "epoch": 7.641011392053348,
+      "grad_norm": 0.5454237461090088,
+      "learning_rate": 0.00029082152449754563,
+      "loss": 0.131,
+      "step": 27500
+    },
+    {
+      "epoch": 7.779938871908864,
+      "grad_norm": 0.48045065999031067,
+      "learning_rate": 0.000281559692507178,
+      "loss": 0.1293,
+      "step": 28000
+    },
+    {
+      "epoch": 7.802167268685746,
+      "eval_loss": 0.1614612638950348,
+      "eval_runtime": 6.2421,
+      "eval_samples_per_second": 80.101,
+      "eval_steps_per_second": 5.126,
+      "step": 28080
+    },
+    {
+      "epoch": 7.918866351764379,
+      "grad_norm": 0.4793488681316376,
+      "learning_rate": 0.0002722978605168102,
+      "loss": 0.1309,
+      "step": 28500
+    },
+    {
+      "epoch": 8.002222839677689,
+      "eval_loss": 0.16146394610404968,
+      "eval_runtime": 6.3071,
+      "eval_samples_per_second": 79.276,
+      "eval_steps_per_second": 5.074,
+      "step": 28800
+    },
+    {
+      "epoch": 8.057793831619895,
+      "grad_norm": 0.8855862617492676,
+      "learning_rate": 0.0002630545521904233,
+      "loss": 0.1235,
+      "step": 29000
+    },
+    {
+      "epoch": 8.19672131147541,
+      "grad_norm": 0.6180191040039062,
+      "learning_rate": 0.0002537927202000556,
+      "loss": 0.1192,
+      "step": 29500
+    },
+    {
+      "epoch": 8.20227841066963,
+      "eval_loss": 0.1589631289243698,
+      "eval_runtime": 6.2706,
+      "eval_samples_per_second": 79.738,
+      "eval_steps_per_second": 5.103,
+      "step": 29520
+    },
+    {
+      "epoch": 8.335648791330925,
+      "grad_norm": 0.6425427198410034,
+      "learning_rate": 0.0002445308882096879,
+      "loss": 0.1186,
+      "step": 30000
+    },
+    {
+      "epoch": 8.402333981661572,
+      "eval_loss": 0.1566726714372635,
+      "eval_runtime": 6.2113,
+      "eval_samples_per_second": 80.499,
+      "eval_steps_per_second": 5.152,
+      "step": 30240
+    },
+    {
+      "epoch": 8.474576271186441,
+      "grad_norm": 0.4892035126686096,
+      "learning_rate": 0.0002352690562193202,
+      "loss": 0.1191,
+      "step": 30500
+    },
+    {
+      "epoch": 8.602389552653515,
+      "eval_loss": 0.15965625643730164,
+      "eval_runtime": 6.0862,
+      "eval_samples_per_second": 82.153,
+      "eval_steps_per_second": 5.258,
+      "step": 30960
+    },
+    {
+      "epoch": 8.613503751041955,
+      "grad_norm": 0.5929815173149109,
+      "learning_rate": 0.00022602574789293324,
+      "loss": 0.1192,
+      "step": 31000
+    },
+    {
+      "epoch": 8.752431230897471,
+      "grad_norm": 0.5730671882629395,
+      "learning_rate": 0.00021676391590256554,
+      "loss": 0.1181,
+      "step": 31500
+    },
+    {
+      "epoch": 8.802445123645457,
+      "eval_loss": 0.15325884521007538,
+      "eval_runtime": 6.072,
+      "eval_samples_per_second": 82.346,
+      "eval_steps_per_second": 5.27,
+      "step": 31680
+    },
+    {
+      "epoch": 8.891358710752987,
+      "grad_norm": 1.0519418716430664,
+      "learning_rate": 0.00020750208391219786,
+      "loss": 0.1181,
+      "step": 32000
+    },
+    {
+      "epoch": 9.0025006946374,
+      "eval_loss": 0.15401768684387207,
+      "eval_runtime": 6.0962,
+      "eval_samples_per_second": 82.018,
+      "eval_steps_per_second": 5.249,
+      "step": 32400
+    },
+    {
+      "epoch": 9.030286190608502,
+      "grad_norm": 0.6488417983055115,
+      "learning_rate": 0.00019824025192183016,
+      "loss": 0.1149,
+      "step": 32500
+    },
+    {
+      "epoch": 9.169213670464018,
+      "grad_norm": 0.5944101214408875,
+      "learning_rate": 0.00018897841993146245,
+      "loss": 0.1068,
+      "step": 33000
+    },
+    {
+      "epoch": 9.202556265629342,
+      "eval_loss": 0.15381553769111633,
+      "eval_runtime": 6.0914,
+      "eval_samples_per_second": 82.083,
+      "eval_steps_per_second": 5.253,
+      "step": 33120
+    },
+    {
+      "epoch": 9.308141150319534,
+      "grad_norm": 0.6464097499847412,
+      "learning_rate": 0.0001797351116050755,
+      "loss": 0.1066,
+      "step": 33500
+    },
+    {
+      "epoch": 9.402611836621285,
+      "eval_loss": 0.15165641903877258,
+      "eval_runtime": 6.0601,
+      "eval_samples_per_second": 82.507,
+      "eval_steps_per_second": 5.28,
+      "step": 33840
+    },
+    {
+      "epoch": 9.447068630175048,
+      "grad_norm": 0.9413381814956665,
+      "learning_rate": 0.0001704732796147078,
+      "loss": 0.1059,
+      "step": 34000
+    },
+    {
+      "epoch": 9.585996110030564,
+      "grad_norm": 0.5482912659645081,
+      "learning_rate": 0.0001612114476243401,
+      "loss": 0.1071,
+      "step": 34500
+    },
+    {
+      "epoch": 9.602667407613225,
+      "eval_loss": 0.15349411964416504,
+      "eval_runtime": 6.0992,
+      "eval_samples_per_second": 81.978,
+      "eval_steps_per_second": 5.247,
+      "step": 34560
+    },
+    {
+      "epoch": 9.72492358988608,
+      "grad_norm": 0.665757954120636,
+      "learning_rate": 0.00015194961563397242,
+      "loss": 0.107,
+      "step": 35000
+    },
+    {
+      "epoch": 9.802722978605168,
+      "eval_loss": 0.14838550984859467,
+      "eval_runtime": 6.2136,
+      "eval_samples_per_second": 80.469,
+      "eval_steps_per_second": 5.15,
+      "step": 35280
+    },
+    {
+      "epoch": 9.863851069741594,
+      "grad_norm": 0.6131353378295898,
+      "learning_rate": 0.00014268778364360472,
+      "loss": 0.1073,
+      "step": 35500
+    },
+    {
+      "epoch": 10.00277854959711,
+      "grad_norm": 0.40674689412117004,
+      "learning_rate": 0.00013344447531721775,
+      "loss": 0.1038,
+      "step": 36000
+    },
+    {
+      "epoch": 10.00277854959711,
+      "eval_loss": 0.1515989899635315,
+      "eval_runtime": 6.0633,
+      "eval_samples_per_second": 82.464,
+      "eval_steps_per_second": 5.278,
+      "step": 36000
+    },
+    {
+      "epoch": 10.141706029452626,
+      "grad_norm": 0.4581647515296936,
+      "learning_rate": 0.00012418264332685007,
+      "loss": 0.0952,
+      "step": 36500
+    },
+    {
+      "epoch": 10.202834120589053,
+      "eval_loss": 0.15648646652698517,
+      "eval_runtime": 6.0728,
+      "eval_samples_per_second": 82.334,
+      "eval_steps_per_second": 5.269,
+      "step": 36720
+    },
+    {
+      "epoch": 10.28063350930814,
+      "grad_norm": 0.9204680323600769,
+      "learning_rate": 0.00011492081133648236,
+      "loss": 0.094,
+      "step": 37000
+    },
+    {
+      "epoch": 10.402889691580995,
+      "eval_loss": 0.15329685807228088,
+      "eval_runtime": 6.2649,
+      "eval_samples_per_second": 79.809,
+      "eval_steps_per_second": 5.108,
+      "step": 37440
+    },
+    {
+      "epoch": 10.419560989163656,
+      "grad_norm": 0.5137987732887268,
+      "learning_rate": 0.00010565897934611466,
+      "loss": 0.0959,
+      "step": 37500
+    },
+    {
+      "epoch": 10.558488469019172,
+      "grad_norm": 0.7176544070243835,
+      "learning_rate": 9.639714735574698e-05,
+      "loss": 0.0943,
+      "step": 38000
+    },
+    {
+      "epoch": 10.602945262572938,
+      "eval_loss": 0.15563952922821045,
+      "eval_runtime": 6.2104,
+      "eval_samples_per_second": 80.51,
+      "eval_steps_per_second": 5.153,
+      "step": 38160
+    },
+    {
+      "epoch": 10.697415948874687,
+      "grad_norm": 0.6775652766227722,
+      "learning_rate": 8.713531536537928e-05,
+      "loss": 0.094,
+      "step": 38500
+    },
+    {
+      "epoch": 10.803000833564878,
+      "eval_loss": 0.15036174654960632,
+      "eval_runtime": 6.2313,
+      "eval_samples_per_second": 80.239,
+      "eval_steps_per_second": 5.135,
+      "step": 38880
+    },
+    {
+      "epoch": 10.836343428730203,
+      "grad_norm": 0.5310354232788086,
+      "learning_rate": 7.787348337501159e-05,
+      "loss": 0.0945,
+      "step": 39000
+    },
+    {
+      "epoch": 10.975270908585719,
+      "grad_norm": 0.5723683834075928,
+      "learning_rate": 6.861165138464388e-05,
+      "loss": 0.0942,
+      "step": 39500
+    },
+    {
+      "epoch": 11.00305640455682,
+      "eval_loss": 0.14920881390571594,
+      "eval_runtime": 6.2676,
+      "eval_samples_per_second": 79.775,
+      "eval_steps_per_second": 5.106,
+      "step": 39600
+    },
+    {
+      "epoch": 11.114198388441233,
+      "grad_norm": 0.6720041632652283,
+      "learning_rate": 5.9368343058256923e-05,
+      "loss": 0.0856,
+      "step": 40000
+    },
+    {
+      "epoch": 11.203111975548763,
+      "eval_loss": 0.15602166950702667,
+      "eval_runtime": 6.2936,
+      "eval_samples_per_second": 79.445,
+      "eval_steps_per_second": 5.084,
+      "step": 40320
+    },
+    {
+      "epoch": 11.253125868296749,
+      "grad_norm": 0.3826921582221985,
+      "learning_rate": 5.0106511067889225e-05,
+      "loss": 0.0847,
+      "step": 40500
+    },
+    {
+      "epoch": 11.392053348152265,
+      "grad_norm": 0.4550657272338867,
+      "learning_rate": 4.086320274150227e-05,
+      "loss": 0.085,
+      "step": 41000
+    },
+    {
+      "epoch": 11.403167546540706,
+      "eval_loss": 0.15526427328586578,
+      "eval_runtime": 6.2717,
+      "eval_samples_per_second": 79.723,
+      "eval_steps_per_second": 5.102,
+      "step": 41040
+    },
+    {
+      "epoch": 11.53098082800778,
+      "grad_norm": 0.7291792035102844,
+      "learning_rate": 3.160137075113457e-05,
+      "loss": 0.0832,
+      "step": 41500
+    },
+    {
+      "epoch": 11.603223117532648,
+      "eval_loss": 0.1560254842042923,
+      "eval_runtime": 6.5085,
+      "eval_samples_per_second": 76.822,
+      "eval_steps_per_second": 4.917,
+      "step": 41760
+    },
+    {
+      "epoch": 11.669908307863295,
+      "grad_norm": 0.5531574487686157,
+      "learning_rate": 2.2339538760766883e-05,
+      "loss": 0.0833,
+      "step": 42000
+    },
+    {
+      "epoch": 11.80327868852459,
+      "eval_loss": 0.15436676144599915,
+      "eval_runtime": 6.4048,
+      "eval_samples_per_second": 78.067,
+      "eval_steps_per_second": 4.996,
+      "step": 42480
+    },
+    {
+      "epoch": 11.808835787718811,
+      "grad_norm": 0.44640883803367615,
+      "learning_rate": 1.3077706770399186e-05,
+      "loss": 0.0835,
+      "step": 42500
+    },
+    {
+      "epoch": 11.947763267574325,
+      "grad_norm": 0.6667990684509277,
+      "learning_rate": 3.815874780031491e-06,
+      "loss": 0.0832,
+      "step": 43000
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.556297159058129e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-43188/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139adae8edce22afe6c27bc652b1dce50af99b8929a4bc88f9a065e1541a95e9
+size 5496