Training in progress, epoch 10, checkpoint

checkpoint-35990/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 0.15.2

checkpoint-35990/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-35990/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509680f3fb6c4242241a16db86b7cd46d61034d86bf8a29b88e33e508f877ddd
+size 268636736

checkpoint-35990/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871e3ed14a2fd7924bd91f188e45b9d49220d94cbb68727adf3de69b6e6057c3
+size 12664203

checkpoint-35990/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6177efcdb6b26628d4f6a2d916aed19f0f7f86ceb0440abcb0ffb31483529bf7
+size 16389

checkpoint-35990/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3435bbfea9a5ed1c08cef334b975d27e88d204310270ed761019d63b072e6790
+size 16389

checkpoint-35990/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd9848cac6d9b1fdf1fe3dfbce928f2a1ec6e7fdfb9be08172481c0f22cc044
+size 16389

checkpoint-35990/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7b3a00393e19b299737508ccf2f9b383a982327229968cab186cda5a579f00
+size 16389

checkpoint-35990/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1fcc0b5d95d8fac46f1477bf9dbfc31e41e573eda3b2018e75dbb157605820
+size 16389

checkpoint-35990/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08cc8a98d94f99a10ebba7531aba2a987ed20afc9e963d6a1bff5eaf90cd7c89
+size 16389

checkpoint-35990/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1017bd8a649a04e14b9923dd4d26d9e2b9715113d789c69b38f5352f5ad814d3
+size 16389

checkpoint-35990/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffcf1c2d4ca0542a6005e68bc2c0c23451bc222e3fddd8e243cd4f6a637574f
+size 16389

checkpoint-35990/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497674e8e4967c7e6f042989cd38d721d83fcec91885c64488a0bde4df9080a3
+size 1383

checkpoint-35990/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee15e8bec2cf746396b5a1e5e1e1b830c49015baaab38b29755225c05e3565c
+size 1465

checkpoint-35990/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-35990/tokenizer_config.json

@@ -0,0 +1,202 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32022": {
+      "content": "###end",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-35990/trainer_state.json

@@ -0,0 +1,923 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 720,
+  "global_step": 35990,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13892747985551543,
+      "grad_norm": 0.6735790967941284,
+      "learning_rate": 0.0007907937390015746,
+      "loss": 0.3742,
+      "step": 500
+    },
+    {
+      "epoch": 0.2000555709919422,
+      "eval_loss": 0.2844131588935852,
+      "eval_runtime": 5.091,
+      "eval_samples_per_second": 98.212,
+      "eval_steps_per_second": 6.286,
+      "step": 720
+    },
+    {
+      "epoch": 0.27785495971103086,
+      "grad_norm": 0.6214504241943359,
+      "learning_rate": 0.0007815319070112068,
+      "loss": 0.2859,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4001111419838844,
+      "eval_loss": 0.2708466649055481,
+      "eval_runtime": 4.8349,
+      "eval_samples_per_second": 103.416,
+      "eval_steps_per_second": 6.619,
+      "step": 1440
+    },
+    {
+      "epoch": 0.41678243956654626,
+      "grad_norm": 0.5057302117347717,
+      "learning_rate": 0.0007722700750208392,
+      "loss": 0.2679,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5557099194220617,
+      "grad_norm": 0.623817503452301,
+      "learning_rate": 0.0007630082430304714,
+      "loss": 0.2527,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6001667129758266,
+      "eval_loss": 0.24877774715423584,
+      "eval_runtime": 5.9656,
+      "eval_samples_per_second": 83.813,
+      "eval_steps_per_second": 5.364,
+      "step": 2160
+    },
+    {
+      "epoch": 0.6946373992775771,
+      "grad_norm": 1.3911620378494263,
+      "learning_rate": 0.0007537649347040845,
+      "loss": 0.2441,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8002222839677688,
+      "eval_loss": 0.2391277253627777,
+      "eval_runtime": 5.9872,
+      "eval_samples_per_second": 83.512,
+      "eval_steps_per_second": 5.345,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8335648791330925,
+      "grad_norm": 0.7922923564910889,
+      "learning_rate": 0.0007445216263776975,
+      "loss": 0.235,
+      "step": 3000
+    },
+    {
+      "epoch": 0.972492358988608,
+      "grad_norm": 0.8539218902587891,
+      "learning_rate": 0.0007352597943873298,
+      "loss": 0.2331,
+      "step": 3500
+    },
+    {
+      "epoch": 1.000277854959711,
+      "eval_loss": 0.23887279629707336,
+      "eval_runtime": 5.6004,
+      "eval_samples_per_second": 89.279,
+      "eval_steps_per_second": 5.714,
+      "step": 3600
+    },
+    {
+      "epoch": 1.1114198388441234,
+      "grad_norm": 0.6812190413475037,
+      "learning_rate": 0.0007259979623969622,
+      "loss": 0.2201,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2003334259516532,
+      "eval_loss": 0.2331564724445343,
+      "eval_runtime": 5.2457,
+      "eval_samples_per_second": 95.317,
+      "eval_steps_per_second": 6.1,
+      "step": 4320
+    },
+    {
+      "epoch": 1.2503473186996388,
+      "grad_norm": 0.6926279067993164,
+      "learning_rate": 0.0007167361304065945,
+      "loss": 0.2199,
+      "step": 4500
+    },
+    {
+      "epoch": 1.3892747985551543,
+      "grad_norm": 0.857128918170929,
+      "learning_rate": 0.0007074742984162268,
+      "loss": 0.2157,
+      "step": 5000
+    },
+    {
+      "epoch": 1.4003889969435954,
+      "eval_loss": 0.22209732234477997,
+      "eval_runtime": 4.9003,
+      "eval_samples_per_second": 102.035,
+      "eval_steps_per_second": 6.53,
+      "step": 5040
+    },
+    {
+      "epoch": 1.5282022784106695,
+      "grad_norm": 0.8350584506988525,
+      "learning_rate": 0.000698212466425859,
+      "loss": 0.2122,
+      "step": 5500
+    },
+    {
+      "epoch": 1.6004445679355377,
+      "eval_loss": 0.22165100276470184,
+      "eval_runtime": 4.8879,
+      "eval_samples_per_second": 102.294,
+      "eval_steps_per_second": 6.547,
+      "step": 5760
+    },
+    {
+      "epoch": 1.667129758266185,
+      "grad_norm": 0.6862344145774841,
+      "learning_rate": 0.0006889691580994721,
+      "loss": 0.2158,
+      "step": 6000
+    },
+    {
+      "epoch": 1.8005001389274797,
+      "eval_loss": 0.21265414357185364,
+      "eval_runtime": 5.1036,
+      "eval_samples_per_second": 97.97,
+      "eval_steps_per_second": 6.27,
+      "step": 6480
+    },
+    {
+      "epoch": 1.8060572381217006,
+      "grad_norm": 0.64631587266922,
+      "learning_rate": 0.0006797073261091044,
+      "loss": 0.2069,
+      "step": 6500
+    },
+    {
+      "epoch": 1.9449847179772157,
+      "grad_norm": 0.6139649748802185,
+      "learning_rate": 0.0006704454941187368,
+      "loss": 0.2063,
+      "step": 7000
+    },
+    {
+      "epoch": 2.000555709919422,
+      "eval_loss": 0.2054276168346405,
+      "eval_runtime": 5.6047,
+      "eval_samples_per_second": 89.211,
+      "eval_steps_per_second": 5.71,
+      "step": 7200
+    },
+    {
+      "epoch": 2.0839121978327313,
+      "grad_norm": 0.5134121179580688,
+      "learning_rate": 0.000661183662128369,
+      "loss": 0.1961,
+      "step": 7500
+    },
+    {
+      "epoch": 2.2006112809113643,
+      "eval_loss": 0.20968343317508698,
+      "eval_runtime": 4.9427,
+      "eval_samples_per_second": 101.16,
+      "eval_steps_per_second": 6.474,
+      "step": 7920
+    },
+    {
+      "epoch": 2.222839677688247,
+      "grad_norm": 0.667497456073761,
+      "learning_rate": 0.0006519218301380013,
+      "loss": 0.198,
+      "step": 8000
+    },
+    {
+      "epoch": 2.361767157543762,
+      "grad_norm": 0.7320435643196106,
+      "learning_rate": 0.0006426599981476336,
+      "loss": 0.1942,
+      "step": 8500
+    },
+    {
+      "epoch": 2.4006668519033063,
+      "eval_loss": 0.201798677444458,
+      "eval_runtime": 5.0966,
+      "eval_samples_per_second": 98.105,
+      "eval_steps_per_second": 6.279,
+      "step": 8640
+    },
+    {
+      "epoch": 2.5006946373992776,
+      "grad_norm": 0.5457369685173035,
+      "learning_rate": 0.000633398166157266,
+      "loss": 0.1904,
+      "step": 9000
+    },
+    {
+      "epoch": 2.600722422895249,
+      "eval_loss": 0.19970637559890747,
+      "eval_runtime": 4.9095,
+      "eval_samples_per_second": 101.843,
+      "eval_steps_per_second": 6.518,
+      "step": 9360
+    },
+    {
+      "epoch": 2.639622117254793,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0006241363341668982,
+      "loss": 0.1928,
+      "step": 9500
+    },
+    {
+      "epoch": 2.7785495971103087,
+      "grad_norm": 0.5789324045181274,
+      "learning_rate": 0.0006148930258405113,
+      "loss": 0.1914,
+      "step": 10000
+    },
+    {
+      "epoch": 2.800777993887191,
+      "eval_loss": 0.20011071860790253,
+      "eval_runtime": 4.9182,
+      "eval_samples_per_second": 101.663,
+      "eval_steps_per_second": 6.506,
+      "step": 10080
+    },
+    {
+      "epoch": 2.917477076965824,
+      "grad_norm": 0.5479323863983154,
+      "learning_rate": 0.0006056311938501436,
+      "loss": 0.193,
+      "step": 10500
+    },
+    {
+      "epoch": 3.000833564879133,
+      "eval_loss": 0.19800344109535217,
+      "eval_runtime": 5.4208,
+      "eval_samples_per_second": 92.236,
+      "eval_steps_per_second": 5.903,
+      "step": 10800
+    },
+    {
+      "epoch": 3.0564045568213394,
+      "grad_norm": 0.509381890296936,
+      "learning_rate": 0.0005963693618597759,
+      "loss": 0.1849,
+      "step": 11000
+    },
+    {
+      "epoch": 3.1953320366768545,
+      "grad_norm": 0.5641015768051147,
+      "learning_rate": 0.0005871075298694081,
+      "loss": 0.1803,
+      "step": 11500
+    },
+    {
+      "epoch": 3.2008891358710754,
+      "eval_loss": 0.19798952341079712,
+      "eval_runtime": 6.0408,
+      "eval_samples_per_second": 82.771,
+      "eval_steps_per_second": 5.297,
+      "step": 11520
+    },
+    {
+      "epoch": 3.33425951653237,
+      "grad_norm": 0.5248855352401733,
+      "learning_rate": 0.0005778456978790405,
+      "loss": 0.1785,
+      "step": 12000
+    },
+    {
+      "epoch": 3.4009447068630174,
+      "eval_loss": 0.1982451230287552,
+      "eval_runtime": 6.0297,
+      "eval_samples_per_second": 82.922,
+      "eval_steps_per_second": 5.307,
+      "step": 12240
+    },
+    {
+      "epoch": 3.4731869963878856,
+      "grad_norm": 1.105663537979126,
+      "learning_rate": 0.0005685838658886728,
+      "loss": 0.1758,
+      "step": 12500
+    },
+    {
+      "epoch": 3.6010002778549595,
+      "eval_loss": 0.1906416267156601,
+      "eval_runtime": 5.9927,
+      "eval_samples_per_second": 83.434,
+      "eval_steps_per_second": 5.34,
+      "step": 12960
+    },
+    {
+      "epoch": 3.612114476243401,
+      "grad_norm": 1.019622802734375,
+      "learning_rate": 0.0005593405575622859,
+      "loss": 0.1765,
+      "step": 13000
+    },
+    {
+      "epoch": 3.7510419560989163,
+      "grad_norm": 0.8380174040794373,
+      "learning_rate": 0.0005500787255719182,
+      "loss": 0.1756,
+      "step": 13500
+    },
+    {
+      "epoch": 3.801055848846902,
+      "eval_loss": 0.18713021278381348,
+      "eval_runtime": 4.8131,
+      "eval_samples_per_second": 103.884,
+      "eval_steps_per_second": 6.649,
+      "step": 13680
+    },
+    {
+      "epoch": 3.889969435954432,
+      "grad_norm": 0.858310878276825,
+      "learning_rate": 0.0005408168935815504,
+      "loss": 0.1773,
+      "step": 14000
+    },
+    {
+      "epoch": 4.001111419838844,
+      "eval_loss": 0.18768689036369324,
+      "eval_runtime": 5.2594,
+      "eval_samples_per_second": 95.068,
+      "eval_steps_per_second": 6.084,
+      "step": 14400
+    },
+    {
+      "epoch": 4.0288969158099475,
+      "grad_norm": 0.8781201243400574,
+      "learning_rate": 0.0005315550615911827,
+      "loss": 0.1728,
+      "step": 14500
+    },
+    {
+      "epoch": 4.167824395665463,
+      "grad_norm": 0.6496415734291077,
+      "learning_rate": 0.0005223117532647958,
+      "loss": 0.1631,
+      "step": 15000
+    },
+    {
+      "epoch": 4.201166990830786,
+      "eval_loss": 0.18398858606815338,
+      "eval_runtime": 5.9345,
+      "eval_samples_per_second": 84.253,
+      "eval_steps_per_second": 5.392,
+      "step": 15120
+    },
+    {
+      "epoch": 4.306751875520978,
+      "grad_norm": 0.6593993306159973,
+      "learning_rate": 0.0005130499212744282,
+      "loss": 0.1665,
+      "step": 15500
+    },
+    {
+      "epoch": 4.4012225618227285,
+      "eval_loss": 0.1805465966463089,
+      "eval_runtime": 6.0284,
+      "eval_samples_per_second": 82.941,
+      "eval_steps_per_second": 5.308,
+      "step": 15840
+    },
+    {
+      "epoch": 4.445679355376494,
+      "grad_norm": 0.43227270245552063,
+      "learning_rate": 0.0005037880892840604,
+      "loss": 0.1658,
+      "step": 16000
+    },
+    {
+      "epoch": 4.584606835232009,
+      "grad_norm": 0.6705788969993591,
+      "learning_rate": 0.0004945262572936927,
+      "loss": 0.1625,
+      "step": 16500
+    },
+    {
+      "epoch": 4.601278132814671,
+      "eval_loss": 0.18674401938915253,
+      "eval_runtime": 4.8422,
+      "eval_samples_per_second": 103.259,
+      "eval_steps_per_second": 6.609,
+      "step": 16560
+    },
+    {
+      "epoch": 4.723534315087524,
+      "grad_norm": 0.9308199882507324,
+      "learning_rate": 0.0004852829489673058,
+      "loss": 0.164,
+      "step": 17000
+    },
+    {
+      "epoch": 4.801333703806613,
+      "eval_loss": 0.17677545547485352,
+      "eval_runtime": 4.874,
+      "eval_samples_per_second": 102.584,
+      "eval_steps_per_second": 6.565,
+      "step": 17280
+    },
+    {
+      "epoch": 4.86246179494304,
+      "grad_norm": 0.488813579082489,
+      "learning_rate": 0.0004760211169769381,
+      "loss": 0.1645,
+      "step": 17500
+    },
+    {
+      "epoch": 5.001389274798555,
+      "grad_norm": 0.7509089708328247,
+      "learning_rate": 0.00046675928498657033,
+      "loss": 0.1593,
+      "step": 18000
+    },
+    {
+      "epoch": 5.001389274798555,
+      "eval_loss": 0.1795799285173416,
+      "eval_runtime": 6.143,
+      "eval_samples_per_second": 81.393,
+      "eval_steps_per_second": 5.209,
+      "step": 18000
+    },
+    {
+      "epoch": 5.14031675465407,
+      "grad_norm": 0.8051738739013672,
+      "learning_rate": 0.0004574974529962027,
+      "loss": 0.1508,
+      "step": 18500
+    },
+    {
+      "epoch": 5.201444845790498,
+      "eval_loss": 0.1730128526687622,
+      "eval_runtime": 6.1102,
+      "eval_samples_per_second": 81.831,
+      "eval_steps_per_second": 5.237,
+      "step": 18720
+    },
+    {
+      "epoch": 5.279244234509586,
+      "grad_norm": 0.616165816783905,
+      "learning_rate": 0.000448235621005835,
+      "loss": 0.151,
+      "step": 19000
+    },
+    {
+      "epoch": 5.401500416782439,
+      "eval_loss": 0.1723448783159256,
+      "eval_runtime": 4.9328,
+      "eval_samples_per_second": 101.362,
+      "eval_steps_per_second": 6.487,
+      "step": 19440
+    },
+    {
+      "epoch": 5.418171714365101,
+      "grad_norm": 0.599356472492218,
+      "learning_rate": 0.00043897378901546733,
+      "loss": 0.152,
+      "step": 19500
+    },
+    {
+      "epoch": 5.5570991942206165,
+      "grad_norm": 0.6316538453102112,
+      "learning_rate": 0.0004297304806890803,
+      "loss": 0.1519,
+      "step": 20000
+    },
+    {
+      "epoch": 5.601555987774382,
+      "eval_loss": 0.17218750715255737,
+      "eval_runtime": 4.8261,
+      "eval_samples_per_second": 103.604,
+      "eval_steps_per_second": 6.631,
+      "step": 20160
+    },
+    {
+      "epoch": 5.6960266740761325,
+      "grad_norm": 0.5698005557060242,
+      "learning_rate": 0.0004204686486987126,
+      "loss": 0.1522,
+      "step": 20500
+    },
+    {
+      "epoch": 5.801611558766324,
+      "eval_loss": 0.17050494253635406,
+      "eval_runtime": 6.0393,
+      "eval_samples_per_second": 82.791,
+      "eval_steps_per_second": 5.299,
+      "step": 20880
+    },
+    {
+      "epoch": 5.834954153931648,
+      "grad_norm": 0.9362701773643494,
+      "learning_rate": 0.00041120681670834495,
+      "loss": 0.1497,
+      "step": 21000
+    },
+    {
+      "epoch": 5.973881633787163,
+      "grad_norm": 0.7077497839927673,
+      "learning_rate": 0.00040194498471797724,
+      "loss": 0.1465,
+      "step": 21500
+    },
+    {
+      "epoch": 6.001667129758266,
+      "eval_loss": 0.1704930067062378,
+      "eval_runtime": 6.2406,
+      "eval_samples_per_second": 80.12,
+      "eval_steps_per_second": 5.128,
+      "step": 21600
+    },
+    {
+      "epoch": 6.112809113642679,
+      "grad_norm": 0.6819673180580139,
+      "learning_rate": 0.00039268315272760954,
+      "loss": 0.1391,
+      "step": 22000
+    },
+    {
+      "epoch": 6.201722700750208,
+      "eval_loss": 0.1641210913658142,
+      "eval_runtime": 6.0676,
+      "eval_samples_per_second": 82.405,
+      "eval_steps_per_second": 5.274,
+      "step": 22320
+    },
+    {
+      "epoch": 6.251736593498194,
+      "grad_norm": 0.6154927015304565,
+      "learning_rate": 0.0003834213207372419,
+      "loss": 0.1383,
+      "step": 22500
+    },
+    {
+      "epoch": 6.390664073353709,
+      "grad_norm": 0.5655333399772644,
+      "learning_rate": 0.00037415948874687413,
+      "loss": 0.1392,
+      "step": 23000
+    },
+    {
+      "epoch": 6.401778271742151,
+      "eval_loss": 0.16602876782417297,
+      "eval_runtime": 4.8554,
+      "eval_samples_per_second": 102.978,
+      "eval_steps_per_second": 6.591,
+      "step": 23040
+    },
+    {
+      "epoch": 6.529591553209225,
+      "grad_norm": 0.6170830726623535,
+      "learning_rate": 0.0003648976567565065,
+      "loss": 0.1374,
+      "step": 23500
+    },
+    {
+      "epoch": 6.601833842734093,
+      "eval_loss": 0.16095949709415436,
+      "eval_runtime": 4.8435,
+      "eval_samples_per_second": 103.232,
+      "eval_steps_per_second": 6.607,
+      "step": 23760
+    },
+    {
+      "epoch": 6.66851903306474,
+      "grad_norm": 0.7002782821655273,
+      "learning_rate": 0.0003556543484301195,
+      "loss": 0.1369,
+      "step": 24000
+    },
+    {
+      "epoch": 6.801889413726035,
+      "eval_loss": 0.1629977971315384,
+      "eval_runtime": 6.0015,
+      "eval_samples_per_second": 83.313,
+      "eval_steps_per_second": 5.332,
+      "step": 24480
+    },
+    {
+      "epoch": 6.807446512920255,
+      "grad_norm": 0.6815934777259827,
+      "learning_rate": 0.0003463925164397518,
+      "loss": 0.1372,
+      "step": 24500
+    },
+    {
+      "epoch": 6.946373992775771,
+      "grad_norm": 0.6028130650520325,
+      "learning_rate": 0.0003371306844493841,
+      "loss": 0.1358,
+      "step": 25000
+    },
+    {
+      "epoch": 7.001944984717977,
+      "eval_loss": 0.15650975704193115,
+      "eval_runtime": 6.1328,
+      "eval_samples_per_second": 81.529,
+      "eval_steps_per_second": 5.218,
+      "step": 25200
+    },
+    {
+      "epoch": 7.085301472631286,
+      "grad_norm": 0.8667997717857361,
+      "learning_rate": 0.0003278873761229972,
+      "loss": 0.1258,
+      "step": 25500
+    },
+    {
+      "epoch": 7.20200055570992,
+      "eval_loss": 0.16240185499191284,
+      "eval_runtime": 6.0855,
+      "eval_samples_per_second": 82.162,
+      "eval_steps_per_second": 5.258,
+      "step": 25920
+    },
+    {
+      "epoch": 7.2242289524868015,
+      "grad_norm": 0.7652863264083862,
+      "learning_rate": 0.0003186255441326294,
+      "loss": 0.1247,
+      "step": 26000
+    },
+    {
+      "epoch": 7.3631564323423175,
+      "grad_norm": 1.3608860969543457,
+      "learning_rate": 0.00030936371214226177,
+      "loss": 0.1259,
+      "step": 26500
+    },
+    {
+      "epoch": 7.402056126701861,
+      "eval_loss": 0.1604655385017395,
+      "eval_runtime": 6.0515,
+      "eval_samples_per_second": 82.624,
+      "eval_steps_per_second": 5.288,
+      "step": 26640
+    },
+    {
+      "epoch": 7.502083912197833,
+      "grad_norm": 0.48411527276039124,
+      "learning_rate": 0.00030010188015189407,
+      "loss": 0.1268,
+      "step": 27000
+    },
+    {
+      "epoch": 7.602111697693804,
+      "eval_loss": 0.15553823113441467,
+      "eval_runtime": 4.8782,
+      "eval_samples_per_second": 102.497,
+      "eval_steps_per_second": 6.56,
+      "step": 27360
+    },
+    {
+      "epoch": 7.641011392053348,
+      "grad_norm": 0.6623326539993286,
+      "learning_rate": 0.0002908585718255071,
+      "loss": 0.1247,
+      "step": 27500
+    },
+    {
+      "epoch": 7.779938871908864,
+      "grad_norm": 0.5693512558937073,
+      "learning_rate": 0.0002815967398351394,
+      "loss": 0.1231,
+      "step": 28000
+    },
+    {
+      "epoch": 7.802167268685746,
+      "eval_loss": 0.15078049898147583,
+      "eval_runtime": 5.5749,
+      "eval_samples_per_second": 89.687,
+      "eval_steps_per_second": 5.74,
+      "step": 28080
+    },
+    {
+      "epoch": 7.918866351764379,
+      "grad_norm": 0.5414377450942993,
+      "learning_rate": 0.0002723349078447717,
+      "loss": 0.1244,
+      "step": 28500
+    },
+    {
+      "epoch": 8.002222839677689,
+      "eval_loss": 0.1523188203573227,
+      "eval_runtime": 6.1165,
+      "eval_samples_per_second": 81.746,
+      "eval_steps_per_second": 5.232,
+      "step": 28800
+    },
+    {
+      "epoch": 8.057793831619895,
+      "grad_norm": 0.7959994077682495,
+      "learning_rate": 0.000263073075854404,
+      "loss": 0.1177,
+      "step": 29000
+    },
+    {
+      "epoch": 8.19672131147541,
+      "grad_norm": 0.7818427085876465,
+      "learning_rate": 0.00025381124386403633,
+      "loss": 0.1125,
+      "step": 29500
+    },
+    {
+      "epoch": 8.20227841066963,
+      "eval_loss": 0.1530105322599411,
+      "eval_runtime": 5.9895,
+      "eval_samples_per_second": 83.479,
+      "eval_steps_per_second": 5.343,
+      "step": 29520
+    },
+    {
+      "epoch": 8.335648791330925,
+      "grad_norm": 0.6304500699043274,
+      "learning_rate": 0.00024456793553764936,
+      "loss": 0.1107,
+      "step": 30000
+    },
+    {
+      "epoch": 8.402333981661572,
+      "eval_loss": 0.15071706473827362,
+      "eval_runtime": 6.0586,
+      "eval_samples_per_second": 82.528,
+      "eval_steps_per_second": 5.282,
+      "step": 30240
+    },
+    {
+      "epoch": 8.474576271186441,
+      "grad_norm": 0.5695451498031616,
+      "learning_rate": 0.00023530610354728166,
+      "loss": 0.1125,
+      "step": 30500
+    },
+    {
+      "epoch": 8.602389552653515,
+      "eval_loss": 0.15306152403354645,
+      "eval_runtime": 5.0581,
+      "eval_samples_per_second": 98.851,
+      "eval_steps_per_second": 6.326,
+      "step": 30960
+    },
+    {
+      "epoch": 8.613503751041955,
+      "grad_norm": 0.6288810968399048,
+      "learning_rate": 0.00022604427155691398,
+      "loss": 0.1128,
+      "step": 31000
+    },
+    {
+      "epoch": 8.752431230897471,
+      "grad_norm": 0.5629562139511108,
+      "learning_rate": 0.00021678243956654627,
+      "loss": 0.1109,
+      "step": 31500
+    },
+    {
+      "epoch": 8.802445123645457,
+      "eval_loss": 0.14975672960281372,
+      "eval_runtime": 6.0264,
+      "eval_samples_per_second": 82.968,
+      "eval_steps_per_second": 5.31,
+      "step": 31680
+    },
+    {
+      "epoch": 8.891358710752987,
+      "grad_norm": 0.7416991591453552,
+      "learning_rate": 0.0002075206075761786,
+      "loss": 0.1115,
+      "step": 32000
+    },
+    {
+      "epoch": 9.0025006946374,
+      "eval_loss": 0.1487710177898407,
+      "eval_runtime": 5.3789,
+      "eval_samples_per_second": 92.955,
+      "eval_steps_per_second": 5.949,
+      "step": 32400
+    },
+    {
+      "epoch": 9.030286190608502,
+      "grad_norm": 0.7242560386657715,
+      "learning_rate": 0.00019827729924979163,
+      "loss": 0.1066,
+      "step": 32500
+    },
+    {
+      "epoch": 9.169213670464018,
+      "grad_norm": 0.7700592279434204,
+      "learning_rate": 0.00018901546725942392,
+      "loss": 0.0983,
+      "step": 33000
+    },
+    {
+      "epoch": 9.202556265629342,
+      "eval_loss": 0.15055981278419495,
+      "eval_runtime": 5.1398,
+      "eval_samples_per_second": 97.28,
+      "eval_steps_per_second": 6.226,
+      "step": 33120
+    },
+    {
+      "epoch": 9.308141150319534,
+      "grad_norm": 0.6550413370132446,
+      "learning_rate": 0.00017975363526905622,
+      "loss": 0.0992,
+      "step": 33500
+    },
+    {
+      "epoch": 9.402611836621285,
+      "eval_loss": 0.1500197798013687,
+      "eval_runtime": 5.8828,
+      "eval_samples_per_second": 84.993,
+      "eval_steps_per_second": 5.44,
+      "step": 33840
+    },
+    {
+      "epoch": 9.447068630175048,
+      "grad_norm": 1.1206508874893188,
+      "learning_rate": 0.0001704918032786885,
+      "loss": 0.0974,
+      "step": 34000
+    },
+    {
+      "epoch": 9.585996110030564,
+      "grad_norm": 0.7649220824241638,
+      "learning_rate": 0.00016122997128832083,
+      "loss": 0.0999,
+      "step": 34500
+    },
+    {
+      "epoch": 9.602667407613225,
+      "eval_loss": 0.14790067076683044,
+      "eval_runtime": 4.866,
+      "eval_samples_per_second": 102.755,
+      "eval_steps_per_second": 6.576,
+      "step": 34560
+    },
+    {
+      "epoch": 9.72492358988608,
+      "grad_norm": 0.6786446571350098,
+      "learning_rate": 0.00015196813929795316,
+      "loss": 0.0994,
+      "step": 35000
+    },
+    {
+      "epoch": 9.802722978605168,
+      "eval_loss": 0.14430680871009827,
+      "eval_runtime": 6.005,
+      "eval_samples_per_second": 83.264,
+      "eval_steps_per_second": 5.329,
+      "step": 35280
+    },
+    {
+      "epoch": 9.863851069741594,
+      "grad_norm": 0.6465508341789246,
+      "learning_rate": 0.00014270630730758545,
+      "loss": 0.0985,
+      "step": 35500
+    }
+  ],
+  "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": 1.0121102553639813e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-35990/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d31253d1d9828754b954b23155d823529e2ebc7f148e5c229e9bc7b696124d
+size 6033