Training in progress, epoch 3, checkpoint

checkpoint-46707/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-46707/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": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-46707/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee4ae1b202220c9e94898f664fd44b9a58966daa491f5fc1210208dbd855194
+size 6304096

checkpoint-46707/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d905f5cb1b0383f2a797f042906874e4ab52f35cdfccb9de917e79acb59aa4
+size 12663802

checkpoint-46707/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e012bfe67a06396f80eaf055620ac01d33b1c332555217dcc4d659f477939b
+size 15984

checkpoint-46707/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c246fff219e67d0f70752037b524a2a6f2f1c5fef994e1ebf20f49e4eaa2691d
+size 15984

checkpoint-46707/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a7c6db0c6336aa44f6853189ce941b5b6c7d10f9dc54a3d1434c1dfabed008c
+size 15984

checkpoint-46707/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e992cf1cddba242fbc3bddee522a2a2291cc35baa926b417357ca6cb3da39a05
+size 15984

checkpoint-46707/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edfb5ce8e6f2fca0e49c2fd3cf0f388b43f3772faf2029c1c5a6203e4d79327d
+size 15984

checkpoint-46707/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ddea8287db271c7ec531b7bd169bd3eeb288e49eb1683af307190d846ce0b6
+size 15984

checkpoint-46707/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a11d95b5e9a6e4dc11215af0420e4aae14055fb1b66f9b24df1ae32333e159
+size 15984

checkpoint-46707/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a09aeb3d94cecf9b05e5b6734acda6363ca84864ee16bac97a1ded002998d20
+size 15984

checkpoint-46707/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2055b82e949db2c4abcbec2e91a1b292525373a735a73b4daf2ec5e942f85b70
+size 1064

checkpoint-46707/trainer_state.json

@@ -0,0 +1,796 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 3114,
+  "global_step": 46707,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03211510052026463,
+      "grad_norm": 0.7474520206451416,
+      "learning_rate": 0.0007978632753120518,
+      "loss": 0.5422,
+      "step": 500
+    },
+    {
+      "epoch": 0.06423020104052926,
+      "grad_norm": 0.89436274766922,
+      "learning_rate": 0.0007957265506241035,
+      "loss": 0.4574,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09634530156079389,
+      "grad_norm": 0.8834966421127319,
+      "learning_rate": 0.0007935855439227525,
+      "loss": 0.4305,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12846040208105852,
+      "grad_norm": 0.9943472743034363,
+      "learning_rate": 0.0007914445372214016,
+      "loss": 0.411,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16057550260132314,
+      "grad_norm": 0.738410472869873,
+      "learning_rate": 0.0007893035305200505,
+      "loss": 0.3989,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19269060312158778,
+      "grad_norm": 1.2562445402145386,
+      "learning_rate": 0.0007871668058321023,
+      "loss": 0.3906,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2000128460402081,
+      "eval_loss": 0.38617298007011414,
+      "eval_runtime": 6.1184,
+      "eval_samples_per_second": 81.721,
+      "eval_steps_per_second": 5.23,
+      "step": 3114
+    },
+    {
+      "epoch": 0.2248057036418524,
+      "grad_norm": 0.8588173389434814,
+      "learning_rate": 0.0007850257991307513,
+      "loss": 0.3847,
+      "step": 3500
+    },
+    {
+      "epoch": 0.25692080416211704,
+      "grad_norm": 0.8775615096092224,
+      "learning_rate": 0.0007828847924294003,
+      "loss": 0.3824,
+      "step": 4000
+    },
+    {
+      "epoch": 0.28903590468238166,
+      "grad_norm": 0.8612831830978394,
+      "learning_rate": 0.0007807437857280493,
+      "loss": 0.374,
+      "step": 4500
+    },
+    {
+      "epoch": 0.3211510052026463,
+      "grad_norm": 1.0078139305114746,
+      "learning_rate": 0.0007786027790266984,
+      "loss": 0.367,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3532661057229109,
+      "grad_norm": 0.7598047852516174,
+      "learning_rate": 0.0007764703363521528,
+      "loss": 0.3685,
+      "step": 5500
+    },
+    {
+      "epoch": 0.38538120624317557,
+      "grad_norm": 0.779103696346283,
+      "learning_rate": 0.0007743293296508018,
+      "loss": 0.3635,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4000256920804162,
+      "eval_loss": 0.3629798889160156,
+      "eval_runtime": 6.0698,
+      "eval_samples_per_second": 82.375,
+      "eval_steps_per_second": 5.272,
+      "step": 6228
+    },
+    {
+      "epoch": 0.4174963067634402,
+      "grad_norm": 1.0634421110153198,
+      "learning_rate": 0.0007721883229494509,
+      "loss": 0.3585,
+      "step": 6500
+    },
+    {
+      "epoch": 0.4496114072837048,
+      "grad_norm": 0.7991892099380493,
+      "learning_rate": 0.0007700473162480999,
+      "loss": 0.3542,
+      "step": 7000
+    },
+    {
+      "epoch": 0.4817265078039694,
+      "grad_norm": 1.0669060945510864,
+      "learning_rate": 0.000767906309546749,
+      "loss": 0.3507,
+      "step": 7500
+    },
+    {
+      "epoch": 0.5138416083242341,
+      "grad_norm": 0.764560878276825,
+      "learning_rate": 0.000765765302845398,
+      "loss": 0.3502,
+      "step": 8000
+    },
+    {
+      "epoch": 0.5459567088444987,
+      "grad_norm": 0.882352888584137,
+      "learning_rate": 0.000763624296144047,
+      "loss": 0.3538,
+      "step": 8500
+    },
+    {
+      "epoch": 0.5780718093647633,
+      "grad_norm": 1.4643352031707764,
+      "learning_rate": 0.000761483289442696,
+      "loss": 0.3503,
+      "step": 9000
+    },
+    {
+      "epoch": 0.6000385381206244,
+      "eval_loss": 0.34752723574638367,
+      "eval_runtime": 6.2876,
+      "eval_samples_per_second": 79.522,
+      "eval_steps_per_second": 5.089,
+      "step": 9342
+    },
+    {
+      "epoch": 0.610186909885028,
+      "grad_norm": 0.9141144752502441,
+      "learning_rate": 0.0007593465647547478,
+      "loss": 0.3461,
+      "step": 9500
+    },
+    {
+      "epoch": 0.6423020104052926,
+      "grad_norm": 0.7810879349708557,
+      "learning_rate": 0.0007572055580533967,
+      "loss": 0.345,
+      "step": 10000
+    },
+    {
+      "epoch": 0.6744171109255572,
+      "grad_norm": 0.6038429141044617,
+      "learning_rate": 0.0007550645513520458,
+      "loss": 0.348,
+      "step": 10500
+    },
+    {
+      "epoch": 0.7065322114458218,
+      "grad_norm": 0.8717966079711914,
+      "learning_rate": 0.0007529235446506948,
+      "loss": 0.3387,
+      "step": 11000
+    },
+    {
+      "epoch": 0.7386473119660865,
+      "grad_norm": 0.8474560976028442,
+      "learning_rate": 0.0007507825379493438,
+      "loss": 0.3493,
+      "step": 11500
+    },
+    {
+      "epoch": 0.7707624124863511,
+      "grad_norm": 1.002699375152588,
+      "learning_rate": 0.0007486415312479928,
+      "loss": 0.3403,
+      "step": 12000
+    },
+    {
+      "epoch": 0.8000513841608324,
+      "eval_loss": 0.3313402533531189,
+      "eval_runtime": 6.1854,
+      "eval_samples_per_second": 80.835,
+      "eval_steps_per_second": 5.173,
+      "step": 12456
+    },
+    {
+      "epoch": 0.8028775130066157,
+      "grad_norm": 0.9874686002731323,
+      "learning_rate": 0.0007465005245466419,
+      "loss": 0.3374,
+      "step": 12500
+    },
+    {
+      "epoch": 0.8349926135268804,
+      "grad_norm": 0.8380157351493835,
+      "learning_rate": 0.000744359517845291,
+      "loss": 0.3321,
+      "step": 13000
+    },
+    {
+      "epoch": 0.8671077140471449,
+      "grad_norm": 0.9501023888587952,
+      "learning_rate": 0.0007422270751707453,
+      "loss": 0.3384,
+      "step": 13500
+    },
+    {
+      "epoch": 0.8992228145674096,
+      "grad_norm": 0.8805665373802185,
+      "learning_rate": 0.0007400860684693944,
+      "loss": 0.3361,
+      "step": 14000
+    },
+    {
+      "epoch": 0.9313379150876743,
+      "grad_norm": 0.9132845401763916,
+      "learning_rate": 0.0007379450617680433,
+      "loss": 0.3346,
+      "step": 14500
+    },
+    {
+      "epoch": 0.9634530156079388,
+      "grad_norm": 1.006101369857788,
+      "learning_rate": 0.0007358040550666924,
+      "loss": 0.3348,
+      "step": 15000
+    },
+    {
+      "epoch": 0.9955681161282035,
+      "grad_norm": 0.7373970746994019,
+      "learning_rate": 0.0007336630483653414,
+      "loss": 0.3331,
+      "step": 15500
+    },
+    {
+      "epoch": 1.0000642302010405,
+      "eval_loss": 0.33074307441711426,
+      "eval_runtime": 6.1886,
+      "eval_samples_per_second": 80.793,
+      "eval_steps_per_second": 5.171,
+      "step": 15570
+    },
+    {
+      "epoch": 1.0276832166484682,
+      "grad_norm": 1.116804599761963,
+      "learning_rate": 0.0007315263236773932,
+      "loss": 0.3198,
+      "step": 16000
+    },
+    {
+      "epoch": 1.0597983171687329,
+      "grad_norm": 0.8930056095123291,
+      "learning_rate": 0.0007293853169760421,
+      "loss": 0.3236,
+      "step": 16500
+    },
+    {
+      "epoch": 1.0919134176889973,
+      "grad_norm": 1.135382056236267,
+      "learning_rate": 0.0007272443102746912,
+      "loss": 0.3195,
+      "step": 17000
+    },
+    {
+      "epoch": 1.124028518209262,
+      "grad_norm": 1.1518044471740723,
+      "learning_rate": 0.0007251033035733402,
+      "loss": 0.3212,
+      "step": 17500
+    },
+    {
+      "epoch": 1.1561436187295266,
+      "grad_norm": 0.8707193732261658,
+      "learning_rate": 0.0007229622968719892,
+      "loss": 0.3189,
+      "step": 18000
+    },
+    {
+      "epoch": 1.1882587192497913,
+      "grad_norm": 1.0189062356948853,
+      "learning_rate": 0.0007208212901706382,
+      "loss": 0.3239,
+      "step": 18500
+    },
+    {
+      "epoch": 1.2000770762412487,
+      "eval_loss": 0.31824222207069397,
+      "eval_runtime": 6.2671,
+      "eval_samples_per_second": 79.782,
+      "eval_steps_per_second": 5.106,
+      "step": 18684
+    },
+    {
+      "epoch": 1.2203738197700558,
+      "grad_norm": 0.9791691303253174,
+      "learning_rate": 0.00071868456548269,
+      "loss": 0.3208,
+      "step": 19000
+    },
+    {
+      "epoch": 1.2524889202903204,
+      "grad_norm": 0.6720991134643555,
+      "learning_rate": 0.000716543558781339,
+      "loss": 0.3196,
+      "step": 19500
+    },
+    {
+      "epoch": 1.2846040208105851,
+      "grad_norm": 0.8015382289886475,
+      "learning_rate": 0.000714402552079988,
+      "loss": 0.322,
+      "step": 20000
+    },
+    {
+      "epoch": 1.3167191213308498,
+      "grad_norm": 0.9411060214042664,
+      "learning_rate": 0.0007122615453786371,
+      "loss": 0.3178,
+      "step": 20500
+    },
+    {
+      "epoch": 1.3488342218511145,
+      "grad_norm": 1.2184011936187744,
+      "learning_rate": 0.000710120538677286,
+      "loss": 0.3157,
+      "step": 21000
+    },
+    {
+      "epoch": 1.3809493223713791,
+      "grad_norm": 0.9301189184188843,
+      "learning_rate": 0.0007079795319759352,
+      "loss": 0.3155,
+      "step": 21500
+    },
+    {
+      "epoch": 1.4000899222814567,
+      "eval_loss": 0.30902907252311707,
+      "eval_runtime": 6.1349,
+      "eval_samples_per_second": 81.501,
+      "eval_steps_per_second": 5.216,
+      "step": 21798
+    },
+    {
+      "epoch": 1.4130644228916436,
+      "grad_norm": 0.8129053115844727,
+      "learning_rate": 0.0007058385252745842,
+      "loss": 0.3187,
+      "step": 22000
+    },
+    {
+      "epoch": 1.4451795234119083,
+      "grad_norm": 0.9045296311378479,
+      "learning_rate": 0.0007037018005866359,
+      "loss": 0.3184,
+      "step": 22500
+    },
+    {
+      "epoch": 1.477294623932173,
+      "grad_norm": 1.3381433486938477,
+      "learning_rate": 0.0007015607938852849,
+      "loss": 0.3161,
+      "step": 23000
+    },
+    {
+      "epoch": 1.5094097244524374,
+      "grad_norm": 1.2223104238510132,
+      "learning_rate": 0.0006994240691973367,
+      "loss": 0.3105,
+      "step": 23500
+    },
+    {
+      "epoch": 1.541524824972702,
+      "grad_norm": 1.6614145040512085,
+      "learning_rate": 0.0006972830624959856,
+      "loss": 0.312,
+      "step": 24000
+    },
+    {
+      "epoch": 1.5736399254929667,
+      "grad_norm": 1.0367958545684814,
+      "learning_rate": 0.0006951420557946347,
+      "loss": 0.3143,
+      "step": 24500
+    },
+    {
+      "epoch": 1.6001027683216649,
+      "eval_loss": 0.3097926378250122,
+      "eval_runtime": 6.0915,
+      "eval_samples_per_second": 82.082,
+      "eval_steps_per_second": 5.253,
+      "step": 24912
+    },
+    {
+      "epoch": 1.6057550260132314,
+      "grad_norm": 0.9055228233337402,
+      "learning_rate": 0.0006930010490932837,
+      "loss": 0.3142,
+      "step": 25000
+    },
+    {
+      "epoch": 1.637870126533496,
+      "grad_norm": 1.0741256475448608,
+      "learning_rate": 0.0006908600423919327,
+      "loss": 0.3172,
+      "step": 25500
+    },
+    {
+      "epoch": 1.6699852270537607,
+      "grad_norm": 0.8932151198387146,
+      "learning_rate": 0.0006887233177039845,
+      "loss": 0.3117,
+      "step": 26000
+    },
+    {
+      "epoch": 1.7021003275740254,
+      "grad_norm": 1.035973310470581,
+      "learning_rate": 0.0006865823110026335,
+      "loss": 0.313,
+      "step": 26500
+    },
+    {
+      "epoch": 1.73421542809429,
+      "grad_norm": 0.9380423426628113,
+      "learning_rate": 0.0006844455863146852,
+      "loss": 0.3083,
+      "step": 27000
+    },
+    {
+      "epoch": 1.7663305286145545,
+      "grad_norm": 0.8082458972930908,
+      "learning_rate": 0.0006823045796133342,
+      "loss": 0.3054,
+      "step": 27500
+    },
+    {
+      "epoch": 1.7984456291348192,
+      "grad_norm": 0.646691620349884,
+      "learning_rate": 0.0006801635729119833,
+      "loss": 0.3114,
+      "step": 28000
+    },
+    {
+      "epoch": 1.8001156143618728,
+      "eval_loss": 0.3078465163707733,
+      "eval_runtime": 6.2786,
+      "eval_samples_per_second": 79.635,
+      "eval_steps_per_second": 5.097,
+      "step": 28026
+    },
+    {
+      "epoch": 1.8305607296550839,
+      "grad_norm": 0.8007400035858154,
+      "learning_rate": 0.0006780225662106322,
+      "loss": 0.3151,
+      "step": 28500
+    },
+    {
+      "epoch": 1.8626758301753483,
+      "grad_norm": 0.8854690194129944,
+      "learning_rate": 0.0006758815595092813,
+      "loss": 0.3094,
+      "step": 29000
+    },
+    {
+      "epoch": 1.894790930695613,
+      "grad_norm": 0.9263831377029419,
+      "learning_rate": 0.0006737405528079303,
+      "loss": 0.3063,
+      "step": 29500
+    },
+    {
+      "epoch": 1.9269060312158777,
+      "grad_norm": 0.946422815322876,
+      "learning_rate": 0.0006715995461065794,
+      "loss": 0.3061,
+      "step": 30000
+    },
+    {
+      "epoch": 1.9590211317361423,
+      "grad_norm": 0.9862657785415649,
+      "learning_rate": 0.0006694585394052283,
+      "loss": 0.306,
+      "step": 30500
+    },
+    {
+      "epoch": 1.991136232256407,
+      "grad_norm": 1.5128605365753174,
+      "learning_rate": 0.0006673175327038774,
+      "loss": 0.305,
+      "step": 31000
+    },
+    {
+      "epoch": 2.000128460402081,
+      "eval_loss": 0.30374282598495483,
+      "eval_runtime": 6.3123,
+      "eval_samples_per_second": 79.21,
+      "eval_steps_per_second": 5.069,
+      "step": 31140
+    },
+    {
+      "epoch": 2.0232513327766717,
+      "grad_norm": 0.9001232385635376,
+      "learning_rate": 0.0006651765260025264,
+      "loss": 0.2992,
+      "step": 31500
+    },
+    {
+      "epoch": 2.0553664332969364,
+      "grad_norm": 0.6829231381416321,
+      "learning_rate": 0.0006630355193011754,
+      "loss": 0.2984,
+      "step": 32000
+    },
+    {
+      "epoch": 2.087481533817201,
+      "grad_norm": 1.010355830192566,
+      "learning_rate": 0.0006608945125998244,
+      "loss": 0.293,
+      "step": 32500
+    },
+    {
+      "epoch": 2.1195966343374657,
+      "grad_norm": 0.8349985480308533,
+      "learning_rate": 0.0006587620699252789,
+      "loss": 0.2984,
+      "step": 33000
+    },
+    {
+      "epoch": 2.15171173485773,
+      "grad_norm": 1.2974556684494019,
+      "learning_rate": 0.0006566210632239279,
+      "loss": 0.2977,
+      "step": 33500
+    },
+    {
+      "epoch": 2.1838268353779946,
+      "grad_norm": 1.0526032447814941,
+      "learning_rate": 0.0006544800565225769,
+      "loss": 0.2934,
+      "step": 34000
+    },
+    {
+      "epoch": 2.2001413064422892,
+      "eval_loss": 0.2976307272911072,
+      "eval_runtime": 6.1928,
+      "eval_samples_per_second": 80.739,
+      "eval_steps_per_second": 5.167,
+      "step": 34254
+    },
+    {
+      "epoch": 2.2159419358982593,
+      "grad_norm": 1.0207550525665283,
+      "learning_rate": 0.000652339049821226,
+      "loss": 0.2999,
+      "step": 34500
+    },
+    {
+      "epoch": 2.248057036418524,
+      "grad_norm": 0.7849873900413513,
+      "learning_rate": 0.0006501980431198749,
+      "loss": 0.3017,
+      "step": 35000
+    },
+    {
+      "epoch": 2.2801721369387886,
+      "grad_norm": 0.807049572467804,
+      "learning_rate": 0.000648057036418524,
+      "loss": 0.2931,
+      "step": 35500
+    },
+    {
+      "epoch": 2.3122872374590533,
+      "grad_norm": 0.9243353605270386,
+      "learning_rate": 0.0006459160297171731,
+      "loss": 0.2956,
+      "step": 36000
+    },
+    {
+      "epoch": 2.344402337979318,
+      "grad_norm": 1.2570290565490723,
+      "learning_rate": 0.0006437750230158221,
+      "loss": 0.2958,
+      "step": 36500
+    },
+    {
+      "epoch": 2.3765174384995826,
+      "grad_norm": 0.8402499556541443,
+      "learning_rate": 0.0006416340163144711,
+      "loss": 0.2983,
+      "step": 37000
+    },
+    {
+      "epoch": 2.4001541524824974,
+      "eval_loss": 0.29359912872314453,
+      "eval_runtime": 6.2635,
+      "eval_samples_per_second": 79.828,
+      "eval_steps_per_second": 5.109,
+      "step": 37368
+    },
+    {
+      "epoch": 2.4086325390198473,
+      "grad_norm": 0.8177831768989563,
+      "learning_rate": 0.0006394930096131202,
+      "loss": 0.2949,
+      "step": 37500
+    },
+    {
+      "epoch": 2.4407476395401115,
+      "grad_norm": 1.740903377532959,
+      "learning_rate": 0.0006373562849251718,
+      "loss": 0.2923,
+      "step": 38000
+    },
+    {
+      "epoch": 2.472862740060376,
+      "grad_norm": 0.799891471862793,
+      "learning_rate": 0.0006352195602372236,
+      "loss": 0.291,
+      "step": 38500
+    },
+    {
+      "epoch": 2.504977840580641,
+      "grad_norm": 0.7158030867576599,
+      "learning_rate": 0.0006330828355492754,
+      "loss": 0.2913,
+      "step": 39000
+    },
+    {
+      "epoch": 2.5370929411009056,
+      "grad_norm": 1.3045659065246582,
+      "learning_rate": 0.0006309418288479243,
+      "loss": 0.2888,
+      "step": 39500
+    },
+    {
+      "epoch": 2.5692080416211702,
+      "grad_norm": 0.874169647693634,
+      "learning_rate": 0.0006288008221465734,
+      "loss": 0.295,
+      "step": 40000
+    },
+    {
+      "epoch": 2.600166998522705,
+      "eval_loss": 0.29626408219337463,
+      "eval_runtime": 6.2399,
+      "eval_samples_per_second": 80.129,
+      "eval_steps_per_second": 5.128,
+      "step": 40482
+    },
+    {
+      "epoch": 2.601323142141435,
+      "grad_norm": 0.9616047739982605,
+      "learning_rate": 0.0006266598154452224,
+      "loss": 0.2929,
+      "step": 40500
+    },
+    {
+      "epoch": 2.6334382426616996,
+      "grad_norm": 0.8935590386390686,
+      "learning_rate": 0.0006245188087438714,
+      "loss": 0.292,
+      "step": 41000
+    },
+    {
+      "epoch": 2.6655533431819642,
+      "grad_norm": 0.7435338497161865,
+      "learning_rate": 0.0006223778020425204,
+      "loss": 0.2904,
+      "step": 41500
+    },
+    {
+      "epoch": 2.697668443702229,
+      "grad_norm": 0.8259156346321106,
+      "learning_rate": 0.0006202367953411695,
+      "loss": 0.2868,
+      "step": 42000
+    },
+    {
+      "epoch": 2.729783544222493,
+      "grad_norm": 0.848035454750061,
+      "learning_rate": 0.0006180957886398185,
+      "loss": 0.2876,
+      "step": 42500
+    },
+    {
+      "epoch": 2.7618986447427583,
+      "grad_norm": 0.9523009657859802,
+      "learning_rate": 0.0006159547819384675,
+      "loss": 0.2891,
+      "step": 43000
+    },
+    {
+      "epoch": 2.7940137452630225,
+      "grad_norm": 0.7964786887168884,
+      "learning_rate": 0.0006138137752371165,
+      "loss": 0.2932,
+      "step": 43500
+    },
+    {
+      "epoch": 2.8001798445629134,
+      "eval_loss": 0.2853344976902008,
+      "eval_runtime": 6.2618,
+      "eval_samples_per_second": 79.849,
+      "eval_steps_per_second": 5.11,
+      "step": 43596
+    },
+    {
+      "epoch": 2.826128845783287,
+      "grad_norm": 1.2521328926086426,
+      "learning_rate": 0.0006116727685357656,
+      "loss": 0.2884,
+      "step": 44000
+    },
+    {
+      "epoch": 2.858243946303552,
+      "grad_norm": 1.0122313499450684,
+      "learning_rate": 0.0006095317618344145,
+      "loss": 0.2896,
+      "step": 44500
+    },
+    {
+      "epoch": 2.8903590468238165,
+      "grad_norm": 0.9321467280387878,
+      "learning_rate": 0.0006073907551330636,
+      "loss": 0.2893,
+      "step": 45000
+    },
+    {
+      "epoch": 2.922474147344081,
+      "grad_norm": 1.090589165687561,
+      "learning_rate": 0.0006052497484317126,
+      "loss": 0.2916,
+      "step": 45500
+    },
+    {
+      "epoch": 2.954589247864346,
+      "grad_norm": 1.4329869747161865,
+      "learning_rate": 0.0006031087417303616,
+      "loss": 0.2871,
+      "step": 46000
+    },
+    {
+      "epoch": 2.9867043483846105,
+      "grad_norm": 0.9811238646507263,
+      "learning_rate": 0.0006009677350290106,
+      "loss": 0.2866,
+      "step": 46500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 186828,
+  "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": 3.1426026591360123e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-46707/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892edd3338e5c2cbc20ea9ef24acea77922058f7e35a99445dd322996489f4e7
+size 5496