Upload 8 files

README.md

@@ -1,3 +1,202 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# 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 0.10.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "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": 16,
+  "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
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606e68bfa25399f65b51d4d0717bf4caf35c3f46881fd1808ca8ecdf30d35a25
+size 16823434

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33cc8f054bd9adb6542e659392973c6d3c68481190e0a4cdf7638c9d9d606c9
+size 33662074

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab528e5cc79c8b0170c4528aa77b2350a561c1d11f0f78ae4dcd1e1a5b50970
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a1e257aac9158b75c35ef44d4eae055e511d1f723567e8ddee4e90477b4e3a
+size 1064

trainer_state.json

@@ -0,0 +1,1173 @@
+{
+  "best_metric": 1.5669885873794556,
+  "best_model_checkpoint": "/scratch/czm5kz/llama2-7b_8_50_0.0003_sg_finetuned_with_output/checkpoint-180",
+  "epoch": 47.407407407407405,
+  "eval_steps": 20,
+  "global_step": 640,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.398926019668579,
+      "learning_rate": 0.0002986153846153846,
+      "loss": 5.3458,
+      "step": 5
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.079797387123108,
+      "learning_rate": 0.0002963076923076923,
+      "loss": 4.6876,
+      "step": 10
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 7.786762237548828,
+      "learning_rate": 0.000294,
+      "loss": 4.3658,
+      "step": 15
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.545445442199707,
+      "learning_rate": 0.0002916923076923077,
+      "loss": 3.4792,
+      "step": 20
+    },
+    {
+      "epoch": 1.48,
+      "eval_loss": 3.3610048294067383,
+      "eval_runtime": 0.4367,
+      "eval_samples_per_second": 61.822,
+      "eval_steps_per_second": 9.159,
+      "step": 20
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 1.6737030744552612,
+      "learning_rate": 0.0002893846153846154,
+      "loss": 3.0828,
+      "step": 25
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 2.414368152618408,
+      "learning_rate": 0.00028707692307692305,
+      "loss": 2.6784,
+      "step": 30
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 3.006044864654541,
+      "learning_rate": 0.00028476923076923075,
+      "loss": 2.4781,
+      "step": 35
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 2.7223751544952393,
+      "learning_rate": 0.00028246153846153845,
+      "loss": 2.2626,
+      "step": 40
+    },
+    {
+      "epoch": 2.96,
+      "eval_loss": 2.527669906616211,
+      "eval_runtime": 0.4336,
+      "eval_samples_per_second": 62.265,
+      "eval_steps_per_second": 9.224,
+      "step": 40
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 4.4172210693359375,
+      "learning_rate": 0.00028015384615384615,
+      "loss": 1.8627,
+      "step": 45
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 3.698852062225342,
+      "learning_rate": 0.0002778461538461538,
+      "loss": 1.6018,
+      "step": 50
+    },
+    {
+      "epoch": 4.07,
+      "grad_norm": 3.051743984222412,
+      "learning_rate": 0.0002755384615384615,
+      "loss": 1.4827,
+      "step": 55
+    },
+    {
+      "epoch": 4.44,
+      "grad_norm": 5.160757064819336,
+      "learning_rate": 0.0002732307692307692,
+      "loss": 1.0585,
+      "step": 60
+    },
+    {
+      "epoch": 4.44,
+      "eval_loss": 2.1469380855560303,
+      "eval_runtime": 0.4338,
+      "eval_samples_per_second": 62.246,
+      "eval_steps_per_second": 9.222,
+      "step": 60
+    },
+    {
+      "epoch": 4.81,
+      "grad_norm": 4.5085062980651855,
+      "learning_rate": 0.0002709230769230769,
+      "loss": 1.0433,
+      "step": 65
+    },
+    {
+      "epoch": 5.19,
+      "grad_norm": 3.886779546737671,
+      "learning_rate": 0.00026861538461538456,
+      "loss": 0.9697,
+      "step": 70
+    },
+    {
+      "epoch": 5.56,
+      "grad_norm": 4.663851261138916,
+      "learning_rate": 0.00026630769230769226,
+      "loss": 0.6188,
+      "step": 75
+    },
+    {
+      "epoch": 5.93,
+      "grad_norm": 5.576120853424072,
+      "learning_rate": 0.00026399999999999997,
+      "loss": 0.7594,
+      "step": 80
+    },
+    {
+      "epoch": 5.93,
+      "eval_loss": 1.739160418510437,
+      "eval_runtime": 0.4327,
+      "eval_samples_per_second": 62.404,
+      "eval_steps_per_second": 9.245,
+      "step": 80
+    },
+    {
+      "epoch": 6.3,
+      "grad_norm": 2.55850887298584,
+      "learning_rate": 0.00026169230769230767,
+      "loss": 0.5985,
+      "step": 85
+    },
+    {
+      "epoch": 6.67,
+      "grad_norm": 3.429755687713623,
+      "learning_rate": 0.00025938461538461537,
+      "loss": 0.4957,
+      "step": 90
+    },
+    {
+      "epoch": 7.04,
+      "grad_norm": 4.753056526184082,
+      "learning_rate": 0.000257076923076923,
+      "loss": 0.6527,
+      "step": 95
+    },
+    {
+      "epoch": 7.41,
+      "grad_norm": 2.638728380203247,
+      "learning_rate": 0.0002547692307692307,
+      "loss": 0.4148,
+      "step": 100
+    },
+    {
+      "epoch": 7.41,
+      "eval_loss": 1.5832433700561523,
+      "eval_runtime": 0.4351,
+      "eval_samples_per_second": 62.055,
+      "eval_steps_per_second": 9.193,
+      "step": 100
+    },
+    {
+      "epoch": 7.78,
+      "grad_norm": 2.906188726425171,
+      "learning_rate": 0.0002524615384615384,
+      "loss": 0.4678,
+      "step": 105
+    },
+    {
+      "epoch": 8.15,
+      "grad_norm": 2.0787110328674316,
+      "learning_rate": 0.00025015384615384613,
+      "loss": 0.4415,
+      "step": 110
+    },
+    {
+      "epoch": 8.52,
+      "grad_norm": 2.6470298767089844,
+      "learning_rate": 0.00024784615384615383,
+      "loss": 0.3638,
+      "step": 115
+    },
+    {
+      "epoch": 8.89,
+      "grad_norm": 3.3667097091674805,
+      "learning_rate": 0.00024553846153846154,
+      "loss": 0.4925,
+      "step": 120
+    },
+    {
+      "epoch": 8.89,
+      "eval_loss": 1.6094781160354614,
+      "eval_runtime": 0.4339,
+      "eval_samples_per_second": 62.231,
+      "eval_steps_per_second": 9.219,
+      "step": 120
+    },
+    {
+      "epoch": 9.26,
+      "grad_norm": 1.8297497034072876,
+      "learning_rate": 0.0002432307692307692,
+      "loss": 0.3612,
+      "step": 125
+    },
+    {
+      "epoch": 9.63,
+      "grad_norm": 2.8483166694641113,
+      "learning_rate": 0.0002409230769230769,
+      "loss": 0.39,
+      "step": 130
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.550173282623291,
+      "learning_rate": 0.0002386153846153846,
+      "loss": 0.4645,
+      "step": 135
+    },
+    {
+      "epoch": 10.37,
+      "grad_norm": 1.982654333114624,
+      "learning_rate": 0.0002363076923076923,
+      "loss": 0.3114,
+      "step": 140
+    },
+    {
+      "epoch": 10.37,
+      "eval_loss": 1.7044697999954224,
+      "eval_runtime": 0.4349,
+      "eval_samples_per_second": 62.08,
+      "eval_steps_per_second": 9.197,
+      "step": 140
+    },
+    {
+      "epoch": 10.74,
+      "grad_norm": 2.9532089233398438,
+      "learning_rate": 0.000234,
+      "loss": 0.4241,
+      "step": 145
+    },
+    {
+      "epoch": 11.11,
+      "grad_norm": 1.4060415029525757,
+      "learning_rate": 0.0002316923076923077,
+      "loss": 0.3897,
+      "step": 150
+    },
+    {
+      "epoch": 11.48,
+      "grad_norm": 1.5898511409759521,
+      "learning_rate": 0.00022938461538461535,
+      "loss": 0.3231,
+      "step": 155
+    },
+    {
+      "epoch": 11.85,
+      "grad_norm": 2.111783266067505,
+      "learning_rate": 0.00022707692307692305,
+      "loss": 0.4056,
+      "step": 160
+    },
+    {
+      "epoch": 11.85,
+      "eval_loss": 1.7500680685043335,
+      "eval_runtime": 0.4341,
+      "eval_samples_per_second": 62.203,
+      "eval_steps_per_second": 9.215,
+      "step": 160
+    },
+    {
+      "epoch": 12.22,
+      "grad_norm": 1.6774641275405884,
+      "learning_rate": 0.00022476923076923075,
+      "loss": 0.3562,
+      "step": 165
+    },
+    {
+      "epoch": 12.59,
+      "grad_norm": 1.5955278873443604,
+      "learning_rate": 0.00022246153846153846,
+      "loss": 0.3484,
+      "step": 170
+    },
+    {
+      "epoch": 12.96,
+      "grad_norm": 1.2137044668197632,
+      "learning_rate": 0.00022015384615384613,
+      "loss": 0.3616,
+      "step": 175
+    },
+    {
+      "epoch": 13.33,
+      "grad_norm": 1.3046234846115112,
+      "learning_rate": 0.00021784615384615383,
+      "loss": 0.3443,
+      "step": 180
+    },
+    {
+      "epoch": 13.33,
+      "eval_loss": 1.5669885873794556,
+      "eval_runtime": 0.4348,
+      "eval_samples_per_second": 62.098,
+      "eval_steps_per_second": 9.2,
+      "step": 180
+    },
+    {
+      "epoch": 13.7,
+      "grad_norm": 2.3079042434692383,
+      "learning_rate": 0.00021553846153846154,
+      "loss": 0.3503,
+      "step": 185
+    },
+    {
+      "epoch": 14.07,
+      "grad_norm": 0.9355862736701965,
+      "learning_rate": 0.00021323076923076921,
+      "loss": 0.3417,
+      "step": 190
+    },
+    {
+      "epoch": 14.44,
+      "grad_norm": 1.706770420074463,
+      "learning_rate": 0.0002109230769230769,
+      "loss": 0.3187,
+      "step": 195
+    },
+    {
+      "epoch": 14.81,
+      "grad_norm": 1.9932715892791748,
+      "learning_rate": 0.0002086153846153846,
+      "loss": 0.3489,
+      "step": 200
+    },
+    {
+      "epoch": 14.81,
+      "eval_loss": 1.6050857305526733,
+      "eval_runtime": 0.4347,
+      "eval_samples_per_second": 62.115,
+      "eval_steps_per_second": 9.202,
+      "step": 200
+    },
+    {
+      "epoch": 15.19,
+      "grad_norm": 0.947511613368988,
+      "learning_rate": 0.0002063076923076923,
+      "loss": 0.3556,
+      "step": 205
+    },
+    {
+      "epoch": 15.56,
+      "grad_norm": 1.3406760692596436,
+      "learning_rate": 0.000204,
+      "loss": 0.3065,
+      "step": 210
+    },
+    {
+      "epoch": 15.93,
+      "grad_norm": 1.2684600353240967,
+      "learning_rate": 0.00020169230769230767,
+      "loss": 0.3413,
+      "step": 215
+    },
+    {
+      "epoch": 16.3,
+      "grad_norm": 1.7013931274414062,
+      "learning_rate": 0.00019938461538461538,
+      "loss": 0.3156,
+      "step": 220
+    },
+    {
+      "epoch": 16.3,
+      "eval_loss": 1.7684317827224731,
+      "eval_runtime": 0.4353,
+      "eval_samples_per_second": 62.027,
+      "eval_steps_per_second": 9.189,
+      "step": 220
+    },
+    {
+      "epoch": 16.67,
+      "grad_norm": 1.1557570695877075,
+      "learning_rate": 0.00019707692307692305,
+      "loss": 0.3084,
+      "step": 225
+    },
+    {
+      "epoch": 17.04,
+      "grad_norm": 1.1206583976745605,
+      "learning_rate": 0.00019476923076923076,
+      "loss": 0.4039,
+      "step": 230
+    },
+    {
+      "epoch": 17.41,
+      "grad_norm": 1.4177170991897583,
+      "learning_rate": 0.00019246153846153843,
+      "loss": 0.3247,
+      "step": 235
+    },
+    {
+      "epoch": 17.78,
+      "grad_norm": 1.4315319061279297,
+      "learning_rate": 0.00019015384615384613,
+      "loss": 0.3107,
+      "step": 240
+    },
+    {
+      "epoch": 17.78,
+      "eval_loss": 1.6817841529846191,
+      "eval_runtime": 0.4335,
+      "eval_samples_per_second": 62.287,
+      "eval_steps_per_second": 9.228,
+      "step": 240
+    },
+    {
+      "epoch": 18.15,
+      "grad_norm": 1.2824641466140747,
+      "learning_rate": 0.00018784615384615384,
+      "loss": 0.3149,
+      "step": 245
+    },
+    {
+      "epoch": 18.52,
+      "grad_norm": 1.095780849456787,
+      "learning_rate": 0.00018553846153846154,
+      "loss": 0.2916,
+      "step": 250
+    },
+    {
+      "epoch": 18.89,
+      "grad_norm": 1.2812676429748535,
+      "learning_rate": 0.00018323076923076922,
+      "loss": 0.3353,
+      "step": 255
+    },
+    {
+      "epoch": 19.26,
+      "grad_norm": 1.171350359916687,
+      "learning_rate": 0.0001809230769230769,
+      "loss": 0.309,
+      "step": 260
+    },
+    {
+      "epoch": 19.26,
+      "eval_loss": 1.7549753189086914,
+      "eval_runtime": 0.4347,
+      "eval_samples_per_second": 62.113,
+      "eval_steps_per_second": 9.202,
+      "step": 260
+    },
+    {
+      "epoch": 19.63,
+      "grad_norm": 1.1714686155319214,
+      "learning_rate": 0.0001786153846153846,
+      "loss": 0.3119,
+      "step": 265
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.0897107124328613,
+      "learning_rate": 0.0001763076923076923,
+      "loss": 0.326,
+      "step": 270
+    },
+    {
+      "epoch": 20.37,
+      "grad_norm": 1.1124438047409058,
+      "learning_rate": 0.00017399999999999997,
+      "loss": 0.2985,
+      "step": 275
+    },
+    {
+      "epoch": 20.74,
+      "grad_norm": 0.9445765018463135,
+      "learning_rate": 0.00017169230769230768,
+      "loss": 0.2918,
+      "step": 280
+    },
+    {
+      "epoch": 20.74,
+      "eval_loss": 1.7201834917068481,
+      "eval_runtime": 0.4514,
+      "eval_samples_per_second": 59.813,
+      "eval_steps_per_second": 8.861,
+      "step": 280
+    },
+    {
+      "epoch": 21.11,
+      "grad_norm": 0.9067970514297485,
+      "learning_rate": 0.00016938461538461538,
+      "loss": 0.3118,
+      "step": 285
+    },
+    {
+      "epoch": 21.48,
+      "grad_norm": 1.0378901958465576,
+      "learning_rate": 0.00016707692307692308,
+      "loss": 0.3016,
+      "step": 290
+    },
+    {
+      "epoch": 21.85,
+      "grad_norm": 1.2347774505615234,
+      "learning_rate": 0.00016476923076923073,
+      "loss": 0.2904,
+      "step": 295
+    },
+    {
+      "epoch": 22.22,
+      "grad_norm": 0.9320012927055359,
+      "learning_rate": 0.00016246153846153843,
+      "loss": 0.3348,
+      "step": 300
+    },
+    {
+      "epoch": 22.22,
+      "eval_loss": 1.7654225826263428,
+      "eval_runtime": 0.4352,
+      "eval_samples_per_second": 62.036,
+      "eval_steps_per_second": 9.191,
+      "step": 300
+    },
+    {
+      "epoch": 22.59,
+      "grad_norm": 0.8344219326972961,
+      "learning_rate": 0.00016015384615384614,
+      "loss": 0.2905,
+      "step": 305
+    },
+    {
+      "epoch": 22.96,
+      "grad_norm": 1.3457179069519043,
+      "learning_rate": 0.00015784615384615384,
+      "loss": 0.3244,
+      "step": 310
+    },
+    {
+      "epoch": 23.33,
+      "grad_norm": 1.1215949058532715,
+      "learning_rate": 0.00015553846153846152,
+      "loss": 0.2964,
+      "step": 315
+    },
+    {
+      "epoch": 23.7,
+      "grad_norm": 0.8459953665733337,
+      "learning_rate": 0.00015323076923076922,
+      "loss": 0.3206,
+      "step": 320
+    },
+    {
+      "epoch": 23.7,
+      "eval_loss": 1.8162420988082886,
+      "eval_runtime": 0.4339,
+      "eval_samples_per_second": 62.219,
+      "eval_steps_per_second": 9.218,
+      "step": 320
+    },
+    {
+      "epoch": 24.07,
+      "grad_norm": 0.8673954010009766,
+      "learning_rate": 0.00015092307692307692,
+      "loss": 0.2768,
+      "step": 325
+    },
+    {
+      "epoch": 24.44,
+      "grad_norm": 0.9475287795066833,
+      "learning_rate": 0.0001486153846153846,
+      "loss": 0.2818,
+      "step": 330
+    },
+    {
+      "epoch": 24.81,
+      "grad_norm": 0.9035760164260864,
+      "learning_rate": 0.0001463076923076923,
+      "loss": 0.3097,
+      "step": 335
+    },
+    {
+      "epoch": 25.19,
+      "grad_norm": 0.8320503830909729,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 0.2968,
+      "step": 340
+    },
+    {
+      "epoch": 25.19,
+      "eval_loss": 1.8249504566192627,
+      "eval_runtime": 0.4343,
+      "eval_samples_per_second": 62.165,
+      "eval_steps_per_second": 9.21,
+      "step": 340
+    },
+    {
+      "epoch": 25.56,
+      "grad_norm": 1.0484280586242676,
+      "learning_rate": 0.00014169230769230768,
+      "loss": 0.2661,
+      "step": 345
+    },
+    {
+      "epoch": 25.93,
+      "grad_norm": 1.3034342527389526,
+      "learning_rate": 0.00013938461538461536,
+      "loss": 0.3249,
+      "step": 350
+    },
+    {
+      "epoch": 26.3,
+      "grad_norm": 0.7918898463249207,
+      "learning_rate": 0.00013707692307692306,
+      "loss": 0.2881,
+      "step": 355
+    },
+    {
+      "epoch": 26.67,
+      "grad_norm": 0.8644436001777649,
+      "learning_rate": 0.00013476923076923076,
+      "loss": 0.3108,
+      "step": 360
+    },
+    {
+      "epoch": 26.67,
+      "eval_loss": 1.859883189201355,
+      "eval_runtime": 0.4339,
+      "eval_samples_per_second": 62.222,
+      "eval_steps_per_second": 9.218,
+      "step": 360
+    },
+    {
+      "epoch": 27.04,
+      "grad_norm": 0.8299930095672607,
+      "learning_rate": 0.00013246153846153846,
+      "loss": 0.2873,
+      "step": 365
+    },
+    {
+      "epoch": 27.41,
+      "grad_norm": 0.7016355991363525,
+      "learning_rate": 0.00013015384615384614,
+      "loss": 0.3059,
+      "step": 370
+    },
+    {
+      "epoch": 27.78,
+      "grad_norm": 0.9215915203094482,
+      "learning_rate": 0.00012784615384615384,
+      "loss": 0.2854,
+      "step": 375
+    },
+    {
+      "epoch": 28.15,
+      "grad_norm": 0.8328156471252441,
+      "learning_rate": 0.00012553846153846152,
+      "loss": 0.274,
+      "step": 380
+    },
+    {
+      "epoch": 28.15,
+      "eval_loss": 1.9108076095581055,
+      "eval_runtime": 0.4355,
+      "eval_samples_per_second": 62.003,
+      "eval_steps_per_second": 9.186,
+      "step": 380
+    },
+    {
+      "epoch": 28.52,
+      "grad_norm": 0.9325290322303772,
+      "learning_rate": 0.00012323076923076922,
+      "loss": 0.2775,
+      "step": 385
+    },
+    {
+      "epoch": 28.89,
+      "grad_norm": 0.882301926612854,
+      "learning_rate": 0.00012092307692307691,
+      "loss": 0.3149,
+      "step": 390
+    },
+    {
+      "epoch": 29.26,
+      "grad_norm": 0.7358686923980713,
+      "learning_rate": 0.0001186153846153846,
+      "loss": 0.2858,
+      "step": 395
+    },
+    {
+      "epoch": 29.63,
+      "grad_norm": 1.316838264465332,
+      "learning_rate": 0.00011630769230769229,
+      "loss": 0.2914,
+      "step": 400
+    },
+    {
+      "epoch": 29.63,
+      "eval_loss": 1.9297478199005127,
+      "eval_runtime": 0.4351,
+      "eval_samples_per_second": 62.054,
+      "eval_steps_per_second": 9.193,
+      "step": 400
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 1.2439055442810059,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.3069,
+      "step": 405
+    },
+    {
+      "epoch": 30.37,
+      "grad_norm": 0.6521609425544739,
+      "learning_rate": 0.00011169230769230768,
+      "loss": 0.2713,
+      "step": 410
+    },
+    {
+      "epoch": 30.74,
+      "grad_norm": 1.044469952583313,
+      "learning_rate": 0.00010938461538461537,
+      "loss": 0.2722,
+      "step": 415
+    },
+    {
+      "epoch": 31.11,
+      "grad_norm": 0.9478164911270142,
+      "learning_rate": 0.00010707692307692306,
+      "loss": 0.3216,
+      "step": 420
+    },
+    {
+      "epoch": 31.11,
+      "eval_loss": 1.9086456298828125,
+      "eval_runtime": 0.4351,
+      "eval_samples_per_second": 62.057,
+      "eval_steps_per_second": 9.194,
+      "step": 420
+    },
+    {
+      "epoch": 31.48,
+      "grad_norm": 0.8392044305801392,
+      "learning_rate": 0.00010476923076923076,
+      "loss": 0.2754,
+      "step": 425
+    },
+    {
+      "epoch": 31.85,
+      "grad_norm": 0.9244445562362671,
+      "learning_rate": 0.00010246153846153844,
+      "loss": 0.2899,
+      "step": 430
+    },
+    {
+      "epoch": 32.22,
+      "grad_norm": 0.7770041227340698,
+      "learning_rate": 0.00010015384615384614,
+      "loss": 0.3074,
+      "step": 435
+    },
+    {
+      "epoch": 32.59,
+      "grad_norm": 0.9049687385559082,
+      "learning_rate": 9.784615384615383e-05,
+      "loss": 0.2837,
+      "step": 440
+    },
+    {
+      "epoch": 32.59,
+      "eval_loss": 1.9283045530319214,
+      "eval_runtime": 0.436,
+      "eval_samples_per_second": 61.931,
+      "eval_steps_per_second": 9.175,
+      "step": 440
+    },
+    {
+      "epoch": 32.96,
+      "grad_norm": 0.9280600547790527,
+      "learning_rate": 9.553846153846153e-05,
+      "loss": 0.2832,
+      "step": 445
+    },
+    {
+      "epoch": 33.33,
+      "grad_norm": 1.0627598762512207,
+      "learning_rate": 9.323076923076921e-05,
+      "loss": 0.3019,
+      "step": 450
+    },
+    {
+      "epoch": 33.7,
+      "grad_norm": 0.8776496052742004,
+      "learning_rate": 9.092307692307691e-05,
+      "loss": 0.2691,
+      "step": 455
+    },
+    {
+      "epoch": 34.07,
+      "grad_norm": 1.0023120641708374,
+      "learning_rate": 8.861538461538462e-05,
+      "loss": 0.2908,
+      "step": 460
+    },
+    {
+      "epoch": 34.07,
+      "eval_loss": 1.9639641046524048,
+      "eval_runtime": 0.4354,
+      "eval_samples_per_second": 62.01,
+      "eval_steps_per_second": 9.187,
+      "step": 460
+    },
+    {
+      "epoch": 34.44,
+      "grad_norm": 0.7977310419082642,
+      "learning_rate": 8.63076923076923e-05,
+      "loss": 0.2448,
+      "step": 465
+    },
+    {
+      "epoch": 34.81,
+      "grad_norm": 0.941286563873291,
+      "learning_rate": 8.4e-05,
+      "loss": 0.3116,
+      "step": 470
+    },
+    {
+      "epoch": 35.19,
+      "grad_norm": 0.8777848482131958,
+      "learning_rate": 8.169230769230768e-05,
+      "loss": 0.297,
+      "step": 475
+    },
+    {
+      "epoch": 35.56,
+      "grad_norm": 1.213904857635498,
+      "learning_rate": 7.938461538461539e-05,
+      "loss": 0.2789,
+      "step": 480
+    },
+    {
+      "epoch": 35.56,
+      "eval_loss": 1.9745168685913086,
+      "eval_runtime": 0.4348,
+      "eval_samples_per_second": 62.101,
+      "eval_steps_per_second": 9.2,
+      "step": 480
+    },
+    {
+      "epoch": 35.93,
+      "grad_norm": 0.9805024266242981,
+      "learning_rate": 7.707692307692306e-05,
+      "loss": 0.2894,
+      "step": 485
+    },
+    {
+      "epoch": 36.3,
+      "grad_norm": 0.829560399055481,
+      "learning_rate": 7.476923076923077e-05,
+      "loss": 0.2597,
+      "step": 490
+    },
+    {
+      "epoch": 36.67,
+      "grad_norm": 1.1455888748168945,
+      "learning_rate": 7.246153846153846e-05,
+      "loss": 0.3081,
+      "step": 495
+    },
+    {
+      "epoch": 37.04,
+      "grad_norm": 0.9539237022399902,
+      "learning_rate": 7.015384615384615e-05,
+      "loss": 0.2773,
+      "step": 500
+    },
+    {
+      "epoch": 37.04,
+      "eval_loss": 1.9331037998199463,
+      "eval_runtime": 0.4366,
+      "eval_samples_per_second": 61.836,
+      "eval_steps_per_second": 9.161,
+      "step": 500
+    },
+    {
+      "epoch": 37.41,
+      "grad_norm": 0.8768445253372192,
+      "learning_rate": 6.784615384615383e-05,
+      "loss": 0.2595,
+      "step": 505
+    },
+    {
+      "epoch": 37.78,
+      "grad_norm": 0.9345956444740295,
+      "learning_rate": 6.553846153846154e-05,
+      "loss": 0.287,
+      "step": 510
+    },
+    {
+      "epoch": 38.15,
+      "grad_norm": 1.006366491317749,
+      "learning_rate": 6.323076923076923e-05,
+      "loss": 0.2988,
+      "step": 515
+    },
+    {
+      "epoch": 38.52,
+      "grad_norm": 0.999914824962616,
+      "learning_rate": 6.0923076923076916e-05,
+      "loss": 0.2734,
+      "step": 520
+    },
+    {
+      "epoch": 38.52,
+      "eval_loss": 1.9785383939743042,
+      "eval_runtime": 0.4355,
+      "eval_samples_per_second": 62.002,
+      "eval_steps_per_second": 9.186,
+      "step": 520
+    },
+    {
+      "epoch": 38.89,
+      "grad_norm": 0.9857865571975708,
+      "learning_rate": 5.8615384615384606e-05,
+      "loss": 0.288,
+      "step": 525
+    },
+    {
+      "epoch": 39.26,
+      "grad_norm": 1.0521814823150635,
+      "learning_rate": 5.63076923076923e-05,
+      "loss": 0.2844,
+      "step": 530
+    },
+    {
+      "epoch": 39.63,
+      "grad_norm": 0.8729674220085144,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 0.2641,
+      "step": 535
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 1.0058977603912354,
+      "learning_rate": 5.169230769230769e-05,
+      "loss": 0.2916,
+      "step": 540
+    },
+    {
+      "epoch": 40.0,
+      "eval_loss": 2.0248498916625977,
+      "eval_runtime": 0.4342,
+      "eval_samples_per_second": 62.187,
+      "eval_steps_per_second": 9.213,
+      "step": 540
+    },
+    {
+      "epoch": 40.37,
+      "grad_norm": 1.0700985193252563,
+      "learning_rate": 4.938461538461538e-05,
+      "loss": 0.2675,
+      "step": 545
+    },
+    {
+      "epoch": 40.74,
+      "grad_norm": 0.9227583408355713,
+      "learning_rate": 4.707692307692307e-05,
+      "loss": 0.2607,
+      "step": 550
+    },
+    {
+      "epoch": 41.11,
+      "grad_norm": 0.658815324306488,
+      "learning_rate": 4.476923076923076e-05,
+      "loss": 0.2806,
+      "step": 555
+    },
+    {
+      "epoch": 41.48,
+      "grad_norm": 0.849854052066803,
+      "learning_rate": 4.246153846153846e-05,
+      "loss": 0.2703,
+      "step": 560
+    },
+    {
+      "epoch": 41.48,
+      "eval_loss": 1.9876518249511719,
+      "eval_runtime": 0.4356,
+      "eval_samples_per_second": 61.988,
+      "eval_steps_per_second": 9.183,
+      "step": 560
+    },
+    {
+      "epoch": 41.85,
+      "grad_norm": 1.0666935443878174,
+      "learning_rate": 4.015384615384615e-05,
+      "loss": 0.2946,
+      "step": 565
+    },
+    {
+      "epoch": 42.22,
+      "grad_norm": 1.0425372123718262,
+      "learning_rate": 3.784615384615384e-05,
+      "loss": 0.2973,
+      "step": 570
+    },
+    {
+      "epoch": 42.59,
+      "grad_norm": 1.135412335395813,
+      "learning_rate": 3.553846153846153e-05,
+      "loss": 0.2846,
+      "step": 575
+    },
+    {
+      "epoch": 42.96,
+      "grad_norm": 0.9318748712539673,
+      "learning_rate": 3.323076923076923e-05,
+      "loss": 0.2608,
+      "step": 580
+    },
+    {
+      "epoch": 42.96,
+      "eval_loss": 2.014052391052246,
+      "eval_runtime": 0.4365,
+      "eval_samples_per_second": 61.863,
+      "eval_steps_per_second": 9.165,
+      "step": 580
+    },
+    {
+      "epoch": 43.33,
+      "grad_norm": 0.740696370601654,
+      "learning_rate": 3.092307692307692e-05,
+      "loss": 0.2745,
+      "step": 585
+    },
+    {
+      "epoch": 43.7,
+      "grad_norm": 1.0200663805007935,
+      "learning_rate": 2.8615384615384615e-05,
+      "loss": 0.2722,
+      "step": 590
+    },
+    {
+      "epoch": 44.07,
+      "grad_norm": 0.9688575863838196,
+      "learning_rate": 2.6307692307692304e-05,
+      "loss": 0.2811,
+      "step": 595
+    },
+    {
+      "epoch": 44.44,
+      "grad_norm": 1.2867329120635986,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 0.262,
+      "step": 600
+    },
+    {
+      "epoch": 44.44,
+      "eval_loss": 2.0364649295806885,
+      "eval_runtime": 0.4343,
+      "eval_samples_per_second": 62.168,
+      "eval_steps_per_second": 9.21,
+      "step": 600
+    },
+    {
+      "epoch": 44.81,
+      "grad_norm": 1.0685030221939087,
+      "learning_rate": 2.169230769230769e-05,
+      "loss": 0.2679,
+      "step": 605
+    },
+    {
+      "epoch": 45.19,
+      "grad_norm": 0.9567782282829285,
+      "learning_rate": 1.9384615384615383e-05,
+      "loss": 0.2855,
+      "step": 610
+    },
+    {
+      "epoch": 45.56,
+      "grad_norm": 0.8821234703063965,
+      "learning_rate": 1.7076923076923076e-05,
+      "loss": 0.2807,
+      "step": 615
+    },
+    {
+      "epoch": 45.93,
+      "grad_norm": 1.212229609489441,
+      "learning_rate": 1.4769230769230768e-05,
+      "loss": 0.2767,
+      "step": 620
+    },
+    {
+      "epoch": 45.93,
+      "eval_loss": 2.0518877506256104,
+      "eval_runtime": 0.4334,
+      "eval_samples_per_second": 62.291,
+      "eval_steps_per_second": 9.228,
+      "step": 620
+    },
+    {
+      "epoch": 46.3,
+      "grad_norm": 1.0351111888885498,
+      "learning_rate": 1.2461538461538461e-05,
+      "loss": 0.2699,
+      "step": 625
+    },
+    {
+      "epoch": 46.67,
+      "grad_norm": 1.1969187259674072,
+      "learning_rate": 1.0153846153846152e-05,
+      "loss": 0.277,
+      "step": 630
+    },
+    {
+      "epoch": 47.04,
+      "grad_norm": 0.7708118557929993,
+      "learning_rate": 7.846153846153845e-06,
+      "loss": 0.2637,
+      "step": 635
+    },
+    {
+      "epoch": 47.41,
+      "grad_norm": 0.8004487752914429,
+      "learning_rate": 5.5384615384615385e-06,
+      "loss": 0.2642,
+      "step": 640
+    },
+    {
+      "epoch": 47.41,
+      "eval_loss": 2.0601537227630615,
+      "eval_runtime": 0.4355,
+      "eval_samples_per_second": 61.996,
+      "eval_steps_per_second": 9.185,
+      "step": 640
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 650,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 20,
+  "total_flos": 5533698562129920.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a957e5a99d0748cd66c2f581dde5af79e6b3afeea680a16092a23641c1e986c1
+size 5048