Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-439/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: heat_transfer_sft_10000_mcq_u_1epoch
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# heat_transfer_sft_10000_mcq_u_1epoch
+
+This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) on the heat_transfer_10000_mcq_u dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0018
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 10
+- eval_batch_size: 10
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 20
+- total_eval_batch_size: 20
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0076        | 0.1139 | 50   | 0.0059          |
+| 0.0054        | 0.2278 | 100  | 0.0050          |
+| 0.0041        | 0.3417 | 150  | 0.0036          |
+| 0.0026        | 0.4556 | 200  | 0.0025          |
+| 0.0025        | 0.5695 | 250  | 0.0024          |
+| 0.0022        | 0.6834 | 300  | 0.0021          |
+| 0.0022        | 0.7973 | 350  | 0.0019          |
+| 0.0021        | 0.9112 | 400  | 0.0018          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda8c803633b25a5b0c403e940670aeda02f88fc350ff05bafda66aa42060858
+size 114106856

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.0018119927262887359,
+    "eval_runtime": 122.2911,
+    "eval_samples_per_second": 7.965,
+    "eval_steps_per_second": 0.401,
+    "total_flos": 9.38862713986089e+17,
+    "train_loss": 0.018706909701194197,
+    "train_runtime": 4591.0233,
+    "train_samples_per_second": 1.909,
+    "train_steps_per_second": 0.096
+}

checkpoint-439/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+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 0.12.0

checkpoint-439/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-439/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda8c803633b25a5b0c403e940670aeda02f88fc350ff05bafda66aa42060858
+size 114106856

checkpoint-439/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea17c1a38562ce723f6a941f7f5649066b878f68f6773ce958feade8a3facff
+size 228536930

checkpoint-439/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91bd7f619e4cd37883f469c08e90105c4d218fd82ffc43ae58fa9fdbcc37fce5
+size 14512

checkpoint-439/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0a7593f9ab52bf47328c6d50954dce1fcd69866aa6f5f35851aef7f7af3899
+size 14512

checkpoint-439/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a29716f458fcc3146637b46cd4b22e43f4b0d5a9e810b73a4f20c6912d0238
+size 1064

checkpoint-439/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-439/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

checkpoint-439/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 439,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04555808656036447,
+      "grad_norm": 0.5296587944030762,
+      "learning_rate": 9.948875483893885e-05,
+      "loss": 0.3433,
+      "step": 20
+    },
+    {
+      "epoch": 0.09111617312072894,
+      "grad_norm": 0.042843956500291824,
+      "learning_rate": 9.796547422034374e-05,
+      "loss": 0.0076,
+      "step": 40
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "eval_loss": 0.005896100774407387,
+      "eval_runtime": 122.4009,
+      "eval_samples_per_second": 7.957,
+      "eval_steps_per_second": 0.4,
+      "step": 50
+    },
+    {
+      "epoch": 0.1366742596810934,
+      "grad_norm": 0.04506906867027283,
+      "learning_rate": 9.546130893802246e-05,
+      "loss": 0.006,
+      "step": 60
+    },
+    {
+      "epoch": 0.18223234624145787,
+      "grad_norm": 0.04249206930398941,
+      "learning_rate": 9.20274686872984e-05,
+      "loss": 0.006,
+      "step": 80
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "grad_norm": 0.034582458436489105,
+      "learning_rate": 8.773417483665309e-05,
+      "loss": 0.0054,
+      "step": 100
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "eval_loss": 0.004958716221153736,
+      "eval_runtime": 122.3931,
+      "eval_samples_per_second": 7.958,
+      "eval_steps_per_second": 0.4,
+      "step": 100
+    },
+    {
+      "epoch": 0.2733485193621868,
+      "grad_norm": 0.09121271967887878,
+      "learning_rate": 8.266922441433284e-05,
+      "loss": 0.0043,
+      "step": 120
+    },
+    {
+      "epoch": 0.31890660592255127,
+      "grad_norm": 0.025009050965309143,
+      "learning_rate": 7.693619467611464e-05,
+      "loss": 0.0041,
+      "step": 140
+    },
+    {
+      "epoch": 0.3416856492027335,
+      "eval_loss": 0.0036018535029143095,
+      "eval_runtime": 122.4383,
+      "eval_samples_per_second": 7.955,
+      "eval_steps_per_second": 0.4,
+      "step": 150
+    },
+    {
+      "epoch": 0.36446469248291574,
+      "grad_norm": 0.06171397864818573,
+      "learning_rate": 7.065232497047384e-05,
+      "loss": 0.0036,
+      "step": 160
+    },
+    {
+      "epoch": 0.41002277904328016,
+      "grad_norm": 0.0585937425494194,
+      "learning_rate": 6.394611921660036e-05,
+      "loss": 0.003,
+      "step": 180
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "grad_norm": 0.03573513403534889,
+      "learning_rate": 5.695471802412413e-05,
+      "loss": 0.0026,
+      "step": 200
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "eval_loss": 0.0025479402393102646,
+      "eval_runtime": 122.4406,
+      "eval_samples_per_second": 7.955,
+      "eval_steps_per_second": 0.4,
+      "step": 200
+    },
+    {
+      "epoch": 0.5011389521640092,
+      "grad_norm": 0.08403529226779938,
+      "learning_rate": 4.982109419419277e-05,
+      "loss": 0.0023,
+      "step": 220
+    },
+    {
+      "epoch": 0.5466970387243736,
+      "grad_norm": 0.08128103613853455,
+      "learning_rate": 4.269112895336161e-05,
+      "loss": 0.0025,
+      "step": 240
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "eval_loss": 0.002369565423578024,
+      "eval_runtime": 122.4121,
+      "eval_samples_per_second": 7.957,
+      "eval_steps_per_second": 0.4,
+      "step": 250
+    },
+    {
+      "epoch": 0.592255125284738,
+      "grad_norm": 0.04797542467713356,
+      "learning_rate": 3.5710628710747e-05,
+      "loss": 0.0025,
+      "step": 260
+    },
+    {
+      "epoch": 0.6378132118451025,
+      "grad_norm": 0.041951198130846024,
+      "learning_rate": 2.9022343345181846e-05,
+      "loss": 0.0022,
+      "step": 280
+    },
+    {
+      "epoch": 0.683371298405467,
+      "grad_norm": 0.03911906108260155,
+      "learning_rate": 2.276304699782381e-05,
+      "loss": 0.0022,
+      "step": 300
+    },
+    {
+      "epoch": 0.683371298405467,
+      "eval_loss": 0.0020905383862555027,
+      "eval_runtime": 122.4348,
+      "eval_samples_per_second": 7.955,
+      "eval_steps_per_second": 0.4,
+      "step": 300
+    },
+    {
+      "epoch": 0.7289293849658315,
+      "grad_norm": 0.07351183891296387,
+      "learning_rate": 1.7060741067442288e-05,
+      "loss": 0.0021,
+      "step": 320
+    },
+    {
+      "epoch": 0.7744874715261959,
+      "grad_norm": 0.06717297434806824,
+      "learning_rate": 1.2032036606589175e-05,
+      "loss": 0.0022,
+      "step": 340
+    },
+    {
+      "epoch": 0.7972665148063781,
+      "eval_loss": 0.0018556159920990467,
+      "eval_runtime": 122.4481,
+      "eval_samples_per_second": 7.954,
+      "eval_steps_per_second": 0.4,
+      "step": 350
+    },
+    {
+      "epoch": 0.8200455580865603,
+      "grad_norm": 0.03857114166021347,
+      "learning_rate": 7.779769648145201e-06,
+      "loss": 0.0015,
+      "step": 360
+    },
+    {
+      "epoch": 0.8656036446469249,
+      "grad_norm": 0.036848343908786774,
+      "learning_rate": 4.390898228352131e-06,
+      "loss": 0.0018,
+      "step": 380
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "grad_norm": 0.09445371478796005,
+      "learning_rate": 1.9347241118030823e-06,
+      "loss": 0.0021,
+      "step": 400
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "eval_loss": 0.0018473172094672918,
+      "eval_runtime": 122.4479,
+      "eval_samples_per_second": 7.954,
+      "eval_steps_per_second": 0.4,
+      "step": 400
+    },
+    {
+      "epoch": 0.9567198177676538,
+      "grad_norm": 0.04989920184016228,
+      "learning_rate": 4.614755837704321e-07,
+      "loss": 0.0018,
+      "step": 420
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 439,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.38862713986089e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-439/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7cc6ee75df7fb14a7358257971adef7e4d552407d4eda98c335735b6aa2b9c3
+size 5496

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.0018119927262887359,
+    "eval_runtime": 122.2911,
+    "eval_samples_per_second": 7.965,
+    "eval_steps_per_second": 0.401
+}

runs/Jan31_20-42-02_ctua-interactive-pod-1/events.out.tfevents.1738356727.ctua-interactive-pod-1.450.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7896b62620f42d4a308e7e47d2cefb79d8687c04458bc3bd858c0de991bbb559
+size 12251

runs/Jan31_20-42-02_ctua-interactive-pod-1/events.out.tfevents.1738361795.ctua-interactive-pod-1.450.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba599d834342d9b9d89017ddf7bc6c413071def463202bf02b4041e59d7dff2
+size 359

runs/Jan31_23-00-44_ctua-interactive-pod-1/events.out.tfevents.1738364461.ctua-interactive-pod-1.1134.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4127842414c88432e79912ed1f5da0bbc96c537bc76a4e5c4b0676acc95353
+size 12251

runs/Jan31_23-00-44_ctua-interactive-pod-1/events.out.tfevents.1738369175.ctua-interactive-pod-1.1134.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce8cd9dcb50c059287df777089793efc6b1b33261c5260f07e85903c222c709
+size 359

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 9.38862713986089e+17,
+    "train_loss": 0.018706909701194197,
+    "train_runtime": 4591.0233,
+    "train_samples_per_second": 1.909,
+    "train_steps_per_second": 0.096
+}

trainer_log.jsonl

@@ -0,0 +1,30 @@
+{"current_steps": 20, "total_steps": 439, "loss": 0.3433, "lr": 9.948875483893885e-05, "epoch": 0.04555808656036447, "percentage": 4.56, "elapsed_time": "0:02:45", "remaining_time": "0:57:54"}
+{"current_steps": 40, "total_steps": 439, "loss": 0.0076, "lr": 9.796547422034374e-05, "epoch": 0.09111617312072894, "percentage": 9.11, "elapsed_time": "0:05:30", "remaining_time": "0:54:52"}
+{"current_steps": 50, "total_steps": 439, "eval_loss": 0.005896100774407387, "epoch": 0.11389521640091116, "percentage": 11.39, "elapsed_time": "0:08:54", "remaining_time": "1:09:18"}
+{"current_steps": 60, "total_steps": 439, "loss": 0.006, "lr": 9.546130893802246e-05, "epoch": 0.1366742596810934, "percentage": 13.67, "elapsed_time": "0:10:16", "remaining_time": "1:04:57"}
+{"current_steps": 80, "total_steps": 439, "loss": 0.006, "lr": 9.20274686872984e-05, "epoch": 0.18223234624145787, "percentage": 18.22, "elapsed_time": "0:13:01", "remaining_time": "0:58:28"}
+{"current_steps": 100, "total_steps": 439, "loss": 0.0054, "lr": 8.773417483665309e-05, "epoch": 0.22779043280182232, "percentage": 22.78, "elapsed_time": "0:15:45", "remaining_time": "0:53:25"}
+{"current_steps": 100, "total_steps": 439, "eval_loss": 0.004958716221153736, "epoch": 0.22779043280182232, "percentage": 22.78, "elapsed_time": "0:17:47", "remaining_time": "1:00:20"}
+{"current_steps": 120, "total_steps": 439, "loss": 0.0043, "lr": 8.266922441433284e-05, "epoch": 0.2733485193621868, "percentage": 27.33, "elapsed_time": "0:20:31", "remaining_time": "0:54:34"}
+{"current_steps": 140, "total_steps": 439, "loss": 0.0041, "lr": 7.693619467611464e-05, "epoch": 0.31890660592255127, "percentage": 31.89, "elapsed_time": "0:23:16", "remaining_time": "0:49:42"}
+{"current_steps": 150, "total_steps": 439, "eval_loss": 0.0036018535029143095, "epoch": 0.3416856492027335, "percentage": 34.17, "elapsed_time": "0:26:40", "remaining_time": "0:51:24"}
+{"current_steps": 160, "total_steps": 439, "loss": 0.0036, "lr": 7.065232497047384e-05, "epoch": 0.36446469248291574, "percentage": 36.45, "elapsed_time": "0:28:03", "remaining_time": "0:48:55"}
+{"current_steps": 180, "total_steps": 439, "loss": 0.003, "lr": 6.394611921660036e-05, "epoch": 0.41002277904328016, "percentage": 41.0, "elapsed_time": "0:30:48", "remaining_time": "0:44:19"}
+{"current_steps": 200, "total_steps": 439, "loss": 0.0026, "lr": 5.695471802412413e-05, "epoch": 0.45558086560364464, "percentage": 45.56, "elapsed_time": "0:33:32", "remaining_time": "0:40:04"}
+{"current_steps": 200, "total_steps": 439, "eval_loss": 0.0025479402393102646, "epoch": 0.45558086560364464, "percentage": 45.56, "elapsed_time": "0:35:34", "remaining_time": "0:42:30"}
+{"current_steps": 220, "total_steps": 439, "loss": 0.0023, "lr": 4.982109419419277e-05, "epoch": 0.5011389521640092, "percentage": 50.11, "elapsed_time": "0:38:19", "remaining_time": "0:38:08"}
+{"current_steps": 240, "total_steps": 439, "loss": 0.0025, "lr": 4.269112895336161e-05, "epoch": 0.5466970387243736, "percentage": 54.67, "elapsed_time": "0:41:03", "remaining_time": "0:34:02"}
+{"current_steps": 250, "total_steps": 439, "eval_loss": 0.002369565423578024, "epoch": 0.5694760820045558, "percentage": 56.95, "elapsed_time": "0:44:28", "remaining_time": "0:33:37"}
+{"current_steps": 260, "total_steps": 439, "loss": 0.0025, "lr": 3.5710628710747e-05, "epoch": 0.592255125284738, "percentage": 59.23, "elapsed_time": "0:45:49", "remaining_time": "0:31:33"}
+{"current_steps": 280, "total_steps": 439, "loss": 0.0022, "lr": 2.9022343345181846e-05, "epoch": 0.6378132118451025, "percentage": 63.78, "elapsed_time": "0:48:33", "remaining_time": "0:27:34"}
+{"current_steps": 300, "total_steps": 439, "loss": 0.0022, "lr": 2.276304699782381e-05, "epoch": 0.683371298405467, "percentage": 68.34, "elapsed_time": "0:51:18", "remaining_time": "0:23:46"}
+{"current_steps": 300, "total_steps": 439, "eval_loss": 0.0020905383862555027, "epoch": 0.683371298405467, "percentage": 68.34, "elapsed_time": "0:53:20", "remaining_time": "0:24:43"}
+{"current_steps": 320, "total_steps": 439, "loss": 0.0021, "lr": 1.7060741067442288e-05, "epoch": 0.7289293849658315, "percentage": 72.89, "elapsed_time": "0:56:05", "remaining_time": "0:20:51"}
+{"current_steps": 340, "total_steps": 439, "loss": 0.0022, "lr": 1.2032036606589175e-05, "epoch": 0.7744874715261959, "percentage": 77.45, "elapsed_time": "0:58:50", "remaining_time": "0:17:07"}
+{"current_steps": 350, "total_steps": 439, "eval_loss": 0.0018556159920990467, "epoch": 0.7972665148063781, "percentage": 79.73, "elapsed_time": "1:02:15", "remaining_time": "0:15:49"}
+{"current_steps": 360, "total_steps": 439, "loss": 0.0015, "lr": 7.779769648145201e-06, "epoch": 0.8200455580865603, "percentage": 82.0, "elapsed_time": "1:03:37", "remaining_time": "0:13:57"}
+{"current_steps": 380, "total_steps": 439, "loss": 0.0018, "lr": 4.390898228352131e-06, "epoch": 0.8656036446469249, "percentage": 86.56, "elapsed_time": "1:06:21", "remaining_time": "0:10:18"}
+{"current_steps": 400, "total_steps": 439, "loss": 0.0021, "lr": 1.9347241118030823e-06, "epoch": 0.9111617312072893, "percentage": 91.12, "elapsed_time": "1:09:05", "remaining_time": "0:06:44"}
+{"current_steps": 400, "total_steps": 439, "eval_loss": 0.0018473172094672918, "epoch": 0.9111617312072893, "percentage": 91.12, "elapsed_time": "1:11:08", "remaining_time": "0:06:56"}
+{"current_steps": 420, "total_steps": 439, "loss": 0.0018, "lr": 4.614755837704321e-07, "epoch": 0.9567198177676538, "percentage": 95.67, "elapsed_time": "1:13:53", "remaining_time": "0:03:20"}
+{"current_steps": 439, "total_steps": 439, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:16:29", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,253 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 439,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04555808656036447,
+      "grad_norm": 0.5296587944030762,
+      "learning_rate": 9.948875483893885e-05,
+      "loss": 0.3433,
+      "step": 20
+    },
+    {
+      "epoch": 0.09111617312072894,
+      "grad_norm": 0.042843956500291824,
+      "learning_rate": 9.796547422034374e-05,
+      "loss": 0.0076,
+      "step": 40
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "eval_loss": 0.005896100774407387,
+      "eval_runtime": 122.4009,
+      "eval_samples_per_second": 7.957,
+      "eval_steps_per_second": 0.4,
+      "step": 50
+    },
+    {
+      "epoch": 0.1366742596810934,
+      "grad_norm": 0.04506906867027283,
+      "learning_rate": 9.546130893802246e-05,
+      "loss": 0.006,
+      "step": 60
+    },
+    {
+      "epoch": 0.18223234624145787,
+      "grad_norm": 0.04249206930398941,
+      "learning_rate": 9.20274686872984e-05,
+      "loss": 0.006,
+      "step": 80
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "grad_norm": 0.034582458436489105,
+      "learning_rate": 8.773417483665309e-05,
+      "loss": 0.0054,
+      "step": 100
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "eval_loss": 0.004958716221153736,
+      "eval_runtime": 122.3931,
+      "eval_samples_per_second": 7.958,
+      "eval_steps_per_second": 0.4,
+      "step": 100
+    },
+    {
+      "epoch": 0.2733485193621868,
+      "grad_norm": 0.09121271967887878,
+      "learning_rate": 8.266922441433284e-05,
+      "loss": 0.0043,
+      "step": 120
+    },
+    {
+      "epoch": 0.31890660592255127,
+      "grad_norm": 0.025009050965309143,
+      "learning_rate": 7.693619467611464e-05,
+      "loss": 0.0041,
+      "step": 140
+    },
+    {
+      "epoch": 0.3416856492027335,
+      "eval_loss": 0.0036018535029143095,
+      "eval_runtime": 122.4383,
+      "eval_samples_per_second": 7.955,
+      "eval_steps_per_second": 0.4,
+      "step": 150
+    },
+    {
+      "epoch": 0.36446469248291574,
+      "grad_norm": 0.06171397864818573,
+      "learning_rate": 7.065232497047384e-05,
+      "loss": 0.0036,
+      "step": 160
+    },
+    {
+      "epoch": 0.41002277904328016,
+      "grad_norm": 0.0585937425494194,
+      "learning_rate": 6.394611921660036e-05,
+      "loss": 0.003,
+      "step": 180
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "grad_norm": 0.03573513403534889,
+      "learning_rate": 5.695471802412413e-05,
+      "loss": 0.0026,
+      "step": 200
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "eval_loss": 0.0025479402393102646,
+      "eval_runtime": 122.4406,
+      "eval_samples_per_second": 7.955,
+      "eval_steps_per_second": 0.4,
+      "step": 200
+    },
+    {
+      "epoch": 0.5011389521640092,
+      "grad_norm": 0.08403529226779938,
+      "learning_rate": 4.982109419419277e-05,
+      "loss": 0.0023,
+      "step": 220
+    },
+    {
+      "epoch": 0.5466970387243736,
+      "grad_norm": 0.08128103613853455,
+      "learning_rate": 4.269112895336161e-05,
+      "loss": 0.0025,
+      "step": 240
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "eval_loss": 0.002369565423578024,
+      "eval_runtime": 122.4121,
+      "eval_samples_per_second": 7.957,
+      "eval_steps_per_second": 0.4,
+      "step": 250
+    },
+    {
+      "epoch": 0.592255125284738,
+      "grad_norm": 0.04797542467713356,
+      "learning_rate": 3.5710628710747e-05,
+      "loss": 0.0025,
+      "step": 260
+    },
+    {
+      "epoch": 0.6378132118451025,
+      "grad_norm": 0.041951198130846024,
+      "learning_rate": 2.9022343345181846e-05,
+      "loss": 0.0022,
+      "step": 280
+    },
+    {
+      "epoch": 0.683371298405467,
+      "grad_norm": 0.03911906108260155,
+      "learning_rate": 2.276304699782381e-05,
+      "loss": 0.0022,
+      "step": 300
+    },
+    {
+      "epoch": 0.683371298405467,
+      "eval_loss": 0.0020905383862555027,
+      "eval_runtime": 122.4348,
+      "eval_samples_per_second": 7.955,
+      "eval_steps_per_second": 0.4,
+      "step": 300
+    },
+    {
+      "epoch": 0.7289293849658315,
+      "grad_norm": 0.07351183891296387,
+      "learning_rate": 1.7060741067442288e-05,
+      "loss": 0.0021,
+      "step": 320
+    },
+    {
+      "epoch": 0.7744874715261959,
+      "grad_norm": 0.06717297434806824,
+      "learning_rate": 1.2032036606589175e-05,
+      "loss": 0.0022,
+      "step": 340
+    },
+    {
+      "epoch": 0.7972665148063781,
+      "eval_loss": 0.0018556159920990467,
+      "eval_runtime": 122.4481,
+      "eval_samples_per_second": 7.954,
+      "eval_steps_per_second": 0.4,
+      "step": 350
+    },
+    {
+      "epoch": 0.8200455580865603,
+      "grad_norm": 0.03857114166021347,
+      "learning_rate": 7.779769648145201e-06,
+      "loss": 0.0015,
+      "step": 360
+    },
+    {
+      "epoch": 0.8656036446469249,
+      "grad_norm": 0.036848343908786774,
+      "learning_rate": 4.390898228352131e-06,
+      "loss": 0.0018,
+      "step": 380
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "grad_norm": 0.09445371478796005,
+      "learning_rate": 1.9347241118030823e-06,
+      "loss": 0.0021,
+      "step": 400
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "eval_loss": 0.0018473172094672918,
+      "eval_runtime": 122.4479,
+      "eval_samples_per_second": 7.954,
+      "eval_steps_per_second": 0.4,
+      "step": 400
+    },
+    {
+      "epoch": 0.9567198177676538,
+      "grad_norm": 0.04989920184016228,
+      "learning_rate": 4.614755837704321e-07,
+      "loss": 0.0018,
+      "step": 420
+    },
+    {
+      "epoch": 1.0,
+      "step": 439,
+      "total_flos": 9.38862713986089e+17,
+      "train_loss": 0.018706909701194197,
+      "train_runtime": 4591.0233,
+      "train_samples_per_second": 1.909,
+      "train_steps_per_second": 0.096
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 439,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.38862713986089e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7cc6ee75df7fb14a7358257971adef7e4d552407d4eda98c335735b6aa2b9c3
+size 5496