Upload sft-r4-e3

.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-471/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/aifs4su/yaodong/models/google/gemma-3-1b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592e4f62d4842e83c1f3115f9bb77a1aee3d14d591f56d07544bcdeea2af42d8
+size 13093200

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.2627781654203597e+17,
+    "train_loss": 1.0978564871850793,
+    "train_runtime": 364.5287,
+    "train_samples_per_second": 165.378,
+    "train_steps_per_second": 1.292
+}

checkpoint-471/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /aifs4su/yaodong/models/google/gemma-3-1b-it
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

checkpoint-471/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/aifs4su/yaodong/models/google/gemma-3-1b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-471/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592e4f62d4842e83c1f3115f9bb77a1aee3d14d591f56d07544bcdeea2af42d8
+size 13093200

checkpoint-471/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-471/special_tokens_map.json

@@ -0,0 +1,42 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-471/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-471/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-471/trainer_state.json

@@ -0,0 +1,363 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 471,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06369426751592357,
+      "grad_norm": 6.031618595123291,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.2979,
+      "step": 10
+    },
+    {
+      "epoch": 0.12738853503184713,
+      "grad_norm": 5.124261379241943,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 2.8325,
+      "step": 20
+    },
+    {
+      "epoch": 0.1910828025477707,
+      "grad_norm": 2.4147489070892334,
+      "learning_rate": 6.041666666666667e-05,
+      "loss": 1.716,
+      "step": 30
+    },
+    {
+      "epoch": 0.25477707006369427,
+      "grad_norm": 1.0314959287643433,
+      "learning_rate": 8.125000000000001e-05,
+      "loss": 1.2752,
+      "step": 40
+    },
+    {
+      "epoch": 0.3184713375796178,
+      "grad_norm": 0.5906504988670349,
+      "learning_rate": 9.999862102299873e-05,
+      "loss": 1.207,
+      "step": 50
+    },
+    {
+      "epoch": 0.3821656050955414,
+      "grad_norm": 0.43713438510894775,
+      "learning_rate": 9.983323579940351e-05,
+      "loss": 1.1241,
+      "step": 60
+    },
+    {
+      "epoch": 0.445859872611465,
+      "grad_norm": 0.40896832942962646,
+      "learning_rate": 9.939310009499348e-05,
+      "loss": 1.0958,
+      "step": 70
+    },
+    {
+      "epoch": 0.5095541401273885,
+      "grad_norm": 0.31001320481300354,
+      "learning_rate": 9.868064055324204e-05,
+      "loss": 1.059,
+      "step": 80
+    },
+    {
+      "epoch": 0.5732484076433121,
+      "grad_norm": 0.3313826024532318,
+      "learning_rate": 9.769978524742229e-05,
+      "loss": 1.0795,
+      "step": 90
+    },
+    {
+      "epoch": 0.6369426751592356,
+      "grad_norm": 0.3064286708831787,
+      "learning_rate": 9.645594202357439e-05,
+      "loss": 1.0693,
+      "step": 100
+    },
+    {
+      "epoch": 0.7006369426751592,
+      "grad_norm": 0.3159961402416229,
+      "learning_rate": 9.495596868489588e-05,
+      "loss": 1.0465,
+      "step": 110
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "grad_norm": 0.39494845271110535,
+      "learning_rate": 9.320813518194084e-05,
+      "loss": 1.0324,
+      "step": 120
+    },
+    {
+      "epoch": 0.8280254777070064,
+      "grad_norm": 0.44708824157714844,
+      "learning_rate": 9.122207801708802e-05,
+      "loss": 1.0234,
+      "step": 130
+    },
+    {
+      "epoch": 0.89171974522293,
+      "grad_norm": 0.41689348220825195,
+      "learning_rate": 8.900874711466435e-05,
+      "loss": 1.0376,
+      "step": 140
+    },
+    {
+      "epoch": 0.9554140127388535,
+      "grad_norm": 0.44199317693710327,
+      "learning_rate": 8.658034544965003e-05,
+      "loss": 0.9996,
+      "step": 150
+    },
+    {
+      "epoch": 1.019108280254777,
+      "grad_norm": 0.4607829451560974,
+      "learning_rate": 8.395026176781627e-05,
+      "loss": 0.9987,
+      "step": 160
+    },
+    {
+      "epoch": 1.0828025477707006,
+      "grad_norm": 0.47777435183525085,
+      "learning_rate": 8.113299676823614e-05,
+      "loss": 0.9745,
+      "step": 170
+    },
+    {
+      "epoch": 1.1464968152866242,
+      "grad_norm": 0.48650094866752625,
+      "learning_rate": 7.814408315515418e-05,
+      "loss": 1.0014,
+      "step": 180
+    },
+    {
+      "epoch": 1.2101910828025477,
+      "grad_norm": 0.42078331112861633,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.0072,
+      "step": 190
+    },
+    {
+      "epoch": 1.2738853503184713,
+      "grad_norm": 0.5042803883552551,
+      "learning_rate": 7.171808188570291e-05,
+      "loss": 1.0023,
+      "step": 200
+    },
+    {
+      "epoch": 1.3375796178343948,
+      "grad_norm": 0.4602188766002655,
+      "learning_rate": 6.831642333423067e-05,
+      "loss": 0.9621,
+      "step": 210
+    },
+    {
+      "epoch": 1.4012738853503186,
+      "grad_norm": 0.4462142586708069,
+      "learning_rate": 6.481377904428171e-05,
+      "loss": 0.9819,
+      "step": 220
+    },
+    {
+      "epoch": 1.4649681528662422,
+      "grad_norm": 0.4639708697795868,
+      "learning_rate": 6.122946048915991e-05,
+      "loss": 0.9851,
+      "step": 230
+    },
+    {
+      "epoch": 1.5286624203821657,
+      "grad_norm": 0.4281213581562042,
+      "learning_rate": 5.75832294449293e-05,
+      "loss": 0.9506,
+      "step": 240
+    },
+    {
+      "epoch": 1.5923566878980893,
+      "grad_norm": 0.4628894627094269,
+      "learning_rate": 5.389518903587017e-05,
+      "loss": 0.9534,
+      "step": 250
+    },
+    {
+      "epoch": 1.6560509554140128,
+      "grad_norm": 0.42661815881729126,
+      "learning_rate": 5.018567289794651e-05,
+      "loss": 0.9577,
+      "step": 260
+    },
+    {
+      "epoch": 1.7197452229299364,
+      "grad_norm": 0.5284398198127747,
+      "learning_rate": 4.647513307137076e-05,
+      "loss": 0.9683,
+      "step": 270
+    },
+    {
+      "epoch": 1.78343949044586,
+      "grad_norm": 0.4475821852684021,
+      "learning_rate": 4.278402724035867e-05,
+      "loss": 0.9667,
+      "step": 280
+    },
+    {
+      "epoch": 1.8471337579617835,
+      "grad_norm": 0.44738808274269104,
+      "learning_rate": 3.913270594176664e-05,
+      "loss": 0.9544,
+      "step": 290
+    },
+    {
+      "epoch": 1.910828025477707,
+      "grad_norm": 0.4267480969429016,
+      "learning_rate": 3.554130036447506e-05,
+      "loss": 0.9899,
+      "step": 300
+    },
+    {
+      "epoch": 1.9745222929936306,
+      "grad_norm": 0.47479352355003357,
+      "learning_rate": 3.202961135812437e-05,
+      "loss": 0.9587,
+      "step": 310
+    },
+    {
+      "epoch": 2.038216560509554,
+      "grad_norm": 0.41422757506370544,
+      "learning_rate": 2.8617000263143078e-05,
+      "loss": 0.9553,
+      "step": 320
+    },
+    {
+      "epoch": 2.1019108280254777,
+      "grad_norm": 0.53452068567276,
+      "learning_rate": 2.5322282163965095e-05,
+      "loss": 0.9506,
+      "step": 330
+    },
+    {
+      "epoch": 2.1656050955414012,
+      "grad_norm": 0.4785228371620178,
+      "learning_rate": 2.216362215397393e-05,
+      "loss": 0.9602,
+      "step": 340
+    },
+    {
+      "epoch": 2.229299363057325,
+      "grad_norm": 0.46735599637031555,
+      "learning_rate": 1.91584351841065e-05,
+      "loss": 0.9424,
+      "step": 350
+    },
+    {
+      "epoch": 2.2929936305732483,
+      "grad_norm": 0.47307127714157104,
+      "learning_rate": 1.6323290047291194e-05,
+      "loss": 0.9036,
+      "step": 360
+    },
+    {
+      "epoch": 2.356687898089172,
+      "grad_norm": 0.4797765910625458,
+      "learning_rate": 1.367381802809185e-05,
+      "loss": 0.9354,
+      "step": 370
+    },
+    {
+      "epoch": 2.4203821656050954,
+      "grad_norm": 0.4451310932636261,
+      "learning_rate": 1.122462672120914e-05,
+      "loss": 0.9319,
+      "step": 380
+    },
+    {
+      "epoch": 2.484076433121019,
+      "grad_norm": 0.47275781631469727,
+      "learning_rate": 8.98921949399179e-06,
+      "loss": 0.99,
+      "step": 390
+    },
+    {
+      "epoch": 2.5477707006369426,
+      "grad_norm": 0.449569970369339,
+      "learning_rate": 6.979921036993042e-06,
+      "loss": 0.9659,
+      "step": 400
+    },
+    {
+      "epoch": 2.611464968152866,
+      "grad_norm": 0.5072051882743835,
+      "learning_rate": 5.207809413041914e-06,
+      "loss": 0.9192,
+      "step": 410
+    },
+    {
+      "epoch": 2.6751592356687897,
+      "grad_norm": 0.44743847846984863,
+      "learning_rate": 3.6826549794698074e-06,
+      "loss": 0.9026,
+      "step": 420
+    },
+    {
+      "epoch": 2.738853503184713,
+      "grad_norm": 0.4364466369152069,
+      "learning_rate": 2.4128665202382326e-06,
+      "loss": 0.9621,
+      "step": 430
+    },
+    {
+      "epoch": 2.802547770700637,
+      "grad_norm": 0.4684942960739136,
+      "learning_rate": 1.4054448849631085e-06,
+      "loss": 0.9417,
+      "step": 440
+    },
+    {
+      "epoch": 2.8662420382165603,
+      "grad_norm": 0.47080230712890625,
+      "learning_rate": 6.659443904419637e-07,
+      "loss": 0.9432,
+      "step": 450
+    },
+    {
+      "epoch": 2.9299363057324843,
+      "grad_norm": 0.4364038109779358,
+      "learning_rate": 1.984421974927375e-07,
+      "loss": 0.9389,
+      "step": 460
+    },
+    {
+      "epoch": 2.9936305732484074,
+      "grad_norm": 0.458974152803421,
+      "learning_rate": 5.515831941993455e-09,
+      "loss": 0.9422,
+      "step": 470
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 471,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2627781654203597e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-471/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc87bd29ddcf8c8d5b6196dd816fdff849e3afb5a8510ffb1a8d6a9c027e659f
+size 6097

special_tokens_map.json

@@ -0,0 +1,42 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.2627781654203597e+17,
+    "train_loss": 1.0978564871850793,
+    "train_runtime": 364.5287,
+    "train_samples_per_second": 165.378,
+    "train_steps_per_second": 1.292
+}

trainer_log.jsonl

@@ -0,0 +1,48 @@
+{"current_steps": 10, "total_steps": 471, "loss": 3.2979, "lr": 1.8750000000000002e-05, "epoch": 0.06369426751592357, "percentage": 2.12, "elapsed_time": "0:00:10", "remaining_time": "0:08:20"}
+{"current_steps": 20, "total_steps": 471, "loss": 2.8325, "lr": 3.958333333333333e-05, "epoch": 0.12738853503184713, "percentage": 4.25, "elapsed_time": "0:00:18", "remaining_time": "0:06:50"}
+{"current_steps": 30, "total_steps": 471, "loss": 1.716, "lr": 6.041666666666667e-05, "epoch": 0.1910828025477707, "percentage": 6.37, "elapsed_time": "0:00:26", "remaining_time": "0:06:26"}
+{"current_steps": 40, "total_steps": 471, "loss": 1.2752, "lr": 8.125000000000001e-05, "epoch": 0.25477707006369427, "percentage": 8.49, "elapsed_time": "0:00:33", "remaining_time": "0:06:03"}
+{"current_steps": 50, "total_steps": 471, "loss": 1.207, "lr": 9.999862102299873e-05, "epoch": 0.3184713375796178, "percentage": 10.62, "elapsed_time": "0:00:41", "remaining_time": "0:05:51"}
+{"current_steps": 60, "total_steps": 471, "loss": 1.1241, "lr": 9.983323579940351e-05, "epoch": 0.3821656050955414, "percentage": 12.74, "elapsed_time": "0:00:49", "remaining_time": "0:05:39"}
+{"current_steps": 70, "total_steps": 471, "loss": 1.0958, "lr": 9.939310009499348e-05, "epoch": 0.445859872611465, "percentage": 14.86, "elapsed_time": "0:00:57", "remaining_time": "0:05:31"}
+{"current_steps": 80, "total_steps": 471, "loss": 1.059, "lr": 9.868064055324204e-05, "epoch": 0.5095541401273885, "percentage": 16.99, "elapsed_time": "0:01:06", "remaining_time": "0:05:25"}
+{"current_steps": 90, "total_steps": 471, "loss": 1.0795, "lr": 9.769978524742229e-05, "epoch": 0.5732484076433121, "percentage": 19.11, "elapsed_time": "0:01:14", "remaining_time": "0:05:13"}
+{"current_steps": 100, "total_steps": 471, "loss": 1.0693, "lr": 9.645594202357439e-05, "epoch": 0.6369426751592356, "percentage": 21.23, "elapsed_time": "0:01:21", "remaining_time": "0:05:01"}
+{"current_steps": 110, "total_steps": 471, "loss": 1.0465, "lr": 9.495596868489588e-05, "epoch": 0.7006369426751592, "percentage": 23.35, "elapsed_time": "0:01:28", "remaining_time": "0:04:49"}
+{"current_steps": 120, "total_steps": 471, "loss": 1.0324, "lr": 9.320813518194084e-05, "epoch": 0.7643312101910829, "percentage": 25.48, "elapsed_time": "0:01:35", "remaining_time": "0:04:40"}
+{"current_steps": 130, "total_steps": 471, "loss": 1.0234, "lr": 9.122207801708802e-05, "epoch": 0.8280254777070064, "percentage": 27.6, "elapsed_time": "0:01:43", "remaining_time": "0:04:31"}
+{"current_steps": 140, "total_steps": 471, "loss": 1.0376, "lr": 8.900874711466435e-05, "epoch": 0.89171974522293, "percentage": 29.72, "elapsed_time": "0:01:50", "remaining_time": "0:04:22"}
+{"current_steps": 150, "total_steps": 471, "loss": 0.9996, "lr": 8.658034544965003e-05, "epoch": 0.9554140127388535, "percentage": 31.85, "elapsed_time": "0:01:58", "remaining_time": "0:04:14"}
+{"current_steps": 160, "total_steps": 471, "loss": 0.9987, "lr": 8.395026176781627e-05, "epoch": 1.019108280254777, "percentage": 33.97, "elapsed_time": "0:02:06", "remaining_time": "0:04:05"}
+{"current_steps": 170, "total_steps": 471, "loss": 0.9745, "lr": 8.113299676823614e-05, "epoch": 1.0828025477707006, "percentage": 36.09, "elapsed_time": "0:02:13", "remaining_time": "0:03:56"}
+{"current_steps": 180, "total_steps": 471, "loss": 1.0014, "lr": 7.814408315515418e-05, "epoch": 1.1464968152866242, "percentage": 38.22, "elapsed_time": "0:02:21", "remaining_time": "0:03:49"}
+{"current_steps": 190, "total_steps": 471, "loss": 1.0072, "lr": 7.500000000000001e-05, "epoch": 1.2101910828025477, "percentage": 40.34, "elapsed_time": "0:02:29", "remaining_time": "0:03:40"}
+{"current_steps": 200, "total_steps": 471, "loss": 1.0023, "lr": 7.171808188570291e-05, "epoch": 1.2738853503184713, "percentage": 42.46, "elapsed_time": "0:02:36", "remaining_time": "0:03:31"}
+{"current_steps": 210, "total_steps": 471, "loss": 0.9621, "lr": 6.831642333423067e-05, "epoch": 1.3375796178343948, "percentage": 44.59, "elapsed_time": "0:02:43", "remaining_time": "0:03:23"}
+{"current_steps": 220, "total_steps": 471, "loss": 0.9819, "lr": 6.481377904428171e-05, "epoch": 1.4012738853503186, "percentage": 46.71, "elapsed_time": "0:02:52", "remaining_time": "0:03:16"}
+{"current_steps": 230, "total_steps": 471, "loss": 0.9851, "lr": 6.122946048915991e-05, "epoch": 1.4649681528662422, "percentage": 48.83, "elapsed_time": "0:02:59", "remaining_time": "0:03:08"}
+{"current_steps": 240, "total_steps": 471, "loss": 0.9506, "lr": 5.75832294449293e-05, "epoch": 1.5286624203821657, "percentage": 50.96, "elapsed_time": "0:03:06", "remaining_time": "0:02:59"}
+{"current_steps": 250, "total_steps": 471, "loss": 0.9534, "lr": 5.389518903587017e-05, "epoch": 1.5923566878980893, "percentage": 53.08, "elapsed_time": "0:03:14", "remaining_time": "0:02:52"}
+{"current_steps": 260, "total_steps": 471, "loss": 0.9577, "lr": 5.018567289794651e-05, "epoch": 1.6560509554140128, "percentage": 55.2, "elapsed_time": "0:03:22", "remaining_time": "0:02:44"}
+{"current_steps": 270, "total_steps": 471, "loss": 0.9683, "lr": 4.647513307137076e-05, "epoch": 1.7197452229299364, "percentage": 57.32, "elapsed_time": "0:03:29", "remaining_time": "0:02:36"}
+{"current_steps": 280, "total_steps": 471, "loss": 0.9667, "lr": 4.278402724035867e-05, "epoch": 1.78343949044586, "percentage": 59.45, "elapsed_time": "0:03:36", "remaining_time": "0:02:27"}
+{"current_steps": 290, "total_steps": 471, "loss": 0.9544, "lr": 3.913270594176664e-05, "epoch": 1.8471337579617835, "percentage": 61.57, "elapsed_time": "0:03:43", "remaining_time": "0:02:19"}
+{"current_steps": 300, "total_steps": 471, "loss": 0.9899, "lr": 3.554130036447506e-05, "epoch": 1.910828025477707, "percentage": 63.69, "elapsed_time": "0:03:52", "remaining_time": "0:02:12"}
+{"current_steps": 310, "total_steps": 471, "loss": 0.9587, "lr": 3.202961135812437e-05, "epoch": 1.9745222929936306, "percentage": 65.82, "elapsed_time": "0:04:00", "remaining_time": "0:02:04"}
+{"current_steps": 320, "total_steps": 471, "loss": 0.9553, "lr": 2.8617000263143078e-05, "epoch": 2.038216560509554, "percentage": 67.94, "elapsed_time": "0:04:07", "remaining_time": "0:01:56"}
+{"current_steps": 330, "total_steps": 471, "loss": 0.9506, "lr": 2.5322282163965095e-05, "epoch": 2.1019108280254777, "percentage": 70.06, "elapsed_time": "0:04:15", "remaining_time": "0:01:49"}
+{"current_steps": 340, "total_steps": 471, "loss": 0.9602, "lr": 2.216362215397393e-05, "epoch": 2.1656050955414012, "percentage": 72.19, "elapsed_time": "0:04:22", "remaining_time": "0:01:41"}
+{"current_steps": 350, "total_steps": 471, "loss": 0.9424, "lr": 1.91584351841065e-05, "epoch": 2.229299363057325, "percentage": 74.31, "elapsed_time": "0:04:30", "remaining_time": "0:01:33"}
+{"current_steps": 360, "total_steps": 471, "loss": 0.9036, "lr": 1.6323290047291194e-05, "epoch": 2.2929936305732483, "percentage": 76.43, "elapsed_time": "0:04:38", "remaining_time": "0:01:25"}
+{"current_steps": 370, "total_steps": 471, "loss": 0.9354, "lr": 1.367381802809185e-05, "epoch": 2.356687898089172, "percentage": 78.56, "elapsed_time": "0:04:45", "remaining_time": "0:01:18"}
+{"current_steps": 380, "total_steps": 471, "loss": 0.9319, "lr": 1.122462672120914e-05, "epoch": 2.4203821656050954, "percentage": 80.68, "elapsed_time": "0:04:53", "remaining_time": "0:01:10"}
+{"current_steps": 390, "total_steps": 471, "loss": 0.99, "lr": 8.98921949399179e-06, "epoch": 2.484076433121019, "percentage": 82.8, "elapsed_time": "0:05:01", "remaining_time": "0:01:02"}
+{"current_steps": 400, "total_steps": 471, "loss": 0.9659, "lr": 6.979921036993042e-06, "epoch": 2.5477707006369426, "percentage": 84.93, "elapsed_time": "0:05:09", "remaining_time": "0:00:54"}
+{"current_steps": 410, "total_steps": 471, "loss": 0.9192, "lr": 5.207809413041914e-06, "epoch": 2.611464968152866, "percentage": 87.05, "elapsed_time": "0:05:16", "remaining_time": "0:00:47"}
+{"current_steps": 420, "total_steps": 471, "loss": 0.9026, "lr": 3.6826549794698074e-06, "epoch": 2.6751592356687897, "percentage": 89.17, "elapsed_time": "0:05:24", "remaining_time": "0:00:39"}
+{"current_steps": 430, "total_steps": 471, "loss": 0.9621, "lr": 2.4128665202382326e-06, "epoch": 2.738853503184713, "percentage": 91.3, "elapsed_time": "0:05:31", "remaining_time": "0:00:31"}
+{"current_steps": 440, "total_steps": 471, "loss": 0.9417, "lr": 1.4054448849631085e-06, "epoch": 2.802547770700637, "percentage": 93.42, "elapsed_time": "0:05:39", "remaining_time": "0:00:23"}
+{"current_steps": 450, "total_steps": 471, "loss": 0.9432, "lr": 6.659443904419637e-07, "epoch": 2.8662420382165603, "percentage": 95.54, "elapsed_time": "0:05:46", "remaining_time": "0:00:16"}
+{"current_steps": 460, "total_steps": 471, "loss": 0.9389, "lr": 1.984421974927375e-07, "epoch": 2.9299363057324843, "percentage": 97.66, "elapsed_time": "0:05:53", "remaining_time": "0:00:08"}
+{"current_steps": 470, "total_steps": 471, "loss": 0.9422, "lr": 5.515831941993455e-09, "epoch": 2.9936305732484074, "percentage": 99.79, "elapsed_time": "0:06:01", "remaining_time": "0:00:00"}
+{"current_steps": 471, "total_steps": 471, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:06:02", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,372 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 471,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06369426751592357,
+      "grad_norm": 6.031618595123291,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.2979,
+      "step": 10
+    },
+    {
+      "epoch": 0.12738853503184713,
+      "grad_norm": 5.124261379241943,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 2.8325,
+      "step": 20
+    },
+    {
+      "epoch": 0.1910828025477707,
+      "grad_norm": 2.4147489070892334,
+      "learning_rate": 6.041666666666667e-05,
+      "loss": 1.716,
+      "step": 30
+    },
+    {
+      "epoch": 0.25477707006369427,
+      "grad_norm": 1.0314959287643433,
+      "learning_rate": 8.125000000000001e-05,
+      "loss": 1.2752,
+      "step": 40
+    },
+    {
+      "epoch": 0.3184713375796178,
+      "grad_norm": 0.5906504988670349,
+      "learning_rate": 9.999862102299873e-05,
+      "loss": 1.207,
+      "step": 50
+    },
+    {
+      "epoch": 0.3821656050955414,
+      "grad_norm": 0.43713438510894775,
+      "learning_rate": 9.983323579940351e-05,
+      "loss": 1.1241,
+      "step": 60
+    },
+    {
+      "epoch": 0.445859872611465,
+      "grad_norm": 0.40896832942962646,
+      "learning_rate": 9.939310009499348e-05,
+      "loss": 1.0958,
+      "step": 70
+    },
+    {
+      "epoch": 0.5095541401273885,
+      "grad_norm": 0.31001320481300354,
+      "learning_rate": 9.868064055324204e-05,
+      "loss": 1.059,
+      "step": 80
+    },
+    {
+      "epoch": 0.5732484076433121,
+      "grad_norm": 0.3313826024532318,
+      "learning_rate": 9.769978524742229e-05,
+      "loss": 1.0795,
+      "step": 90
+    },
+    {
+      "epoch": 0.6369426751592356,
+      "grad_norm": 0.3064286708831787,
+      "learning_rate": 9.645594202357439e-05,
+      "loss": 1.0693,
+      "step": 100
+    },
+    {
+      "epoch": 0.7006369426751592,
+      "grad_norm": 0.3159961402416229,
+      "learning_rate": 9.495596868489588e-05,
+      "loss": 1.0465,
+      "step": 110
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "grad_norm": 0.39494845271110535,
+      "learning_rate": 9.320813518194084e-05,
+      "loss": 1.0324,
+      "step": 120
+    },
+    {
+      "epoch": 0.8280254777070064,
+      "grad_norm": 0.44708824157714844,
+      "learning_rate": 9.122207801708802e-05,
+      "loss": 1.0234,
+      "step": 130
+    },
+    {
+      "epoch": 0.89171974522293,
+      "grad_norm": 0.41689348220825195,
+      "learning_rate": 8.900874711466435e-05,
+      "loss": 1.0376,
+      "step": 140
+    },
+    {
+      "epoch": 0.9554140127388535,
+      "grad_norm": 0.44199317693710327,
+      "learning_rate": 8.658034544965003e-05,
+      "loss": 0.9996,
+      "step": 150
+    },
+    {
+      "epoch": 1.019108280254777,
+      "grad_norm": 0.4607829451560974,
+      "learning_rate": 8.395026176781627e-05,
+      "loss": 0.9987,
+      "step": 160
+    },
+    {
+      "epoch": 1.0828025477707006,
+      "grad_norm": 0.47777435183525085,
+      "learning_rate": 8.113299676823614e-05,
+      "loss": 0.9745,
+      "step": 170
+    },
+    {
+      "epoch": 1.1464968152866242,
+      "grad_norm": 0.48650094866752625,
+      "learning_rate": 7.814408315515418e-05,
+      "loss": 1.0014,
+      "step": 180
+    },
+    {
+      "epoch": 1.2101910828025477,
+      "grad_norm": 0.42078331112861633,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.0072,
+      "step": 190
+    },
+    {
+      "epoch": 1.2738853503184713,
+      "grad_norm": 0.5042803883552551,
+      "learning_rate": 7.171808188570291e-05,
+      "loss": 1.0023,
+      "step": 200
+    },
+    {
+      "epoch": 1.3375796178343948,
+      "grad_norm": 0.4602188766002655,
+      "learning_rate": 6.831642333423067e-05,
+      "loss": 0.9621,
+      "step": 210
+    },
+    {
+      "epoch": 1.4012738853503186,
+      "grad_norm": 0.4462142586708069,
+      "learning_rate": 6.481377904428171e-05,
+      "loss": 0.9819,
+      "step": 220
+    },
+    {
+      "epoch": 1.4649681528662422,
+      "grad_norm": 0.4639708697795868,
+      "learning_rate": 6.122946048915991e-05,
+      "loss": 0.9851,
+      "step": 230
+    },
+    {
+      "epoch": 1.5286624203821657,
+      "grad_norm": 0.4281213581562042,
+      "learning_rate": 5.75832294449293e-05,
+      "loss": 0.9506,
+      "step": 240
+    },
+    {
+      "epoch": 1.5923566878980893,
+      "grad_norm": 0.4628894627094269,
+      "learning_rate": 5.389518903587017e-05,
+      "loss": 0.9534,
+      "step": 250
+    },
+    {
+      "epoch": 1.6560509554140128,
+      "grad_norm": 0.42661815881729126,
+      "learning_rate": 5.018567289794651e-05,
+      "loss": 0.9577,
+      "step": 260
+    },
+    {
+      "epoch": 1.7197452229299364,
+      "grad_norm": 0.5284398198127747,
+      "learning_rate": 4.647513307137076e-05,
+      "loss": 0.9683,
+      "step": 270
+    },
+    {
+      "epoch": 1.78343949044586,
+      "grad_norm": 0.4475821852684021,
+      "learning_rate": 4.278402724035867e-05,
+      "loss": 0.9667,
+      "step": 280
+    },
+    {
+      "epoch": 1.8471337579617835,
+      "grad_norm": 0.44738808274269104,
+      "learning_rate": 3.913270594176664e-05,
+      "loss": 0.9544,
+      "step": 290
+    },
+    {
+      "epoch": 1.910828025477707,
+      "grad_norm": 0.4267480969429016,
+      "learning_rate": 3.554130036447506e-05,
+      "loss": 0.9899,
+      "step": 300
+    },
+    {
+      "epoch": 1.9745222929936306,
+      "grad_norm": 0.47479352355003357,
+      "learning_rate": 3.202961135812437e-05,
+      "loss": 0.9587,
+      "step": 310
+    },
+    {
+      "epoch": 2.038216560509554,
+      "grad_norm": 0.41422757506370544,
+      "learning_rate": 2.8617000263143078e-05,
+      "loss": 0.9553,
+      "step": 320
+    },
+    {
+      "epoch": 2.1019108280254777,
+      "grad_norm": 0.53452068567276,
+      "learning_rate": 2.5322282163965095e-05,
+      "loss": 0.9506,
+      "step": 330
+    },
+    {
+      "epoch": 2.1656050955414012,
+      "grad_norm": 0.4785228371620178,
+      "learning_rate": 2.216362215397393e-05,
+      "loss": 0.9602,
+      "step": 340
+    },
+    {
+      "epoch": 2.229299363057325,
+      "grad_norm": 0.46735599637031555,
+      "learning_rate": 1.91584351841065e-05,
+      "loss": 0.9424,
+      "step": 350
+    },
+    {
+      "epoch": 2.2929936305732483,
+      "grad_norm": 0.47307127714157104,
+      "learning_rate": 1.6323290047291194e-05,
+      "loss": 0.9036,
+      "step": 360
+    },
+    {
+      "epoch": 2.356687898089172,
+      "grad_norm": 0.4797765910625458,
+      "learning_rate": 1.367381802809185e-05,
+      "loss": 0.9354,
+      "step": 370
+    },
+    {
+      "epoch": 2.4203821656050954,
+      "grad_norm": 0.4451310932636261,
+      "learning_rate": 1.122462672120914e-05,
+      "loss": 0.9319,
+      "step": 380
+    },
+    {
+      "epoch": 2.484076433121019,
+      "grad_norm": 0.47275781631469727,
+      "learning_rate": 8.98921949399179e-06,
+      "loss": 0.99,
+      "step": 390
+    },
+    {
+      "epoch": 2.5477707006369426,
+      "grad_norm": 0.449569970369339,
+      "learning_rate": 6.979921036993042e-06,
+      "loss": 0.9659,
+      "step": 400
+    },
+    {
+      "epoch": 2.611464968152866,
+      "grad_norm": 0.5072051882743835,
+      "learning_rate": 5.207809413041914e-06,
+      "loss": 0.9192,
+      "step": 410
+    },
+    {
+      "epoch": 2.6751592356687897,
+      "grad_norm": 0.44743847846984863,
+      "learning_rate": 3.6826549794698074e-06,
+      "loss": 0.9026,
+      "step": 420
+    },
+    {
+      "epoch": 2.738853503184713,
+      "grad_norm": 0.4364466369152069,
+      "learning_rate": 2.4128665202382326e-06,
+      "loss": 0.9621,
+      "step": 430
+    },
+    {
+      "epoch": 2.802547770700637,
+      "grad_norm": 0.4684942960739136,
+      "learning_rate": 1.4054448849631085e-06,
+      "loss": 0.9417,
+      "step": 440
+    },
+    {
+      "epoch": 2.8662420382165603,
+      "grad_norm": 0.47080230712890625,
+      "learning_rate": 6.659443904419637e-07,
+      "loss": 0.9432,
+      "step": 450
+    },
+    {
+      "epoch": 2.9299363057324843,
+      "grad_norm": 0.4364038109779358,
+      "learning_rate": 1.984421974927375e-07,
+      "loss": 0.9389,
+      "step": 460
+    },
+    {
+      "epoch": 2.9936305732484074,
+      "grad_norm": 0.458974152803421,
+      "learning_rate": 5.515831941993455e-09,
+      "loss": 0.9422,
+      "step": 470
+    },
+    {
+      "epoch": 3.0,
+      "step": 471,
+      "total_flos": 1.2627781654203597e+17,
+      "train_loss": 1.0978564871850793,
+      "train_runtime": 364.5287,
+      "train_samples_per_second": 165.378,
+      "train_steps_per_second": 1.292
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 471,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2627781654203597e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc87bd29ddcf8c8d5b6196dd816fdff849e3afb5a8510ffb1a8d6a9c027e659f
+size 6097