Upload checkpoint-1250

checkpoints/checkpoint-1250/README.md

@@ -0,0 +1,208 @@
+---
+base_model: google/gemma-3-4b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-4b-it
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoints/checkpoint-1250/adapter_config.json

@@ -0,0 +1,145 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-4b-it",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 192,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 96,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "language_model.layers.8.self_attn.v_proj",
+    "language_model.layers.1.self_attn.k_proj",
+    "28.self_attn.k_proj",
+    "27.self_attn.k_proj",
+    "language_model.layers.18.self_attn.q_proj",
+    "language_model.layers.12.self_attn.k_proj",
+    "language_model.layers.14.self_attn.q_proj",
+    "language_model.layers.24.self_attn.q_proj",
+    "language_model.layers.4.self_attn.q_proj",
+    "language_model.layers.16.self_attn.k_proj",
+    "language_model.layers.4.self_attn.v_proj",
+    "28.self_attn.v_proj",
+    "language_model.layers.18.self_attn.v_proj",
+    "language_model.layers.0.self_attn.v_proj",
+    "language_model.layers.19.self_attn.k_proj",
+    "language_model.layers.12.self_attn.v_proj",
+    "language_model.layers.10.self_attn.k_proj",
+    "language_model.layers.25.self_attn.v_proj",
+    "language_model.layers.19.self_attn.q_proj",
+    "language_model.layers.1.self_attn.v_proj",
+    "language_model.layers.5.self_attn.k_proj",
+    "31.self_attn.k_proj",
+    "language_model.layers.19.self_attn.v_proj",
+    "33.self_attn.q_proj",
+    "language_model.layers.24.self_attn.v_proj",
+    "29.self_attn.k_proj",
+    "language_model.layers.26.self_attn.v_proj",
+    "language_model.layers.15.self_attn.v_proj",
+    "language_model.layers.18.self_attn.k_proj",
+    "language_model.layers.0.self_attn.k_proj",
+    "language_model.layers.20.self_attn.k_proj",
+    "language_model.layers.8.self_attn.q_proj",
+    "31.self_attn.v_proj",
+    "language_model.layers.10.self_attn.v_proj",
+    "language_model.layers.6.self_attn.q_proj",
+    "language_model.layers.2.self_attn.k_proj",
+    "29.self_attn.q_proj",
+    "language_model.layers.23.self_attn.q_proj",
+    "language_model.layers.5.self_attn.v_proj",
+    "language_model.layers.15.self_attn.q_proj",
+    "language_model.layers.2.self_attn.q_proj",
+    "language_model.layers.3.self_attn.q_proj",
+    "language_model.layers.6.self_attn.v_proj",
+    "language_model.layers.11.self_attn.q_proj",
+    "32.self_attn.q_proj",
+    "language_model.layers.14.self_attn.v_proj",
+    "language_model.layers.17.self_attn.v_proj",
+    "27.self_attn.q_proj",
+    "language_model.layers.21.self_attn.q_proj",
+    "language_model.layers.7.self_attn.q_proj",
+    "28.self_attn.q_proj",
+    "language_model.layers.9.self_attn.v_proj",
+    "33.self_attn.k_proj",
+    "language_model.layers.17.self_attn.q_proj",
+    "language_model.layers.3.self_attn.k_proj",
+    "language_model.layers.11.self_attn.v_proj",
+    "30.self_attn.k_proj",
+    "language_model.layers.26.self_attn.q_proj",
+    "language_model.layers.12.self_attn.q_proj",
+    "o_proj",
+    "29.self_attn.v_proj",
+    "language_model.layers.14.self_attn.k_proj",
+    "27.self_attn.v_proj",
+    "language_model.layers.8.self_attn.k_proj",
+    "language_model.layers.20.self_attn.v_proj",
+    "language_model.layers.2.self_attn.v_proj",
+    "language_model.layers.23.self_attn.v_proj",
+    "language_model.layers.13.self_attn.q_proj",
+    "language_model.layers.7.self_attn.v_proj",
+    "gate_proj",
+    "language_model.layers.13.self_attn.k_proj",
+    "language_model.layers.17.self_attn.k_proj",
+    "30.self_attn.v_proj",
+    "33.self_attn.v_proj",
+    "language_model.layers.3.self_attn.v_proj",
+    "31.self_attn.q_proj",
+    "language_model.layers.23.self_attn.k_proj",
+    "language_model.layers.24.self_attn.k_proj",
+    "language_model.layers.7.self_attn.k_proj",
+    "language_model.layers.25.self_attn.q_proj",
+    "language_model.layers.6.self_attn.k_proj",
+    "32.self_attn.k_proj",
+    "language_model.layers.25.self_attn.k_proj",
+    "language_model.layers.9.self_attn.k_proj",
+    "down_proj",
+    "language_model.layers.11.self_attn.k_proj",
+    "language_model.layers.0.self_attn.q_proj",
+    "language_model.layers.20.self_attn.q_proj",
+    "30.self_attn.q_proj",
+    "language_model.layers.22.self_attn.v_proj",
+    "language_model.layers.5.self_attn.q_proj",
+    "32.self_attn.v_proj",
+    "language_model.layers.13.self_attn.v_proj",
+    "language_model.layers.10.self_attn.q_proj",
+    "language_model.layers.9.self_attn.q_proj",
+    "language_model.layers.16.self_attn.v_proj",
+    "language_model.layers.15.self_attn.k_proj",
+    "language_model.layers.22.self_attn.k_proj",
+    "language_model.layers.16.self_attn.q_proj",
+    "language_model.layers.21.self_attn.v_proj",
+    "language_model.layers.4.self_attn.k_proj",
+    "language_model.layers.1.self_attn.q_proj",
+    "up_proj",
+    "language_model.layers.21.self_attn.k_proj",
+    "language_model.layers.26.self_attn.k_proj",
+    "language_model.layers.22.self_attn.q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/checkpoint-1250/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e58ffc3727bdf2c6b521f1ad8708f373a917adad89861f646b5a7315620ccb80
+size 715331368

checkpoints/checkpoint-1250/added_tokens.json

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

checkpoints/checkpoint-1250/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoints/checkpoint-1250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6565cec2776cdfd454a3483335072b3df0eb2591e65024b88fd291095b14695
+size 1430929015

checkpoints/checkpoint-1250/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

checkpoints/checkpoint-1250/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

checkpoints/checkpoint-1250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5d97bf798a7fa8b5ddbce03264fb72b870dda3d4d6c4a2bcbf34945a736435
+size 14645

checkpoints/checkpoint-1250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e7446d3c8bb9dbccb342fffb121390d527e0e1fd5ee9c1a396b030514a8402
+size 1465

checkpoints/checkpoint-1250/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "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": "<end_of_turn>",
+    "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
+  }
+}

checkpoints/checkpoint-1250/tokenizer.model

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

checkpoints/checkpoint-1250/trainer_state.json

@@ -0,0 +1,584 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.9603174603174605,
+  "eval_steps": 50,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0992063492063492,
+      "grad_norm": 2.4192488193511963,
+      "learning_rate": 4.7619047619047615e-06,
+      "loss": 1.3237,
+      "step": 25
+    },
+    {
+      "epoch": 0.1984126984126984,
+      "grad_norm": 0.8920113444328308,
+      "learning_rate": 9.722222222222223e-06,
+      "loss": 0.6721,
+      "step": 50
+    },
+    {
+      "epoch": 0.1984126984126984,
+      "eval_loss": 0.48523738980293274,
+      "eval_runtime": 17.2583,
+      "eval_samples_per_second": 4.867,
+      "eval_steps_per_second": 2.434,
+      "step": 50
+    },
+    {
+      "epoch": 0.2976190476190476,
+      "grad_norm": 0.5771058797836304,
+      "learning_rate": 1.4682539682539683e-05,
+      "loss": 0.3509,
+      "step": 75
+    },
+    {
+      "epoch": 0.3968253968253968,
+      "grad_norm": 0.5407119393348694,
+      "learning_rate": 1.9642857142857145e-05,
+      "loss": 0.2735,
+      "step": 100
+    },
+    {
+      "epoch": 0.3968253968253968,
+      "eval_loss": 0.28276199102401733,
+      "eval_runtime": 17.2337,
+      "eval_samples_per_second": 4.874,
+      "eval_steps_per_second": 2.437,
+      "step": 100
+    },
+    {
+      "epoch": 0.49603174603174605,
+      "grad_norm": 0.496040016412735,
+      "learning_rate": 2.4603174603174602e-05,
+      "loss": 0.2463,
+      "step": 125
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 0.4996989667415619,
+      "learning_rate": 2.9563492063492066e-05,
+      "loss": 0.2279,
+      "step": 150
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "eval_loss": 0.24540141224861145,
+      "eval_runtime": 17.2092,
+      "eval_samples_per_second": 4.881,
+      "eval_steps_per_second": 2.441,
+      "step": 150
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.5580428838729858,
+      "learning_rate": 3.4523809523809526e-05,
+      "loss": 0.214,
+      "step": 175
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.4554564356803894,
+      "learning_rate": 3.9484126984126986e-05,
+      "loss": 0.2046,
+      "step": 200
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "eval_loss": 0.22907117009162903,
+      "eval_runtime": 17.3315,
+      "eval_samples_per_second": 4.847,
+      "eval_steps_per_second": 2.423,
+      "step": 200
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 0.5286790132522583,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.1943,
+      "step": 225
+    },
+    {
+      "epoch": 0.9920634920634921,
+      "grad_norm": 0.4137091040611267,
+      "learning_rate": 4.940476190476191e-05,
+      "loss": 0.1885,
+      "step": 250
+    },
+    {
+      "epoch": 0.9920634920634921,
+      "eval_loss": 0.20971575379371643,
+      "eval_runtime": 17.2857,
+      "eval_samples_per_second": 4.859,
+      "eval_steps_per_second": 2.43,
+      "step": 250
+    },
+    {
+      "epoch": 1.0912698412698412,
+      "grad_norm": 0.4036062955856323,
+      "learning_rate": 5.436507936507936e-05,
+      "loss": 0.1656,
+      "step": 275
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.43942078948020935,
+      "learning_rate": 5.932539682539683e-05,
+      "loss": 0.1668,
+      "step": 300
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "eval_loss": 0.19860731065273285,
+      "eval_runtime": 17.4085,
+      "eval_samples_per_second": 4.825,
+      "eval_steps_per_second": 2.413,
+      "step": 300
+    },
+    {
+      "epoch": 1.2896825396825398,
+      "grad_norm": 0.38786229491233826,
+      "learning_rate": 6.428571428571429e-05,
+      "loss": 0.1575,
+      "step": 325
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.3493235409259796,
+      "learning_rate": 6.924603174603174e-05,
+      "loss": 0.1619,
+      "step": 350
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "eval_loss": 0.19389225542545319,
+      "eval_runtime": 17.2223,
+      "eval_samples_per_second": 4.877,
+      "eval_steps_per_second": 2.439,
+      "step": 350
+    },
+    {
+      "epoch": 1.4880952380952381,
+      "grad_norm": 0.39436835050582886,
+      "learning_rate": 7.420634920634921e-05,
+      "loss": 0.1524,
+      "step": 375
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "grad_norm": 0.3463725745677948,
+      "learning_rate": 7.916666666666666e-05,
+      "loss": 0.1482,
+      "step": 400
+    },
+    {
+      "epoch": 1.5873015873015874,
+      "eval_loss": 0.185992032289505,
+      "eval_runtime": 17.0685,
+      "eval_samples_per_second": 4.921,
+      "eval_steps_per_second": 2.461,
+      "step": 400
+    },
+    {
+      "epoch": 1.6865079365079365,
+      "grad_norm": 0.3713228702545166,
+      "learning_rate": 8.412698412698413e-05,
+      "loss": 0.149,
+      "step": 425
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.30970633029937744,
+      "learning_rate": 8.90873015873016e-05,
+      "loss": 0.1486,
+      "step": 450
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "eval_loss": 0.17747902870178223,
+      "eval_runtime": 17.1226,
+      "eval_samples_per_second": 4.906,
+      "eval_steps_per_second": 2.453,
+      "step": 450
+    },
+    {
+      "epoch": 1.8849206349206349,
+      "grad_norm": 0.3172999918460846,
+      "learning_rate": 9.404761904761905e-05,
+      "loss": 0.147,
+      "step": 475
+    },
+    {
+      "epoch": 1.9841269841269842,
+      "grad_norm": 0.3906099498271942,
+      "learning_rate": 9.900793650793652e-05,
+      "loss": 0.1427,
+      "step": 500
+    },
+    {
+      "epoch": 1.9841269841269842,
+      "eval_loss": 0.17465326189994812,
+      "eval_runtime": 17.3304,
+      "eval_samples_per_second": 4.847,
+      "eval_steps_per_second": 2.423,
+      "step": 500
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.402475506067276,
+      "learning_rate": 9.999520325413887e-05,
+      "loss": 0.1208,
+      "step": 525
+    },
+    {
+      "epoch": 2.1825396825396823,
+      "grad_norm": 0.37534043192863464,
+      "learning_rate": 9.997571805142639e-05,
+      "loss": 0.1163,
+      "step": 550
+    },
+    {
+      "epoch": 2.1825396825396823,
+      "eval_loss": 0.1724633127450943,
+      "eval_runtime": 17.1218,
+      "eval_samples_per_second": 4.906,
+      "eval_steps_per_second": 2.453,
+      "step": 550
+    },
+    {
+      "epoch": 2.2817460317460316,
+      "grad_norm": 0.30866020917892456,
+      "learning_rate": 9.994125043229752e-05,
+      "loss": 0.1104,
+      "step": 575
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.3464547395706177,
+      "learning_rate": 9.989181072993494e-05,
+      "loss": 0.1111,
+      "step": 600
+    },
+    {
+      "epoch": 2.380952380952381,
+      "eval_loss": 0.16887226700782776,
+      "eval_runtime": 17.1039,
+      "eval_samples_per_second": 4.911,
+      "eval_steps_per_second": 2.456,
+      "step": 600
+    },
+    {
+      "epoch": 2.4801587301587302,
+      "grad_norm": 0.3208065927028656,
+      "learning_rate": 9.982741376606078e-05,
+      "loss": 0.1153,
+      "step": 625
+    },
+    {
+      "epoch": 2.5793650793650795,
+      "grad_norm": 0.2699253559112549,
+      "learning_rate": 9.97480788464933e-05,
+      "loss": 0.106,
+      "step": 650
+    },
+    {
+      "epoch": 2.5793650793650795,
+      "eval_loss": 0.16333948075771332,
+      "eval_runtime": 17.2826,
+      "eval_samples_per_second": 4.86,
+      "eval_steps_per_second": 2.43,
+      "step": 650
+    },
+    {
+      "epoch": 2.678571428571429,
+      "grad_norm": 0.2834033668041229,
+      "learning_rate": 9.965382975535902e-05,
+      "loss": 0.1121,
+      "step": 675
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.2606027126312256,
+      "learning_rate": 9.954469474796241e-05,
+      "loss": 0.1127,
+      "step": 700
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "eval_loss": 0.1618286520242691,
+      "eval_runtime": 17.132,
+      "eval_samples_per_second": 4.903,
+      "eval_steps_per_second": 2.452,
+      "step": 700
+    },
+    {
+      "epoch": 2.876984126984127,
+      "grad_norm": 0.30125725269317627,
+      "learning_rate": 9.942070654231517e-05,
+      "loss": 0.1044,
+      "step": 725
+    },
+    {
+      "epoch": 2.9761904761904763,
+      "grad_norm": 0.29861846566200256,
+      "learning_rate": 9.928190230932746e-05,
+      "loss": 0.1136,
+      "step": 750
+    },
+    {
+      "epoch": 2.9761904761904763,
+      "eval_loss": 0.1563536822795868,
+      "eval_runtime": 17.1692,
+      "eval_samples_per_second": 4.892,
+      "eval_steps_per_second": 2.446,
+      "step": 750
+    },
+    {
+      "epoch": 3.0753968253968256,
+      "grad_norm": 0.2677716910839081,
+      "learning_rate": 9.912832366166442e-05,
+      "loss": 0.0872,
+      "step": 775
+    },
+    {
+      "epoch": 3.1746031746031744,
+      "grad_norm": 0.32582488656044006,
+      "learning_rate": 9.896001664127084e-05,
+      "loss": 0.0755,
+      "step": 800
+    },
+    {
+      "epoch": 3.1746031746031744,
+      "eval_loss": 0.1705877184867859,
+      "eval_runtime": 17.0936,
+      "eval_samples_per_second": 4.914,
+      "eval_steps_per_second": 2.457,
+      "step": 800
+    },
+    {
+      "epoch": 3.2738095238095237,
+      "grad_norm": 0.3075025677680969,
+      "learning_rate": 9.87770317055681e-05,
+      "loss": 0.0797,
+      "step": 825
+    },
+    {
+      "epoch": 3.373015873015873,
+      "grad_norm": 0.31252071261405945,
+      "learning_rate": 9.85794237123274e-05,
+      "loss": 0.0798,
+      "step": 850
+    },
+    {
+      "epoch": 3.373015873015873,
+      "eval_loss": 0.17046943306922913,
+      "eval_runtime": 17.1741,
+      "eval_samples_per_second": 4.891,
+      "eval_steps_per_second": 2.446,
+      "step": 850
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 0.27937978506088257,
+      "learning_rate": 9.836725190322362e-05,
+      "loss": 0.083,
+      "step": 875
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.2692514955997467,
+      "learning_rate": 9.814057988607512e-05,
+      "loss": 0.0793,
+      "step": 900
+    },
+    {
+      "epoch": 3.571428571428571,
+      "eval_loss": 0.1626635193824768,
+      "eval_runtime": 17.1732,
+      "eval_samples_per_second": 4.891,
+      "eval_steps_per_second": 2.446,
+      "step": 900
+    },
+    {
+      "epoch": 3.6706349206349205,
+      "grad_norm": 0.27245843410491943,
+      "learning_rate": 9.789947561577445e-05,
+      "loss": 0.0829,
+      "step": 925
+    },
+    {
+      "epoch": 3.7698412698412698,
+      "grad_norm": 0.43121346831321716,
+      "learning_rate": 9.764401137391593e-05,
+      "loss": 0.0855,
+      "step": 950
+    },
+    {
+      "epoch": 3.7698412698412698,
+      "eval_loss": 0.16290047764778137,
+      "eval_runtime": 17.2802,
+      "eval_samples_per_second": 4.861,
+      "eval_steps_per_second": 2.431,
+      "step": 950
+    },
+    {
+      "epoch": 3.869047619047619,
+      "grad_norm": 0.2564437985420227,
+      "learning_rate": 9.737426374712603e-05,
+      "loss": 0.0832,
+      "step": 975
+    },
+    {
+      "epoch": 3.9682539682539684,
+      "grad_norm": 0.2569499611854553,
+      "learning_rate": 9.709031360410318e-05,
+      "loss": 0.0822,
+      "step": 1000
+    },
+    {
+      "epoch": 3.9682539682539684,
+      "eval_loss": 0.1599450260400772,
+      "eval_runtime": 17.1601,
+      "eval_samples_per_second": 4.895,
+      "eval_steps_per_second": 2.448,
+      "step": 1000
+    },
+    {
+      "epoch": 4.067460317460317,
+      "grad_norm": 0.25898122787475586,
+      "learning_rate": 9.679224607137381e-05,
+      "loss": 0.0663,
+      "step": 1025
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.2629934549331665,
+      "learning_rate": 9.648015050777199e-05,
+      "loss": 0.0581,
+      "step": 1050
+    },
+    {
+      "epoch": 4.166666666666667,
+      "eval_loss": 0.17531248927116394,
+      "eval_runtime": 17.1692,
+      "eval_samples_per_second": 4.892,
+      "eval_steps_per_second": 2.446,
+      "step": 1050
+    },
+    {
+      "epoch": 4.265873015873016,
+      "grad_norm": 0.28607141971588135,
+      "learning_rate": 9.61541204776501e-05,
+      "loss": 0.0619,
+      "step": 1075
+    },
+    {
+      "epoch": 4.365079365079365,
+      "grad_norm": 0.4162488877773285,
+      "learning_rate": 9.581425372282891e-05,
+      "loss": 0.0604,
+      "step": 1100
+    },
+    {
+      "epoch": 4.365079365079365,
+      "eval_loss": 0.17279614508152008,
+      "eval_runtime": 17.0524,
+      "eval_samples_per_second": 4.926,
+      "eval_steps_per_second": 2.463,
+      "step": 1100
+    },
+    {
+      "epoch": 4.464285714285714,
+      "grad_norm": 0.3403438627719879,
+      "learning_rate": 9.546065213329508e-05,
+      "loss": 0.0612,
+      "step": 1125
+    },
+    {
+      "epoch": 4.563492063492063,
+      "grad_norm": 0.2564021944999695,
+      "learning_rate": 9.509342171665525e-05,
+      "loss": 0.0606,
+      "step": 1150
+    },
+    {
+      "epoch": 4.563492063492063,
+      "eval_loss": 0.17525893449783325,
+      "eval_runtime": 17.2006,
+      "eval_samples_per_second": 4.884,
+      "eval_steps_per_second": 2.442,
+      "step": 1150
+    },
+    {
+      "epoch": 4.662698412698413,
+      "grad_norm": 0.32691073417663574,
+      "learning_rate": 9.471267256635554e-05,
+      "loss": 0.0652,
+      "step": 1175
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.3063746988773346,
+      "learning_rate": 9.431851882867624e-05,
+      "loss": 0.0643,
+      "step": 1200
+    },
+    {
+      "epoch": 4.761904761904762,
+      "eval_loss": 0.18040473759174347,
+      "eval_runtime": 17.2703,
+      "eval_samples_per_second": 4.864,
+      "eval_steps_per_second": 2.432,
+      "step": 1200
+    },
+    {
+      "epoch": 4.861111111111111,
+      "grad_norm": 0.3747937083244324,
+      "learning_rate": 9.391107866851143e-05,
+      "loss": 0.0641,
+      "step": 1225
+    },
+    {
+      "epoch": 4.9603174603174605,
+      "grad_norm": 0.24522322416305542,
+      "learning_rate": 9.349047423394385e-05,
+      "loss": 0.0664,
+      "step": 1250
+    },
+    {
+      "epoch": 4.9603174603174605,
+      "eval_loss": 0.1712796539068222,
+      "eval_runtime": 17.304,
+      "eval_samples_per_second": 4.854,
+      "eval_steps_per_second": 2.427,
+      "step": 1250
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 5040,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.604987901694659e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-1250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca03ebf8e1c9fa7550ff212acc32e6d9abdcb46765cbc6176fd96677cf5ed5b
+size 6289