Upload checkpoint-1100

checkpoints-ocr-only/checkpoint-1100/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-ocr-only/checkpoint-1100/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.3.self_attn.q_proj",
+    "language_model.layers.10.self_attn.q_proj",
+    "language_model.layers.8.self_attn.q_proj",
+    "language_model.layers.21.self_attn.q_proj",
+    "language_model.layers.17.self_attn.v_proj",
+    "language_model.layers.15.self_attn.k_proj",
+    "language_model.layers.14.self_attn.v_proj",
+    "language_model.layers.22.self_attn.v_proj",
+    "language_model.layers.16.self_attn.v_proj",
+    "language_model.layers.26.self_attn.q_proj",
+    "language_model.layers.10.self_attn.k_proj",
+    "language_model.layers.0.self_attn.q_proj",
+    "language_model.layers.17.self_attn.q_proj",
+    "language_model.layers.11.self_attn.k_proj",
+    "31.self_attn.v_proj",
+    "up_proj",
+    "language_model.layers.4.self_attn.q_proj",
+    "language_model.layers.25.self_attn.q_proj",
+    "language_model.layers.23.self_attn.q_proj",
+    "30.self_attn.v_proj",
+    "language_model.layers.5.self_attn.v_proj",
+    "27.self_attn.k_proj",
+    "29.self_attn.v_proj",
+    "language_model.layers.19.self_attn.q_proj",
+    "language_model.layers.20.self_attn.v_proj",
+    "language_model.layers.14.self_attn.k_proj",
+    "29.self_attn.k_proj",
+    "language_model.layers.15.self_attn.q_proj",
+    "language_model.layers.13.self_attn.v_proj",
+    "33.self_attn.q_proj",
+    "language_model.layers.25.self_attn.k_proj",
+    "language_model.layers.1.self_attn.q_proj",
+    "language_model.layers.24.self_attn.q_proj",
+    "language_model.layers.20.self_attn.q_proj",
+    "28.self_attn.k_proj",
+    "31.self_attn.q_proj",
+    "33.self_attn.k_proj",
+    "language_model.layers.16.self_attn.k_proj",
+    "31.self_attn.k_proj",
+    "32.self_attn.k_proj",
+    "language_model.layers.9.self_attn.q_proj",
+    "language_model.layers.0.self_attn.v_proj",
+    "language_model.layers.0.self_attn.k_proj",
+    "language_model.layers.12.self_attn.v_proj",
+    "language_model.layers.11.self_attn.v_proj",
+    "language_model.layers.7.self_attn.q_proj",
+    "language_model.layers.21.self_attn.k_proj",
+    "language_model.layers.24.self_attn.k_proj",
+    "language_model.layers.2.self_attn.k_proj",
+    "language_model.layers.19.self_attn.k_proj",
+    "language_model.layers.9.self_attn.k_proj",
+    "language_model.layers.16.self_attn.q_proj",
+    "language_model.layers.6.self_attn.q_proj",
+    "language_model.layers.23.self_attn.v_proj",
+    "language_model.layers.4.self_attn.k_proj",
+    "language_model.layers.10.self_attn.v_proj",
+    "down_proj",
+    "language_model.layers.8.self_attn.v_proj",
+    "language_model.layers.22.self_attn.q_proj",
+    "o_proj",
+    "language_model.layers.22.self_attn.k_proj",
+    "language_model.layers.15.self_attn.v_proj",
+    "language_model.layers.2.self_attn.v_proj",
+    "language_model.layers.17.self_attn.k_proj",
+    "language_model.layers.1.self_attn.v_proj",
+    "29.self_attn.q_proj",
+    "28.self_attn.v_proj",
+    "language_model.layers.6.self_attn.k_proj",
+    "language_model.layers.18.self_attn.k_proj",
+    "language_model.layers.7.self_attn.v_proj",
+    "27.self_attn.v_proj",
+    "language_model.layers.9.self_attn.v_proj",
+    "language_model.layers.12.self_attn.k_proj",
+    "language_model.layers.7.self_attn.k_proj",
+    "28.self_attn.q_proj",
+    "language_model.layers.3.self_attn.k_proj",
+    "language_model.layers.21.self_attn.v_proj",
+    "language_model.layers.20.self_attn.k_proj",
+    "language_model.layers.3.self_attn.v_proj",
+    "language_model.layers.4.self_attn.v_proj",
+    "language_model.layers.25.self_attn.v_proj",
+    "language_model.layers.23.self_attn.k_proj",
+    "language_model.layers.6.self_attn.v_proj",
+    "language_model.layers.8.self_attn.k_proj",
+    "language_model.layers.13.self_attn.k_proj",
+    "language_model.layers.13.self_attn.q_proj",
+    "language_model.layers.24.self_attn.v_proj",
+    "30.self_attn.q_proj",
+    "language_model.layers.26.self_attn.v_proj",
+    "language_model.layers.12.self_attn.q_proj",
+    "language_model.layers.5.self_attn.q_proj",
+    "language_model.layers.19.self_attn.v_proj",
+    "gate_proj",
+    "language_model.layers.2.self_attn.q_proj",
+    "language_model.layers.11.self_attn.q_proj",
+    "32.self_attn.v_proj",
+    "32.self_attn.q_proj",
+    "language_model.layers.18.self_attn.q_proj",
+    "27.self_attn.q_proj",
+    "language_model.layers.1.self_attn.k_proj",
+    "language_model.layers.26.self_attn.k_proj",
+    "language_model.layers.18.self_attn.v_proj",
+    "30.self_attn.k_proj",
+    "33.self_attn.v_proj",
+    "language_model.layers.14.self_attn.q_proj",
+    "language_model.layers.5.self_attn.k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints-ocr-only/checkpoint-1100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459d9cc73d7ed51c847b8eae5dda40f6ad57b249363ff2266ad32a15b78f3958
+size 715331368

checkpoints-ocr-only/checkpoint-1100/added_tokens.json

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

checkpoints-ocr-only/checkpoint-1100/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-ocr-only/checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672f2ff9cdb85ebfdccb37703b74dffa26713df5800a3388278e32110c3e3943
+size 1430929015

checkpoints-ocr-only/checkpoint-1100/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-ocr-only/checkpoint-1100/processor_config.json

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

checkpoints-ocr-only/checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29adc3f04b16f4ac7f5b1dc3d9fcb19c78040ad671c4b2bf4a3cc4d244df933
+size 14645

checkpoints-ocr-only/checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8afa6838ad951b65a970b1167b9bfe70b16d835f5414fd9e456b83b44548a3b
+size 1465

checkpoints-ocr-only/checkpoint-1100/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-ocr-only/checkpoint-1100/tokenizer.model

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

checkpoints-ocr-only/checkpoint-1100/trainer_state.json

@@ -0,0 +1,518 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.732338308457711,
+  "eval_steps": 50,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19900497512437812,
+      "grad_norm": 1.7990126609802246,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 0.793,
+      "step": 25
+    },
+    {
+      "epoch": 0.39800995024875624,
+      "grad_norm": 0.8365816473960876,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 0.4716,
+      "step": 50
+    },
+    {
+      "epoch": 0.39800995024875624,
+      "eval_loss": 0.4320129156112671,
+      "eval_runtime": 6.7601,
+      "eval_samples_per_second": 6.213,
+      "eval_steps_per_second": 3.106,
+      "step": 50
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.7775853872299194,
+      "learning_rate": 2.9365079365079366e-05,
+      "loss": 0.3361,
+      "step": 75
+    },
+    {
+      "epoch": 0.7960199004975125,
+      "grad_norm": 0.6636790633201599,
+      "learning_rate": 3.928571428571429e-05,
+      "loss": 0.2948,
+      "step": 100
+    },
+    {
+      "epoch": 0.7960199004975125,
+      "eval_loss": 0.33022385835647583,
+      "eval_runtime": 6.6898,
+      "eval_samples_per_second": 6.278,
+      "eval_steps_per_second": 3.139,
+      "step": 100
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 1.2261595726013184,
+      "learning_rate": 4.9206349206349204e-05,
+      "loss": 0.2676,
+      "step": 125
+    },
+    {
+      "epoch": 1.191044776119403,
+      "grad_norm": 0.7317036986351013,
+      "learning_rate": 5.912698412698413e-05,
+      "loss": 0.2117,
+      "step": 150
+    },
+    {
+      "epoch": 1.191044776119403,
+      "eval_loss": 0.29277661442756653,
+      "eval_runtime": 6.7738,
+      "eval_samples_per_second": 6.2,
+      "eval_steps_per_second": 3.1,
+      "step": 150
+    },
+    {
+      "epoch": 1.390049751243781,
+      "grad_norm": 0.6499411463737488,
+      "learning_rate": 6.904761904761905e-05,
+      "loss": 0.2012,
+      "step": 175
+    },
+    {
+      "epoch": 1.5890547263681594,
+      "grad_norm": 0.5185657143592834,
+      "learning_rate": 7.896825396825397e-05,
+      "loss": 0.2078,
+      "step": 200
+    },
+    {
+      "epoch": 1.5890547263681594,
+      "eval_loss": 0.2523292899131775,
+      "eval_runtime": 6.7163,
+      "eval_samples_per_second": 6.253,
+      "eval_steps_per_second": 3.127,
+      "step": 200
+    },
+    {
+      "epoch": 1.7880597014925375,
+      "grad_norm": 0.5884851217269897,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.1881,
+      "step": 225
+    },
+    {
+      "epoch": 1.9870646766169155,
+      "grad_norm": 0.6400936841964722,
+      "learning_rate": 9.880952380952381e-05,
+      "loss": 0.1796,
+      "step": 250
+    },
+    {
+      "epoch": 1.9870646766169155,
+      "eval_loss": 0.2420523464679718,
+      "eval_runtime": 6.7416,
+      "eval_samples_per_second": 6.23,
+      "eval_steps_per_second": 3.115,
+      "step": 250
+    },
+    {
+      "epoch": 2.183084577114428,
+      "grad_norm": 0.6703982949256897,
+      "learning_rate": 9.997678517546382e-05,
+      "loss": 0.1139,
+      "step": 275
+    },
+    {
+      "epoch": 2.382089552238806,
+      "grad_norm": 0.6321631669998169,
+      "learning_rate": 9.989407561073525e-05,
+      "loss": 0.1172,
+      "step": 300
+    },
+    {
+      "epoch": 2.382089552238806,
+      "eval_loss": 0.2354932576417923,
+      "eval_runtime": 6.7603,
+      "eval_samples_per_second": 6.213,
+      "eval_steps_per_second": 3.106,
+      "step": 300
+    },
+    {
+      "epoch": 2.581094527363184,
+      "grad_norm": 0.8059718608856201,
+      "learning_rate": 9.975153876827008e-05,
+      "loss": 0.1069,
+      "step": 325
+    },
+    {
+      "epoch": 2.780099502487562,
+      "grad_norm": 0.4948858916759491,
+      "learning_rate": 9.954934556197257e-05,
+      "loss": 0.1151,
+      "step": 350
+    },
+    {
+      "epoch": 2.780099502487562,
+      "eval_loss": 0.21575972437858582,
+      "eval_runtime": 6.7672,
+      "eval_samples_per_second": 6.206,
+      "eval_steps_per_second": 3.103,
+      "step": 350
+    },
+    {
+      "epoch": 2.97910447761194,
+      "grad_norm": 0.6088687777519226,
+      "learning_rate": 9.928773843884593e-05,
+      "loss": 0.1119,
+      "step": 375
+    },
+    {
+      "epoch": 3.175124378109453,
+      "grad_norm": 0.4257402718067169,
+      "learning_rate": 9.896703108827759e-05,
+      "loss": 0.0685,
+      "step": 400
+    },
+    {
+      "epoch": 3.175124378109453,
+      "eval_loss": 0.22026698291301727,
+      "eval_runtime": 6.7778,
+      "eval_samples_per_second": 6.197,
+      "eval_steps_per_second": 3.098,
+      "step": 400
+    },
+    {
+      "epoch": 3.374129353233831,
+      "grad_norm": 0.7841633558273315,
+      "learning_rate": 9.85876080658986e-05,
+      "loss": 0.0618,
+      "step": 425
+    },
+    {
+      "epoch": 3.573134328358209,
+      "grad_norm": 0.49762266874313354,
+      "learning_rate": 9.814992433246858e-05,
+      "loss": 0.0674,
+      "step": 450
+    },
+    {
+      "epoch": 3.573134328358209,
+      "eval_loss": 0.22196471691131592,
+      "eval_runtime": 6.7554,
+      "eval_samples_per_second": 6.217,
+      "eval_steps_per_second": 3.109,
+      "step": 450
+    },
+    {
+      "epoch": 3.772139303482587,
+      "grad_norm": 0.4496731758117676,
+      "learning_rate": 9.765450470833865e-05,
+      "loss": 0.0669,
+      "step": 475
+    },
+    {
+      "epoch": 3.9711442786069653,
+      "grad_norm": 0.6780857443809509,
+      "learning_rate": 9.710194324414683e-05,
+      "loss": 0.0731,
+      "step": 500
+    },
+    {
+      "epoch": 3.9711442786069653,
+      "eval_loss": 0.2176351547241211,
+      "eval_runtime": 6.8114,
+      "eval_samples_per_second": 6.166,
+      "eval_steps_per_second": 3.083,
+      "step": 500
+    },
+    {
+      "epoch": 4.167164179104478,
+      "grad_norm": 0.5854173898696899,
+      "learning_rate": 9.649290250850029e-05,
+      "loss": 0.0452,
+      "step": 525
+    },
+    {
+      "epoch": 4.366169154228856,
+      "grad_norm": 0.6070399284362793,
+      "learning_rate": 9.582811279349882e-05,
+      "loss": 0.0426,
+      "step": 550
+    },
+    {
+      "epoch": 4.366169154228856,
+      "eval_loss": 0.24056479334831238,
+      "eval_runtime": 6.7662,
+      "eval_samples_per_second": 6.207,
+      "eval_steps_per_second": 3.104,
+      "step": 550
+    },
+    {
+      "epoch": 4.565174129353234,
+      "grad_norm": 0.4359109103679657,
+      "learning_rate": 9.51083712390519e-05,
+      "loss": 0.047,
+      "step": 575
+    },
+    {
+      "epoch": 4.764179104477612,
+      "grad_norm": 0.6713975071907043,
+      "learning_rate": 9.433454087703954e-05,
+      "loss": 0.0489,
+      "step": 600
+    },
+    {
+      "epoch": 4.764179104477612,
+      "eval_loss": 0.23347003757953644,
+      "eval_runtime": 6.83,
+      "eval_samples_per_second": 6.149,
+      "eval_steps_per_second": 3.075,
+      "step": 600
+    },
+    {
+      "epoch": 4.96318407960199,
+      "grad_norm": 0.4408963918685913,
+      "learning_rate": 9.350754959646306e-05,
+      "loss": 0.0482,
+      "step": 625
+    },
+    {
+      "epoch": 5.159203980099503,
+      "grad_norm": 0.6063380241394043,
+      "learning_rate": 9.26283890308265e-05,
+      "loss": 0.0329,
+      "step": 650
+    },
+    {
+      "epoch": 5.159203980099503,
+      "eval_loss": 0.2555783689022064,
+      "eval_runtime": 6.7811,
+      "eval_samples_per_second": 6.194,
+      "eval_steps_per_second": 3.097,
+      "step": 650
+    },
+    {
+      "epoch": 5.358208955223881,
+      "grad_norm": 0.3942003846168518,
+      "learning_rate": 9.169811336908296e-05,
+      "loss": 0.0307,
+      "step": 675
+    },
+    {
+      "epoch": 5.557213930348259,
+      "grad_norm": 0.44800761342048645,
+      "learning_rate": 9.071783809157167e-05,
+      "loss": 0.0298,
+      "step": 700
+    },
+    {
+      "epoch": 5.557213930348259,
+      "eval_loss": 0.253120094537735,
+      "eval_runtime": 6.763,
+      "eval_samples_per_second": 6.21,
+      "eval_steps_per_second": 3.105,
+      "step": 700
+    },
+    {
+      "epoch": 5.756218905472637,
+      "grad_norm": 0.2204218953847885,
+      "learning_rate": 8.968873863246128e-05,
+      "loss": 0.0325,
+      "step": 725
+    },
+    {
+      "epoch": 5.955223880597015,
+      "grad_norm": 0.3857346773147583,
+      "learning_rate": 8.861204897030346e-05,
+      "loss": 0.033,
+      "step": 750
+    },
+    {
+      "epoch": 5.955223880597015,
+      "eval_loss": 0.2424595206975937,
+      "eval_runtime": 6.7501,
+      "eval_samples_per_second": 6.222,
+      "eval_steps_per_second": 3.111,
+      "step": 750
+    },
+    {
+      "epoch": 6.151243781094528,
+      "grad_norm": 0.4148959517478943,
+      "learning_rate": 8.748906014838672e-05,
+      "loss": 0.0234,
+      "step": 775
+    },
+    {
+      "epoch": 6.350248756218906,
+      "grad_norm": 0.32743915915489197,
+      "learning_rate": 8.632111872666475e-05,
+      "loss": 0.021,
+      "step": 800
+    },
+    {
+      "epoch": 6.350248756218906,
+      "eval_loss": 0.2568890154361725,
+      "eval_runtime": 6.7623,
+      "eval_samples_per_second": 6.211,
+      "eval_steps_per_second": 3.105,
+      "step": 800
+    },
+    {
+      "epoch": 6.549253731343284,
+      "grad_norm": 0.3489019274711609,
+      "learning_rate": 8.510962516711546e-05,
+      "loss": 0.0213,
+      "step": 825
+    },
+    {
+      "epoch": 6.748258706467662,
+      "grad_norm": 0.3466608226299286,
+      "learning_rate": 8.385603215446704e-05,
+      "loss": 0.0237,
+      "step": 850
+    },
+    {
+      "epoch": 6.748258706467662,
+      "eval_loss": 0.26632529497146606,
+      "eval_runtime": 6.7153,
+      "eval_samples_per_second": 6.254,
+      "eval_steps_per_second": 3.127,
+      "step": 850
+    },
+    {
+      "epoch": 6.94726368159204,
+      "grad_norm": 0.3111066222190857,
+      "learning_rate": 8.256184285430409e-05,
+      "loss": 0.0245,
+      "step": 875
+    },
+    {
+      "epoch": 7.143283582089552,
+      "grad_norm": 0.22405096888542175,
+      "learning_rate": 8.122860911064333e-05,
+      "loss": 0.0179,
+      "step": 900
+    },
+    {
+      "epoch": 7.143283582089552,
+      "eval_loss": 0.285622239112854,
+      "eval_runtime": 6.7714,
+      "eval_samples_per_second": 6.203,
+      "eval_steps_per_second": 3.101,
+      "step": 900
+    },
+    {
+      "epoch": 7.34228855721393,
+      "grad_norm": 0.21382500231266022,
+      "learning_rate": 7.985792958513931e-05,
+      "loss": 0.0163,
+      "step": 925
+    },
+    {
+      "epoch": 7.541293532338308,
+      "grad_norm": 0.29507020115852356,
+      "learning_rate": 7.845144784015203e-05,
+      "loss": 0.0165,
+      "step": 950
+    },
+    {
+      "epoch": 7.541293532338308,
+      "eval_loss": 0.2754693627357483,
+      "eval_runtime": 6.8303,
+      "eval_samples_per_second": 6.149,
+      "eval_steps_per_second": 3.075,
+      "step": 950
+    },
+    {
+      "epoch": 7.740298507462686,
+      "grad_norm": 0.320900022983551,
+      "learning_rate": 7.701085036797461e-05,
+      "loss": 0.0171,
+      "step": 975
+    },
+    {
+      "epoch": 7.939303482587064,
+      "grad_norm": 0.1665511578321457,
+      "learning_rate": 7.553786456858429e-05,
+      "loss": 0.0173,
+      "step": 1000
+    },
+    {
+      "epoch": 7.939303482587064,
+      "eval_loss": 0.2736968398094177,
+      "eval_runtime": 6.7238,
+      "eval_samples_per_second": 6.247,
+      "eval_steps_per_second": 3.123,
+      "step": 1000
+    },
+    {
+      "epoch": 8.135323383084577,
+      "grad_norm": 0.3113134503364563,
+      "learning_rate": 7.403425667834164e-05,
+      "loss": 0.0133,
+      "step": 1025
+    },
+    {
+      "epoch": 8.334328358208955,
+      "grad_norm": 0.2369716763496399,
+      "learning_rate": 7.250182965212168e-05,
+      "loss": 0.0123,
+      "step": 1050
+    },
+    {
+      "epoch": 8.334328358208955,
+      "eval_loss": 0.28673774003982544,
+      "eval_runtime": 6.851,
+      "eval_samples_per_second": 6.131,
+      "eval_steps_per_second": 3.065,
+      "step": 1050
+    },
+    {
+      "epoch": 8.533333333333333,
+      "grad_norm": 0.1607227623462677,
+      "learning_rate": 7.094242100141625e-05,
+      "loss": 0.0128,
+      "step": 1075
+    },
+    {
+      "epoch": 8.732338308457711,
+      "grad_norm": 0.18972866237163544,
+      "learning_rate": 6.935790059100003e-05,
+      "loss": 0.0124,
+      "step": 1100
+    },
+    {
+      "epoch": 8.732338308457711,
+      "eval_loss": 0.2650262713432312,
+      "eval_runtime": 6.7801,
+      "eval_samples_per_second": 6.195,
+      "eval_steps_per_second": 3.097,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2520,
+  "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": 3.537091121936978e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints-ocr-only/checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07baa04e423886873e69f97242e133a08112d8355ffd13914f2af0b6219a235d
+size 6289