Upload checkpoint checkpoint-1500

.gitattributes

@@ -39,3 +39,4 @@ checkpoint-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1350/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-1500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.16.0

checkpoint-1500/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2|ffw_layer_1|ffw_layer_2|pos_proj|post|linear_start|linear_end|embedding_projection).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2|ffw_layer_1|ffw_layer_2|pos_proj|post|linear_start|linear_end|embedding_projection)))",
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b8b4b70500320938ba67a3194541ccc6d6cc0f7b0f80a01fad18db41e1153e
+size 614801160

checkpoint-1500/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 -%}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842746dc0cbe24e14b9ec173aa4abab421625fdb813df122aa8c7c590ede131c
+size 314017998

checkpoint-1500/preprocessor_config.json

@@ -0,0 +1,51 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "disable_grouping": null,
+  "dither": 0.0,
+  "do_center_crop": null,
+  "do_convert_rgb": null,
+  "do_normalize": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_size": 128,
+  "fft_length": 1024,
+  "fft_overdrive": true,
+  "frame_length": 512,
+  "hop_length": 160,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessorFast",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "input_scale_factor": 1.0,
+  "max_frequency": 7600.0,
+  "mel_floor": 1e-05,
+  "min_frequency": 125.0,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "per_bin_mean": null,
+  "per_bin_stddev": null,
+  "preemphasis": 0.97,
+  "preemphasis_htk_flavor": true,
+  "processor_class": "Gemma3nProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_attention_mask": true,
+  "return_tensors": null,
+  "sampling_rate": 16000,
+  "size": {
+    "height": 768,
+    "width": 768
+  }
+}

checkpoint-1500/processor_config.json

@@ -0,0 +1,5 @@
+{
+  "audio_seq_length": 188,
+  "image_seq_length": 256,
+  "processor_class": "Gemma3nProcessor"
+}

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b3b511d3ca97b15ae5676626f70f2841ab5615dee3dacae694c48e1f247c77
+size 14244

checkpoint-1500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84187c2d9d617e502e945550d81ca292e025619b579f753e47ae36a545f025f1
+size 988

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be54412ecb180133f027de9f7b0347a7f2200ef92bb0f50506ef028bfb0fbc72
+size 1064

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "audio_token": "<audio_soft_token>",
+  "boa_token": "<start_of_audio>",
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoa_token": "<end_of_audio>",
+  "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
+  }
+}

checkpoint-1500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c35ee648c07754b44cd9e371c75d4caa05c4504910b7ad29b1847ee9d8ba5d
+size 33442553

checkpoint-1500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5f0cc48abfbfc04d14562270a32e02149a3e7035f368cc5a462786f4a59961
+size 4696020

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.097412480974125,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.061068702290076333,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 9.249,
+      "step": 10
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 4165304.25,
+      "learning_rate": 7.317073170731707e-09,
+      "loss": 9.3268,
+      "step": 20
+    },
+    {
+      "epoch": 0.183206106870229,
+      "grad_norm": 52283.171875,
+      "learning_rate": 3.170731707317073e-08,
+      "loss": 5.2487,
+      "step": 30
+    },
+    {
+      "epoch": 0.24427480916030533,
+      "grad_norm": 34552.171875,
+      "learning_rate": 5.609756097560976e-08,
+      "loss": 3.5598,
+      "step": 40
+    },
+    {
+      "epoch": 0.3053435114503817,
+      "grad_norm": 26069.314453125,
+      "learning_rate": 8.048780487804878e-08,
+      "loss": 3.2428,
+      "step": 50
+    },
+    {
+      "epoch": 0.366412213740458,
+      "grad_norm": 17445.56640625,
+      "learning_rate": 1.048780487804878e-07,
+      "loss": 3.2248,
+      "step": 60
+    },
+    {
+      "epoch": 0.42748091603053434,
+      "grad_norm": 23311.046875,
+      "learning_rate": 1.2926829268292682e-07,
+      "loss": 3.2595,
+      "step": 70
+    },
+    {
+      "epoch": 0.48854961832061067,
+      "grad_norm": 13832.998046875,
+      "learning_rate": 1.5365853658536586e-07,
+      "loss": 3.0941,
+      "step": 80
+    },
+    {
+      "epoch": 0.549618320610687,
+      "grad_norm": 11702.7421875,
+      "learning_rate": 1.7804878048780488e-07,
+      "loss": 3.0741,
+      "step": 90
+    },
+    {
+      "epoch": 0.6106870229007634,
+      "grad_norm": 11529.9228515625,
+      "learning_rate": 1.997289972899729e-07,
+      "loss": 3.163,
+      "step": 100
+    },
+    {
+      "epoch": 0.6717557251908397,
+      "grad_norm": 9445.1396484375,
+      "learning_rate": 1.970189701897019e-07,
+      "loss": 3.0271,
+      "step": 110
+    },
+    {
+      "epoch": 0.732824427480916,
+      "grad_norm": 9955.53515625,
+      "learning_rate": 1.9430894308943088e-07,
+      "loss": 2.9452,
+      "step": 120
+    },
+    {
+      "epoch": 0.7938931297709924,
+      "grad_norm": 8468.791015625,
+      "learning_rate": 1.915989159891599e-07,
+      "loss": 2.9369,
+      "step": 130
+    },
+    {
+      "epoch": 0.8549618320610687,
+      "grad_norm": 9535.78125,
+      "learning_rate": 1.8888888888888888e-07,
+      "loss": 2.8495,
+      "step": 140
+    },
+    {
+      "epoch": 0.916030534351145,
+      "grad_norm": 6875.52783203125,
+      "learning_rate": 1.861788617886179e-07,
+      "loss": 2.9174,
+      "step": 150
+    },
+    {
+      "epoch": 0.9770992366412213,
+      "grad_norm": 7618.35107421875,
+      "learning_rate": 1.8346883468834688e-07,
+      "loss": 2.8059,
+      "step": 160
+    },
+    {
+      "epoch": 1.036641221374046,
+      "grad_norm": 7838.251953125,
+      "learning_rate": 1.8075880758807586e-07,
+      "loss": 2.7811,
+      "step": 170
+    },
+    {
+      "epoch": 1.0977099236641221,
+      "grad_norm": 7657.27880859375,
+      "learning_rate": 1.7804878048780488e-07,
+      "loss": 2.7413,
+      "step": 180
+    },
+    {
+      "epoch": 1.1587786259541986,
+      "grad_norm": 7777.9345703125,
+      "learning_rate": 1.753387533875339e-07,
+      "loss": 2.7186,
+      "step": 190
+    },
+    {
+      "epoch": 1.2198473282442748,
+      "grad_norm": 8100.41259765625,
+      "learning_rate": 1.7262872628726285e-07,
+      "loss": 2.6789,
+      "step": 200
+    },
+    {
+      "epoch": 1.2809160305343512,
+      "grad_norm": 6984.42822265625,
+      "learning_rate": 1.6991869918699186e-07,
+      "loss": 2.608,
+      "step": 210
+    },
+    {
+      "epoch": 1.3419847328244274,
+      "grad_norm": 7442.26806640625,
+      "learning_rate": 1.6720867208672087e-07,
+      "loss": 2.5542,
+      "step": 220
+    },
+    {
+      "epoch": 1.4030534351145039,
+      "grad_norm": 7562.8271484375,
+      "learning_rate": 1.6449864498644986e-07,
+      "loss": 2.7031,
+      "step": 230
+    },
+    {
+      "epoch": 1.46412213740458,
+      "grad_norm": 7235.27392578125,
+      "learning_rate": 1.6178861788617885e-07,
+      "loss": 2.6075,
+      "step": 240
+    },
+    {
+      "epoch": 1.5251908396946565,
+      "grad_norm": 7698.4599609375,
+      "learning_rate": 1.5907859078590786e-07,
+      "loss": 2.5737,
+      "step": 250
+    },
+    {
+      "epoch": 1.5862595419847327,
+      "grad_norm": 6776.5927734375,
+      "learning_rate": 1.5636856368563685e-07,
+      "loss": 2.6098,
+      "step": 260
+    },
+    {
+      "epoch": 1.6473282442748092,
+      "grad_norm": 6810.216796875,
+      "learning_rate": 1.5365853658536586e-07,
+      "loss": 2.6596,
+      "step": 270
+    },
+    {
+      "epoch": 1.7083969465648856,
+      "grad_norm": 8227.4892578125,
+      "learning_rate": 1.5094850948509485e-07,
+      "loss": 2.5461,
+      "step": 280
+    },
+    {
+      "epoch": 1.7694656488549618,
+      "grad_norm": 6727.93212890625,
+      "learning_rate": 1.4823848238482383e-07,
+      "loss": 2.5579,
+      "step": 290
+    },
+    {
+      "epoch": 1.830534351145038,
+      "grad_norm": 7243.64111328125,
+      "learning_rate": 1.4552845528455284e-07,
+      "loss": 2.5538,
+      "step": 300
+    },
+    {
+      "epoch": 1.8916030534351145,
+      "grad_norm": 6177.71240234375,
+      "learning_rate": 1.4281842818428186e-07,
+      "loss": 2.4577,
+      "step": 310
+    },
+    {
+      "epoch": 1.952671755725191,
+      "grad_norm": 7574.3271484375,
+      "learning_rate": 1.4010840108401082e-07,
+      "loss": 2.4778,
+      "step": 320
+    },
+    {
+      "epoch": 2.018320610687023,
+      "grad_norm": 6852.73095703125,
+      "learning_rate": 1.3739837398373983e-07,
+      "loss": 2.7076,
+      "step": 330
+    },
+    {
+      "epoch": 2.0793893129770993,
+      "grad_norm": 6963.75927734375,
+      "learning_rate": 1.3468834688346884e-07,
+      "loss": 2.3829,
+      "step": 340
+    },
+    {
+      "epoch": 2.1404580152671757,
+      "grad_norm": 7274.21630859375,
+      "learning_rate": 1.3197831978319783e-07,
+      "loss": 2.4186,
+      "step": 350
+    },
+    {
+      "epoch": 2.1954198473282442,
+      "grad_norm": 6927.31884765625,
+      "learning_rate": 1.2926829268292682e-07,
+      "loss": 2.5768,
+      "step": 360
+    },
+    {
+      "epoch": 2.2564885496183207,
+      "grad_norm": 6366.95458984375,
+      "learning_rate": 1.265582655826558e-07,
+      "loss": 2.3761,
+      "step": 370
+    },
+    {
+      "epoch": 2.317557251908397,
+      "grad_norm": 7380.29638671875,
+      "learning_rate": 1.2384823848238481e-07,
+      "loss": 2.289,
+      "step": 380
+    },
+    {
+      "epoch": 2.378625954198473,
+      "grad_norm": 5605.09375,
+      "learning_rate": 1.2113821138211383e-07,
+      "loss": 2.4026,
+      "step": 390
+    },
+    {
+      "epoch": 2.4396946564885496,
+      "grad_norm": 7360.8037109375,
+      "learning_rate": 1.184281842818428e-07,
+      "loss": 2.5143,
+      "step": 400
+    },
+    {
+      "epoch": 2.500763358778626,
+      "grad_norm": 6937.611328125,
+      "learning_rate": 1.1571815718157181e-07,
+      "loss": 2.3633,
+      "step": 410
+    },
+    {
+      "epoch": 2.5618320610687024,
+      "grad_norm": 7583.28173828125,
+      "learning_rate": 1.1300813008130081e-07,
+      "loss": 2.4694,
+      "step": 420
+    },
+    {
+      "epoch": 2.6229007633587784,
+      "grad_norm": 6622.31201171875,
+      "learning_rate": 1.102981029810298e-07,
+      "loss": 2.4963,
+      "step": 430
+    },
+    {
+      "epoch": 2.683969465648855,
+      "grad_norm": 6935.6689453125,
+      "learning_rate": 1.075880758807588e-07,
+      "loss": 2.3218,
+      "step": 440
+    },
+    {
+      "epoch": 2.7450381679389313,
+      "grad_norm": 7263.111328125,
+      "learning_rate": 1.048780487804878e-07,
+      "loss": 2.3239,
+      "step": 450
+    },
+    {
+      "epoch": 2.8061068702290077,
+      "grad_norm": 7146.81787109375,
+      "learning_rate": 1.0216802168021679e-07,
+      "loss": 2.4087,
+      "step": 460
+    },
+    {
+      "epoch": 2.867175572519084,
+      "grad_norm": 7680.18701171875,
+      "learning_rate": 9.94579945799458e-08,
+      "loss": 2.2903,
+      "step": 470
+    },
+    {
+      "epoch": 2.92824427480916,
+      "grad_norm": 6631.55224609375,
+      "learning_rate": 9.67479674796748e-08,
+      "loss": 2.3723,
+      "step": 480
+    },
+    {
+      "epoch": 2.9893129770992366,
+      "grad_norm": 8262.0439453125,
+      "learning_rate": 9.40379403794038e-08,
+      "loss": 2.2509,
+      "step": 490
+    },
+    {
+      "epoch": 3.0549618320610685,
+      "grad_norm": 6400.1064453125,
+      "learning_rate": 9.132791327913278e-08,
+      "loss": 2.4533,
+      "step": 500
+    },
+    {
+      "epoch": 3.116030534351145,
+      "grad_norm": 7908.66796875,
+      "learning_rate": 8.861788617886178e-08,
+      "loss": 2.303,
+      "step": 510
+    },
+    {
+      "epoch": 3.1770992366412214,
+      "grad_norm": 7437.154296875,
+      "learning_rate": 8.590785907859078e-08,
+      "loss": 2.3311,
+      "step": 520
+    },
+    {
+      "epoch": 3.238167938931298,
+      "grad_norm": 6793.77734375,
+      "learning_rate": 8.319783197831978e-08,
+      "loss": 2.2842,
+      "step": 530
+    },
+    {
+      "epoch": 3.2992366412213743,
+      "grad_norm": 9131.279296875,
+      "learning_rate": 8.048780487804878e-08,
+      "loss": 2.2995,
+      "step": 540
+    },
+    {
+      "epoch": 3.3603053435114503,
+      "grad_norm": 7804.341796875,
+      "learning_rate": 7.777777777777778e-08,
+      "loss": 2.2221,
+      "step": 550
+    },
+    {
+      "epoch": 3.4213740458015267,
+      "grad_norm": 8277.4609375,
+      "learning_rate": 7.506775067750677e-08,
+      "loss": 2.2648,
+      "step": 560
+    },
+    {
+      "epoch": 3.482442748091603,
+      "grad_norm": 7000.59326171875,
+      "learning_rate": 7.235772357723577e-08,
+      "loss": 2.2273,
+      "step": 570
+    },
+    {
+      "epoch": 3.543511450381679,
+      "grad_norm": 7754.044921875,
+      "learning_rate": 6.964769647696477e-08,
+      "loss": 2.1737,
+      "step": 580
+    },
+    {
+      "epoch": 3.6045801526717556,
+      "grad_norm": 7529.0654296875,
+      "learning_rate": 6.693766937669377e-08,
+      "loss": 2.3555,
+      "step": 590
+    },
+    {
+      "epoch": 3.665648854961832,
+      "grad_norm": 7320.09765625,
+      "learning_rate": 6.422764227642277e-08,
+      "loss": 2.2353,
+      "step": 600
+    },
+    {
+      "epoch": 3.7267175572519085,
+      "grad_norm": 8644.646484375,
+      "learning_rate": 6.151761517615177e-08,
+      "loss": 2.2864,
+      "step": 610
+    },
+    {
+      "epoch": 3.787786259541985,
+      "grad_norm": 8324.064453125,
+      "learning_rate": 5.880758807588075e-08,
+      "loss": 2.2941,
+      "step": 620
+    },
+    {
+      "epoch": 3.8488549618320613,
+      "grad_norm": 6925.88818359375,
+      "learning_rate": 5.609756097560976e-08,
+      "loss": 2.1825,
+      "step": 630
+    },
+    {
+      "epoch": 3.9099236641221373,
+      "grad_norm": 6678.88671875,
+      "learning_rate": 5.338753387533875e-08,
+      "loss": 2.2171,
+      "step": 640
+    },
+    {
+      "epoch": 3.9709923664122138,
+      "grad_norm": 8466.0029296875,
+      "learning_rate": 5.0677506775067745e-08,
+      "loss": 2.2335,
+      "step": 650
+    },
+    {
+      "epoch": 4.030534351145038,
+      "grad_norm": 8722.5830078125,
+      "learning_rate": 4.7967479674796744e-08,
+      "loss": 2.1464,
+      "step": 660
+    },
+    {
+      "epoch": 4.091603053435114,
+      "grad_norm": 9296.1796875,
+      "learning_rate": 4.5257452574525744e-08,
+      "loss": 2.1578,
+      "step": 670
+    },
+    {
+      "epoch": 4.152671755725191,
+      "grad_norm": 7651.701171875,
+      "learning_rate": 4.254742547425474e-08,
+      "loss": 2.1347,
+      "step": 680
+    },
+    {
+      "epoch": 4.213740458015267,
+      "grad_norm": 8067.0537109375,
+      "learning_rate": 3.9837398373983736e-08,
+      "loss": 2.1919,
+      "step": 690
+    },
+    {
+      "epoch": 4.2748091603053435,
+      "grad_norm": 7839.83984375,
+      "learning_rate": 3.7127371273712736e-08,
+      "loss": 2.1151,
+      "step": 700
+    },
+    {
+      "epoch": 4.33587786259542,
+      "grad_norm": 8194.3720703125,
+      "learning_rate": 3.441734417344173e-08,
+      "loss": 2.1244,
+      "step": 710
+    },
+    {
+      "epoch": 4.396946564885496,
+      "grad_norm": 8937.380859375,
+      "learning_rate": 3.170731707317073e-08,
+      "loss": 2.1311,
+      "step": 720
+    },
+    {
+      "epoch": 4.458015267175573,
+      "grad_norm": 7251.05029296875,
+      "learning_rate": 2.899728997289973e-08,
+      "loss": 2.0479,
+      "step": 730
+    },
+    {
+      "epoch": 4.519083969465649,
+      "grad_norm": 8328.97265625,
+      "learning_rate": 2.6287262872628724e-08,
+      "loss": 2.1177,
+      "step": 740
+    },
+    {
+      "epoch": 4.580152671755725,
+      "grad_norm": 8175.35205078125,
+      "learning_rate": 2.3577235772357724e-08,
+      "loss": 2.1621,
+      "step": 750
+    },
+    {
+      "epoch": 4.641221374045801,
+      "grad_norm": 7537.1240234375,
+      "learning_rate": 2.086720867208672e-08,
+      "loss": 2.0763,
+      "step": 760
+    },
+    {
+      "epoch": 4.702290076335878,
+      "grad_norm": 8975.009765625,
+      "learning_rate": 1.8157181571815717e-08,
+      "loss": 2.0954,
+      "step": 770
+    },
+    {
+      "epoch": 4.763358778625954,
+      "grad_norm": 7654.59375,
+      "learning_rate": 1.5447154471544716e-08,
+      "loss": 2.1462,
+      "step": 780
+    },
+    {
+      "epoch": 4.824427480916031,
+      "grad_norm": 7649.91455078125,
+      "learning_rate": 1.2737127371273712e-08,
+      "loss": 2.1864,
+      "step": 790
+    },
+    {
+      "epoch": 4.885496183206107,
+      "grad_norm": 10591.94140625,
+      "learning_rate": 1.002710027100271e-08,
+      "loss": 2.1013,
+      "step": 800
+    },
+    {
+      "epoch": 4.9404580152671755,
+      "grad_norm": 8500.8115234375,
+      "learning_rate": 1.1476964769647696e-07,
+      "loss": 2.0822,
+      "step": 810
+    },
+    {
+      "epoch": 5.006106870229008,
+      "grad_norm": 16557.328125,
+      "learning_rate": 1.1341463414634144e-07,
+      "loss": 2.2811,
+      "step": 820
+    },
+    {
+      "epoch": 5.067175572519084,
+      "grad_norm": 9301.4140625,
+      "learning_rate": 1.1205962059620595e-07,
+      "loss": 2.0959,
+      "step": 830
+    },
+    {
+      "epoch": 5.12824427480916,
+      "grad_norm": 9356.20703125,
+      "learning_rate": 1.1070460704607045e-07,
+      "loss": 2.2202,
+      "step": 840
+    },
+    {
+      "epoch": 5.189312977099236,
+      "grad_norm": 9045.6015625,
+      "learning_rate": 1.0934959349593496e-07,
+      "loss": 2.0862,
+      "step": 850
+    },
+    {
+      "epoch": 5.250381679389313,
+      "grad_norm": 8579.5859375,
+      "learning_rate": 1.0799457994579945e-07,
+      "loss": 2.0973,
+      "step": 860
+    },
+    {
+      "epoch": 5.311450381679389,
+      "grad_norm": 7725.3818359375,
+      "learning_rate": 1.0663956639566396e-07,
+      "loss": 2.0951,
+      "step": 870
+    },
+    {
+      "epoch": 5.372519083969466,
+      "grad_norm": 9646.31640625,
+      "learning_rate": 1.0528455284552844e-07,
+      "loss": 2.1344,
+      "step": 880
+    },
+    {
+      "epoch": 5.433587786259542,
+      "grad_norm": 9842.650390625,
+      "learning_rate": 1.0392953929539295e-07,
+      "loss": 2.2454,
+      "step": 890
+    },
+    {
+      "epoch": 5.4946564885496185,
+      "grad_norm": 8958.8818359375,
+      "learning_rate": 1.0257452574525744e-07,
+      "loss": 2.1991,
+      "step": 900
+    },
+    {
+      "epoch": 5.555725190839695,
+      "grad_norm": 8466.1337890625,
+      "learning_rate": 1.0121951219512195e-07,
+      "loss": 2.2648,
+      "step": 910
+    },
+    {
+      "epoch": 5.6167938931297705,
+      "grad_norm": 9552.7763671875,
+      "learning_rate": 9.986449864498645e-08,
+      "loss": 2.1624,
+      "step": 920
+    },
+    {
+      "epoch": 5.677862595419847,
+      "grad_norm": 8758.2080078125,
+      "learning_rate": 9.850948509485095e-08,
+      "loss": 2.1695,
+      "step": 930
+    },
+    {
+      "epoch": 5.738931297709923,
+      "grad_norm": 9433.7724609375,
+      "learning_rate": 9.715447154471544e-08,
+      "loss": 2.1904,
+      "step": 940
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 9150.314453125,
+      "learning_rate": 9.579945799457995e-08,
+      "loss": 2.1277,
+      "step": 950
+    },
+    {
+      "epoch": 5.861068702290076,
+      "grad_norm": 8703.0556640625,
+      "learning_rate": 9.444444444444444e-08,
+      "loss": 2.1673,
+      "step": 960
+    },
+    {
+      "epoch": 5.922137404580153,
+      "grad_norm": 9572.4521484375,
+      "learning_rate": 9.308943089430895e-08,
+      "loss": 2.1902,
+      "step": 970
+    },
+    {
+      "epoch": 5.983206106870229,
+      "grad_norm": 9630.294921875,
+      "learning_rate": 9.173441734417344e-08,
+      "loss": 2.1784,
+      "step": 980
+    },
+    {
+      "epoch": 6.042748091603054,
+      "grad_norm": 8915.1728515625,
+      "learning_rate": 9.037940379403793e-08,
+      "loss": 2.0724,
+      "step": 990
+    },
+    {
+      "epoch": 6.10381679389313,
+      "grad_norm": 8847.3818359375,
+      "learning_rate": 8.902439024390244e-08,
+      "loss": 2.0575,
+      "step": 1000
+    },
+    {
+      "epoch": 6.1648854961832065,
+      "grad_norm": 8241.4892578125,
+      "learning_rate": 8.766937669376694e-08,
+      "loss": 2.0178,
+      "step": 1010
+    },
+    {
+      "epoch": 6.225954198473282,
+      "grad_norm": 8648.701171875,
+      "learning_rate": 8.631436314363142e-08,
+      "loss": 2.0011,
+      "step": 1020
+    },
+    {
+      "epoch": 6.2870229007633585,
+      "grad_norm": 9467.17578125,
+      "learning_rate": 8.495934959349593e-08,
+      "loss": 2.0981,
+      "step": 1030
+    },
+    {
+      "epoch": 6.348091603053435,
+      "grad_norm": 10499.0380859375,
+      "learning_rate": 8.360433604336044e-08,
+      "loss": 2.0203,
+      "step": 1040
+    },
+    {
+      "epoch": 6.409160305343511,
+      "grad_norm": 9693.4306640625,
+      "learning_rate": 8.224932249322493e-08,
+      "loss": 2.0391,
+      "step": 1050
+    },
+    {
+      "epoch": 6.470229007633588,
+      "grad_norm": 7993.0908203125,
+      "learning_rate": 8.089430894308942e-08,
+      "loss": 2.0454,
+      "step": 1060
+    },
+    {
+      "epoch": 6.531297709923664,
+      "grad_norm": 9091.1513671875,
+      "learning_rate": 7.953929539295393e-08,
+      "loss": 2.0395,
+      "step": 1070
+    },
+    {
+      "epoch": 6.592366412213741,
+      "grad_norm": 9397.640625,
+      "learning_rate": 7.818428184281842e-08,
+      "loss": 2.0451,
+      "step": 1080
+    },
+    {
+      "epoch": 6.653435114503817,
+      "grad_norm": 8570.2080078125,
+      "learning_rate": 7.682926829268293e-08,
+      "loss": 2.0093,
+      "step": 1090
+    },
+    {
+      "epoch": 6.7145038167938935,
+      "grad_norm": 9464.01953125,
+      "learning_rate": 7.547425474254742e-08,
+      "loss": 2.0962,
+      "step": 1100
+    },
+    {
+      "epoch": 6.775572519083969,
+      "grad_norm": 9121.5888671875,
+      "learning_rate": 7.411924119241192e-08,
+      "loss": 2.0348,
+      "step": 1110
+    },
+    {
+      "epoch": 6.8366412213740455,
+      "grad_norm": 10847.6826171875,
+      "learning_rate": 7.276422764227642e-08,
+      "loss": 2.2046,
+      "step": 1120
+    },
+    {
+      "epoch": 6.897709923664122,
+      "grad_norm": 9057.5810546875,
+      "learning_rate": 7.140921409214093e-08,
+      "loss": 2.0798,
+      "step": 1130
+    },
+    {
+      "epoch": 6.958778625954198,
+      "grad_norm": 8820.8388671875,
+      "learning_rate": 7.005420054200541e-08,
+      "loss": 2.0917,
+      "step": 1140
+    },
+    {
+      "epoch": 7.018320610687023,
+      "grad_norm": 10036.4736328125,
+      "learning_rate": 6.869918699186992e-08,
+      "loss": 1.9786,
+      "step": 1150
+    },
+    {
+      "epoch": 7.036529680365296,
+      "grad_norm": 11530.90625,
+      "learning_rate": 6.828282828282827e-08,
+      "loss": 2.2471,
+      "step": 1160
+    },
+    {
+      "epoch": 7.097412480974125,
+      "grad_norm": 9662.255859375,
+      "learning_rate": 6.693602693602694e-08,
+      "loss": 1.9145,
+      "step": 1170
+    },
+    {
+      "epoch": 7.158295281582953,
+      "grad_norm": 10183.75390625,
+      "learning_rate": 6.558922558922558e-08,
+      "loss": 1.9465,
+      "step": 1180
+    },
+    {
+      "epoch": 7.219178082191781,
+      "grad_norm": 9636.931640625,
+      "learning_rate": 6.424242424242425e-08,
+      "loss": 2.0657,
+      "step": 1190
+    },
+    {
+      "epoch": 7.280060882800608,
+      "grad_norm": 11796.3876953125,
+      "learning_rate": 6.289562289562289e-08,
+      "loss": 1.9164,
+      "step": 1200
+    },
+    {
+      "epoch": 7.340943683409437,
+      "grad_norm": 9830.958984375,
+      "learning_rate": 6.154882154882155e-08,
+      "loss": 1.9941,
+      "step": 1210
+    },
+    {
+      "epoch": 7.401826484018265,
+      "grad_norm": 10664.53515625,
+      "learning_rate": 6.02020202020202e-08,
+      "loss": 1.953,
+      "step": 1220
+    },
+    {
+      "epoch": 7.462709284627093,
+      "grad_norm": 9731.1494140625,
+      "learning_rate": 5.8855218855218856e-08,
+      "loss": 1.9209,
+      "step": 1230
+    },
+    {
+      "epoch": 7.52359208523592,
+      "grad_norm": 9153.5048828125,
+      "learning_rate": 5.750841750841751e-08,
+      "loss": 1.9879,
+      "step": 1240
+    },
+    {
+      "epoch": 7.584474885844749,
+      "grad_norm": 10567.484375,
+      "learning_rate": 5.6161616161616156e-08,
+      "loss": 1.9345,
+      "step": 1250
+    },
+    {
+      "epoch": 7.645357686453577,
+      "grad_norm": 8448.8466796875,
+      "learning_rate": 5.481481481481482e-08,
+      "loss": 1.9926,
+      "step": 1260
+    },
+    {
+      "epoch": 7.706240487062405,
+      "grad_norm": 11257.6962890625,
+      "learning_rate": 5.3468013468013464e-08,
+      "loss": 1.9992,
+      "step": 1270
+    },
+    {
+      "epoch": 7.767123287671232,
+      "grad_norm": 11524.0078125,
+      "learning_rate": 5.2121212121212124e-08,
+      "loss": 1.9299,
+      "step": 1280
+    },
+    {
+      "epoch": 7.828006088280061,
+      "grad_norm": 9651.0849609375,
+      "learning_rate": 5.077441077441077e-08,
+      "loss": 1.849,
+      "step": 1290
+    },
+    {
+      "epoch": 7.888888888888889,
+      "grad_norm": 12215.9716796875,
+      "learning_rate": 4.9427609427609425e-08,
+      "loss": 1.9062,
+      "step": 1300
+    },
+    {
+      "epoch": 7.949771689497717,
+      "grad_norm": 9862.4873046875,
+      "learning_rate": 4.808080808080808e-08,
+      "loss": 2.037,
+      "step": 1310
+    },
+    {
+      "epoch": 8.006088280060883,
+      "grad_norm": 8664.2333984375,
+      "learning_rate": 4.673400673400673e-08,
+      "loss": 2.0005,
+      "step": 1320
+    },
+    {
+      "epoch": 8.066971080669711,
+      "grad_norm": 11388.3916015625,
+      "learning_rate": 4.5387205387205386e-08,
+      "loss": 1.8947,
+      "step": 1330
+    },
+    {
+      "epoch": 8.127853881278538,
+      "grad_norm": 10665.3232421875,
+      "learning_rate": 4.404040404040404e-08,
+      "loss": 1.8415,
+      "step": 1340
+    },
+    {
+      "epoch": 8.188736681887367,
+      "grad_norm": 10964.359375,
+      "learning_rate": 4.2693602693602693e-08,
+      "loss": 1.8473,
+      "step": 1350
+    },
+    {
+      "epoch": 8.249619482496195,
+      "grad_norm": 9963.1298828125,
+      "learning_rate": 4.134680134680135e-08,
+      "loss": 1.7807,
+      "step": 1360
+    },
+    {
+      "epoch": 8.310502283105023,
+      "grad_norm": 12549.642578125,
+      "learning_rate": 4e-08,
+      "loss": 1.815,
+      "step": 1370
+    },
+    {
+      "epoch": 8.37138508371385,
+      "grad_norm": 11064.408203125,
+      "learning_rate": 3.865319865319865e-08,
+      "loss": 1.8857,
+      "step": 1380
+    },
+    {
+      "epoch": 8.432267884322679,
+      "grad_norm": 13068.6435546875,
+      "learning_rate": 3.73063973063973e-08,
+      "loss": 1.8759,
+      "step": 1390
+    },
+    {
+      "epoch": 8.493150684931507,
+      "grad_norm": 9904.9130859375,
+      "learning_rate": 3.5959595959595955e-08,
+      "loss": 1.9724,
+      "step": 1400
+    },
+    {
+      "epoch": 8.554033485540335,
+      "grad_norm": 11745.4697265625,
+      "learning_rate": 3.461279461279461e-08,
+      "loss": 1.8481,
+      "step": 1410
+    },
+    {
+      "epoch": 8.614916286149162,
+      "grad_norm": 10344.3388671875,
+      "learning_rate": 3.326599326599326e-08,
+      "loss": 1.9,
+      "step": 1420
+    },
+    {
+      "epoch": 8.67579908675799,
+      "grad_norm": 12014.765625,
+      "learning_rate": 3.1919191919191916e-08,
+      "loss": 1.8255,
+      "step": 1430
+    },
+    {
+      "epoch": 8.736681887366819,
+      "grad_norm": 10758.5947265625,
+      "learning_rate": 3.057239057239057e-08,
+      "loss": 1.909,
+      "step": 1440
+    },
+    {
+      "epoch": 8.797564687975648,
+      "grad_norm": 11520.53125,
+      "learning_rate": 2.9225589225589227e-08,
+      "loss": 1.8298,
+      "step": 1450
+    },
+    {
+      "epoch": 8.858447488584474,
+      "grad_norm": 9759.4873046875,
+      "learning_rate": 2.787878787878788e-08,
+      "loss": 1.8486,
+      "step": 1460
+    },
+    {
+      "epoch": 8.919330289193303,
+      "grad_norm": 11182.212890625,
+      "learning_rate": 2.6531986531986535e-08,
+      "loss": 1.7386,
+      "step": 1470
+    },
+    {
+      "epoch": 8.980213089802131,
+      "grad_norm": 12480.6689453125,
+      "learning_rate": 2.5185185185185182e-08,
+      "loss": 1.8489,
+      "step": 1480
+    },
+    {
+      "epoch": 9.036529680365296,
+      "grad_norm": 12609.5810546875,
+      "learning_rate": 2.383838383838384e-08,
+      "loss": 1.8636,
+      "step": 1490
+    },
+    {
+      "epoch": 9.097412480974125,
+      "grad_norm": 10469.3212890625,
+      "learning_rate": 2.249158249158249e-08,
+      "loss": 1.7988,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1650,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 1.107607832223601e+17,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c09c4d184ae529e4b03d240dc5ca0716c67e78523baa7d9a9ed621a4fad68f
+size 5816