Upload checkpoint-125 (shard 0, 0:500)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,210 @@
----
-license: mit
----
+---
+base_model: karanjaWakaba/Fundi-gemma-3-4b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:karanjaWakaba/Fundi-gemma-3-4b-it
+- 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 0.18.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForConditionalGeneration",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "karanjaWakaba/Fundi-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": 16,
+  "lora_bias": false,
+  "lora_dropout": 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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4053b5408c0a74d6a5641833304cc8d45f2e0b90e5943ba1bcdaed80349240b1
+size 154116312

added_tokens.json

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

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 -%}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8721c919ba3a881aac13bc0ed429e8b58d2505eb84f9c9b0fea3ffb4bc761fb
+size 308668611

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8903d53b9e10f8ff419a13f0d896f7a9b4b4bc1d5992dc1a59ea7fb6ee1ada7d
+size 1465

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4fdaea8f34bfe56f80c1e60bbf519ec05b18fc908f8a90e3c6f9aab17a5e417
+size 33384823

tokenizer.model

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

trainer_state.json

@@ -0,0 +1,909 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 25.793832778930664,
+      "learning_rate": 0.0,
+      "loss": 6.584,
+      "step": 1
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 13.568841934204102,
+      "learning_rate": 5e-05,
+      "loss": 6.6522,
+      "step": 2
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 11.561059951782227,
+      "learning_rate": 0.0001,
+      "loss": 5.9642,
+      "step": 3
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 5.680331707000732,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.9425,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.546603202819824,
+      "learning_rate": 0.0002,
+      "loss": 4.326,
+      "step": 5
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 4.473374366760254,
+      "learning_rate": 0.00019996629653035126,
+      "loss": 3.3931,
+      "step": 6
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 2.3445334434509277,
+      "learning_rate": 0.00019986520883988232,
+      "loss": 2.5561,
+      "step": 7
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.068652629852295,
+      "learning_rate": 0.00019969680506871137,
+      "loss": 2.3971,
+      "step": 8
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 2.5447134971618652,
+      "learning_rate": 0.00019946119873266613,
+      "loss": 2.2805,
+      "step": 9
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.117267370223999,
+      "learning_rate": 0.00019915854864676664,
+      "loss": 2.0018,
+      "step": 10
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 2.8068959712982178,
+      "learning_rate": 0.00019878905881817252,
+      "loss": 1.595,
+      "step": 11
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2.6068270206451416,
+      "learning_rate": 0.00019835297830866826,
+      "loss": 1.3036,
+      "step": 12
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 2.610274076461792,
+      "learning_rate": 0.00019785060106677818,
+      "loss": 1.158,
+      "step": 13
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 1.9986518621444702,
+      "learning_rate": 0.00019728226572962473,
+      "loss": 1.0842,
+      "step": 14
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.960787534713745,
+      "learning_rate": 0.0001966483553946637,
+      "loss": 0.6865,
+      "step": 15
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.8033719062805176,
+      "learning_rate": 0.00019594929736144976,
+      "loss": 0.9723,
+      "step": 16
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 1.8416571617126465,
+      "learning_rate": 0.00019518556284360696,
+      "loss": 0.5046,
+      "step": 17
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 2.130685329437256,
+      "learning_rate": 0.0001943576666511982,
+      "loss": 0.6281,
+      "step": 18
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 1.495326280593872,
+      "learning_rate": 0.0001934661668437073,
+      "loss": 0.5963,
+      "step": 19
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.3207380771636963,
+      "learning_rate": 0.0001925116643538684,
+      "loss": 0.5284,
+      "step": 20
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 1.107489824295044,
+      "learning_rate": 0.00019149480258259533,
+      "loss": 0.5401,
+      "step": 21
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 1.3609563112258911,
+      "learning_rate": 0.00019041626696528503,
+      "loss": 0.5235,
+      "step": 22
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 1.9667028188705444,
+      "learning_rate": 0.0001892767845097864,
+      "loss": 0.6937,
+      "step": 23
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 1.5321439504623413,
+      "learning_rate": 0.00018807712330634642,
+      "loss": 0.634,
+      "step": 24
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.942885398864746,
+      "learning_rate": 0.0001868180920098644,
+      "loss": 0.5873,
+      "step": 25
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 1.4890539646148682,
+      "learning_rate": 0.00018550053929480202,
+      "loss": 0.3326,
+      "step": 26
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 1.4116085767745972,
+      "learning_rate": 0.00018412535328311814,
+      "loss": 0.5479,
+      "step": 27
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 3.1542837619781494,
+      "learning_rate": 0.0001826934609456129,
+      "loss": 0.7073,
+      "step": 28
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 1.3499246835708618,
+      "learning_rate": 0.00018120582747708502,
+      "loss": 0.401,
+      "step": 29
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.8711500763893127,
+      "learning_rate": 0.0001796634556457236,
+      "loss": 0.3248,
+      "step": 30
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 1.7886465787887573,
+      "learning_rate": 0.0001780673851171728,
+      "loss": 0.2482,
+      "step": 31
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.8746187686920166,
+      "learning_rate": 0.00017641869175372493,
+      "loss": 0.4221,
+      "step": 32
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 1.0862362384796143,
+      "learning_rate": 0.00017471848688911464,
+      "loss": 0.5361,
+      "step": 33
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 1.3110648393630981,
+      "learning_rate": 0.000172967916579403,
+      "loss": 0.4763,
+      "step": 34
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.766996443271637,
+      "learning_rate": 0.00017116816083045602,
+      "loss": 0.3516,
+      "step": 35
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.752439022064209,
+      "learning_rate": 0.0001693204328025389,
+      "loss": 0.2962,
+      "step": 36
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.7569783329963684,
+      "learning_rate": 0.00016742597799256182,
+      "loss": 0.3195,
+      "step": 37
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.8362028002738953,
+      "learning_rate": 0.00016548607339452853,
+      "loss": 0.3789,
+      "step": 38
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 1.3477740287780762,
+      "learning_rate": 0.00016350202663875386,
+      "loss": 0.4758,
+      "step": 39
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.0475071668624878,
+      "learning_rate": 0.0001614751751104301,
+      "loss": 0.3537,
+      "step": 40
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 1.4833306074142456,
+      "learning_rate": 0.00015940688504813662,
+      "loss": 0.6678,
+      "step": 41
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.8795812726020813,
+      "learning_rate": 0.00015729855062290022,
+      "loss": 0.334,
+      "step": 42
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.7298890352249146,
+      "learning_rate": 0.00015515159299842707,
+      "loss": 0.3561,
+      "step": 43
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.7962450385093689,
+      "learning_rate": 0.00015296745937313987,
+      "loss": 0.2704,
+      "step": 44
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.8491911888122559,
+      "learning_rate": 0.00015074762200466556,
+      "loss": 0.2358,
+      "step": 45
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.7416512370109558,
+      "learning_rate": 0.00014849357721743168,
+      "loss": 0.2971,
+      "step": 46
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.4766864776611328,
+      "learning_rate": 0.00014620684439403962,
+      "loss": 0.1689,
+      "step": 47
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.8100759387016296,
+      "learning_rate": 0.0001438889649510956,
+      "loss": 0.2251,
+      "step": 48
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.9556536078453064,
+      "learning_rate": 0.00014154150130018866,
+      "loss": 0.2489,
+      "step": 49
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3303494453430176,
+      "learning_rate": 0.00013916603579471705,
+      "loss": 0.4159,
+      "step": 50
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 1.3591687679290771,
+      "learning_rate": 0.000136764169663272,
+      "loss": 0.472,
+      "step": 51
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.9764088988304138,
+      "learning_rate": 0.00013433752193029886,
+      "loss": 0.3542,
+      "step": 52
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 2.5439016819000244,
+      "learning_rate": 0.00013188772832476188,
+      "loss": 0.2969,
+      "step": 53
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 1.1185020208358765,
+      "learning_rate": 0.00012941644017754964,
+      "loss": 0.8427,
+      "step": 54
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.8044344782829285,
+      "learning_rate": 0.00012692532330836346,
+      "loss": 0.3605,
+      "step": 55
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 1.0738575458526611,
+      "learning_rate": 0.00012441605690283915,
+      "loss": 0.6313,
+      "step": 56
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.7780060172080994,
+      "learning_rate": 0.0001218903323806595,
+      "loss": 0.2993,
+      "step": 57
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 1.107829213142395,
+      "learning_rate": 0.00011934985225541998,
+      "loss": 0.4604,
+      "step": 58
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.8053715229034424,
+      "learning_rate": 0.00011679632898701649,
+      "loss": 0.422,
+      "step": 59
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9035547971725464,
+      "learning_rate": 0.00011423148382732853,
+      "loss": 0.4498,
+      "step": 60
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.9326309561729431,
+      "learning_rate": 0.00011165704565997593,
+      "loss": 0.2175,
+      "step": 61
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.9421969056129456,
+      "learning_rate": 0.00010907474983493144,
+      "loss": 0.3126,
+      "step": 62
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.8789677619934082,
+      "learning_rate": 0.0001064863369987743,
+      "loss": 0.2643,
+      "step": 63
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.811412513256073,
+      "learning_rate": 0.00010389355192137377,
+      "loss": 0.2758,
+      "step": 64
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.807129442691803,
+      "learning_rate": 0.0001012981423197931,
+      "loss": 0.3874,
+      "step": 65
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 1.8044140338897705,
+      "learning_rate": 9.870185768020693e-05,
+      "loss": 1.0087,
+      "step": 66
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6637558341026306,
+      "learning_rate": 9.610644807862625e-05,
+      "loss": 0.2891,
+      "step": 67
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.8017358779907227,
+      "learning_rate": 9.35136630012257e-05,
+      "loss": 0.3787,
+      "step": 68
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.7182633280754089,
+      "learning_rate": 9.092525016506858e-05,
+      "loss": 0.2114,
+      "step": 69
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0652369260787964,
+      "learning_rate": 8.83429543400241e-05,
+      "loss": 0.6665,
+      "step": 70
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 2.6918482780456543,
+      "learning_rate": 8.57685161726715e-05,
+      "loss": 0.4555,
+      "step": 71
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 1.1191420555114746,
+      "learning_rate": 8.320367101298351e-05,
+      "loss": 0.2852,
+      "step": 72
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.9481638073921204,
+      "learning_rate": 8.065014774458003e-05,
+      "loss": 0.2524,
+      "step": 73
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.6806588768959045,
+      "learning_rate": 7.810966761934053e-05,
+      "loss": 0.2967,
+      "step": 74
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.9989390969276428,
+      "learning_rate": 7.558394309716088e-05,
+      "loss": 0.4744,
+      "step": 75
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 1.010926365852356,
+      "learning_rate": 7.307467669163655e-05,
+      "loss": 0.4361,
+      "step": 76
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 1.8283597230911255,
+      "learning_rate": 7.058355982245037e-05,
+      "loss": 0.2773,
+      "step": 77
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.5690564513206482,
+      "learning_rate": 6.811227167523815e-05,
+      "loss": 0.1639,
+      "step": 78
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6089824438095093,
+      "learning_rate": 6.566247806970119e-05,
+      "loss": 0.1559,
+      "step": 79
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.7581542730331421,
+      "learning_rate": 6.323583033672799e-05,
+      "loss": 0.1544,
+      "step": 80
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 1.0674035549163818,
+      "learning_rate": 6.083396420528298e-05,
+      "loss": 0.2147,
+      "step": 81
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.703313946723938,
+      "learning_rate": 5.845849869981137e-05,
+      "loss": 0.1857,
+      "step": 82
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.8968911170959473,
+      "learning_rate": 5.611103504890444e-05,
+      "loss": 0.3395,
+      "step": 83
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.9625732898712158,
+      "learning_rate": 5.379315560596038e-05,
+      "loss": 0.5385,
+      "step": 84
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5642362833023071,
+      "learning_rate": 5.1506422782568345e-05,
+      "loss": 0.2009,
+      "step": 85
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.9801595211029053,
+      "learning_rate": 4.9252377995334444e-05,
+      "loss": 0.3329,
+      "step": 86
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 1.0322242975234985,
+      "learning_rate": 4.703254062686017e-05,
+      "loss": 0.6369,
+      "step": 87
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.7713143229484558,
+      "learning_rate": 4.484840700157295e-05,
+      "loss": 0.2155,
+      "step": 88
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.9648834466934204,
+      "learning_rate": 4.270144937709981e-05,
+      "loss": 0.7433,
+      "step": 89
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.6654515266418457,
+      "learning_rate": 4.059311495186338e-05,
+      "loss": 0.3375,
+      "step": 90
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 1.130812644958496,
+      "learning_rate": 3.852482488956992e-05,
+      "loss": 0.1846,
+      "step": 91
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 1.4182406663894653,
+      "learning_rate": 3.649797336124615e-05,
+      "loss": 0.3651,
+      "step": 92
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.936773955821991,
+      "learning_rate": 3.45139266054715e-05,
+      "loss": 0.417,
+      "step": 93
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 1.4703994989395142,
+      "learning_rate": 3.257402200743821e-05,
+      "loss": 0.3177,
+      "step": 94
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.689566969871521,
+      "learning_rate": 3.0679567197461134e-05,
+      "loss": 0.2653,
+      "step": 95
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.7440553307533264,
+      "learning_rate": 2.8831839169543996e-05,
+      "loss": 0.3188,
+      "step": 96
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.900610625743866,
+      "learning_rate": 2.7032083420597e-05,
+      "loss": 0.1997,
+      "step": 97
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 1.7975131273269653,
+      "learning_rate": 2.528151311088537e-05,
+      "loss": 0.4677,
+      "step": 98
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 3.3086400032043457,
+      "learning_rate": 2.3581308246275103e-05,
+      "loss": 0.389,
+      "step": 99
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8635153770446777,
+      "learning_rate": 2.1932614882827197e-05,
+      "loss": 0.2616,
+      "step": 100
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7538619637489319,
+      "learning_rate": 2.03365443542764e-05,
+      "loss": 0.3289,
+      "step": 101
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.8256278038024902,
+      "learning_rate": 1.879417252291502e-05,
+      "loss": 0.6344,
+      "step": 102
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 1.1889182329177856,
+      "learning_rate": 1.730653905438714e-05,
+      "loss": 0.3849,
+      "step": 103
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.5800666809082031,
+      "learning_rate": 1.587464671688187e-05,
+      "loss": 0.1959,
+      "step": 104
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.4363621473312378,
+      "learning_rate": 1.4499460705197998e-05,
+      "loss": 0.1956,
+      "step": 105
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.8140222430229187,
+      "learning_rate": 1.3181907990135622e-05,
+      "loss": 0.3094,
+      "step": 106
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 1.0056933164596558,
+      "learning_rate": 1.1922876693653585e-05,
+      "loss": 0.875,
+      "step": 107
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.9508771896362305,
+      "learning_rate": 1.0723215490213634e-05,
+      "loss": 0.3727,
+      "step": 108
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.8251389265060425,
+      "learning_rate": 9.583733034714981e-06,
+      "loss": 0.4169,
+      "step": 109
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8247069716453552,
+      "learning_rate": 8.505197417404687e-06,
+      "loss": 0.341,
+      "step": 110
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.8102564811706543,
+      "learning_rate": 7.488335646131628e-06,
+      "loss": 0.3859,
+      "step": 111
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 1.6328413486480713,
+      "learning_rate": 6.533833156292679e-06,
+      "loss": 0.2918,
+      "step": 112
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 1.1046022176742554,
+      "learning_rate": 5.6423333488018095e-06,
+      "loss": 0.5513,
+      "step": 113
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7437154054641724,
+      "learning_rate": 4.8144371563930476e-06,
+      "loss": 0.2759,
+      "step": 114
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.2430754899978638,
+      "learning_rate": 4.050702638550275e-06,
+      "loss": 0.315,
+      "step": 115
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 1.0340789556503296,
+      "learning_rate": 3.3516446053363015e-06,
+      "loss": 0.2041,
+      "step": 116
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7553964853286743,
+      "learning_rate": 2.717734270375272e-06,
+      "loss": 0.3513,
+      "step": 117
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.9530523419380188,
+      "learning_rate": 2.1493989332218468e-06,
+      "loss": 0.4893,
+      "step": 118
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 1.7030022144317627,
+      "learning_rate": 1.6470216913317626e-06,
+      "loss": 0.3728,
+      "step": 119
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.7979387044906616,
+      "learning_rate": 1.2109411818274852e-06,
+      "loss": 0.2825,
+      "step": 120
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.9357576966285706,
+      "learning_rate": 8.41451353233369e-07,
+      "loss": 0.3145,
+      "step": 121
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.8759410381317139,
+      "learning_rate": 5.388012673338661e-07,
+      "loss": 0.3718,
+      "step": 122
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.7602233290672302,
+      "learning_rate": 3.0319493128866396e-07,
+      "loss": 0.2441,
+      "step": 123
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 1.2068487405776978,
+      "learning_rate": 1.3479116011769767e-07,
+      "loss": 0.3679,
+      "step": 124
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7169966697692871,
+      "learning_rate": 3.370346964876036e-08,
+      "loss": 0.266,
+      "step": 125
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 125,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 125,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3973327050904512.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40d350bfec45018ae1621af4a1ca5a142f9f858ced223be889bace9317bdc25
+size 6353