Training in progress, step 239, checkpoint

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: fxmarty/tiny-llama-fast-tokenizer
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "fxmarty/tiny-llama-fast-tokenizer",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad1d51c0c62f663d5cfc954237eb7f6f6ca25163717e837ddb7bc79f6b9308c
+size 2145944

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec12caee61a04b8933a404348688d2d65263cca8a255b060c859ca4b9cc1e60
+size 4310020

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0646a489ccdba05a51f0107a16da30f50177123790a8193e0041fab683741f31
+size 14960

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29faad77f51b7ec07d0f8a439d74ae5220f376992313cafa15eb1fc33eba6246
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d2c4ebb06be4c500f26eb0d63f36fad2c451d01baa2e6e6d37fb173438178e6
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef6fcddbb9a9fb63c9d7db56891f36b802c1137bf86d17a2d09a85e0a230ada
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c6fb109a04b755b3d205df40095bae8e9e2747d3f4c48a4c29e1751341e23b
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1706 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3297688858226975,
+  "eval_steps": 500,
+  "global_step": 239,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013797861331493618,
+      "grad_norm": 0.37928757071495056,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 10.3875,
+      "step": 1
+    },
+    {
+      "epoch": 0.0027595722662987236,
+      "grad_norm": 0.4158506393432617,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 10.3804,
+      "step": 2
+    },
+    {
+      "epoch": 0.004139358399448086,
+      "grad_norm": 0.4176561236381531,
+      "learning_rate": 3e-06,
+      "loss": 10.3729,
+      "step": 3
+    },
+    {
+      "epoch": 0.005519144532597447,
+      "grad_norm": 0.4464573562145233,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 10.3778,
+      "step": 4
+    },
+    {
+      "epoch": 0.006898930665746809,
+      "grad_norm": 0.4155403673648834,
+      "learning_rate": 5e-06,
+      "loss": 10.3817,
+      "step": 5
+    },
+    {
+      "epoch": 0.008278716798896172,
+      "grad_norm": 0.4856280982494354,
+      "learning_rate": 6e-06,
+      "loss": 10.3782,
+      "step": 6
+    },
+    {
+      "epoch": 0.009658502932045532,
+      "grad_norm": 0.4716717600822449,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 10.3727,
+      "step": 7
+    },
+    {
+      "epoch": 0.011038289065194894,
+      "grad_norm": 0.4803764820098877,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 10.3701,
+      "step": 8
+    },
+    {
+      "epoch": 0.012418075198344257,
+      "grad_norm": 0.4964543282985687,
+      "learning_rate": 9e-06,
+      "loss": 10.3719,
+      "step": 9
+    },
+    {
+      "epoch": 0.013797861331493619,
+      "grad_norm": 0.5420424938201904,
+      "learning_rate": 1e-05,
+      "loss": 10.3879,
+      "step": 10
+    },
+    {
+      "epoch": 0.015177647464642981,
+      "grad_norm": 0.5523043274879456,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 10.3767,
+      "step": 11
+    },
+    {
+      "epoch": 0.016557433597792343,
+      "grad_norm": 0.5524217486381531,
+      "learning_rate": 1.2e-05,
+      "loss": 10.3849,
+      "step": 12
+    },
+    {
+      "epoch": 0.017937219730941704,
+      "grad_norm": 0.47942158579826355,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 10.3652,
+      "step": 13
+    },
+    {
+      "epoch": 0.019317005864091064,
+      "grad_norm": 0.3707212805747986,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 10.3772,
+      "step": 14
+    },
+    {
+      "epoch": 0.020696791997240428,
+      "grad_norm": 0.43476638197898865,
+      "learning_rate": 1.5e-05,
+      "loss": 10.3805,
+      "step": 15
+    },
+    {
+      "epoch": 0.02207657813038979,
+      "grad_norm": 0.44521450996398926,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 10.3757,
+      "step": 16
+    },
+    {
+      "epoch": 0.023456364263539153,
+      "grad_norm": 0.5112989544868469,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 10.3853,
+      "step": 17
+    },
+    {
+      "epoch": 0.024836150396688513,
+      "grad_norm": 0.48292139172554016,
+      "learning_rate": 1.8e-05,
+      "loss": 10.3791,
+      "step": 18
+    },
+    {
+      "epoch": 0.026215936529837874,
+      "grad_norm": 0.46689826250076294,
+      "learning_rate": 1.9e-05,
+      "loss": 10.3874,
+      "step": 19
+    },
+    {
+      "epoch": 0.027595722662987238,
+      "grad_norm": 0.4777892231941223,
+      "learning_rate": 2e-05,
+      "loss": 10.3751,
+      "step": 20
+    },
+    {
+      "epoch": 0.028975508796136598,
+      "grad_norm": 0.5070079565048218,
+      "learning_rate": 2.1e-05,
+      "loss": 10.3844,
+      "step": 21
+    },
+    {
+      "epoch": 0.030355294929285962,
+      "grad_norm": 0.5363792181015015,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 10.3806,
+      "step": 22
+    },
+    {
+      "epoch": 0.03173508106243532,
+      "grad_norm": 0.5464498400688171,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 10.3758,
+      "step": 23
+    },
+    {
+      "epoch": 0.03311486719558469,
+      "grad_norm": 0.6037337779998779,
+      "learning_rate": 2.4e-05,
+      "loss": 10.3716,
+      "step": 24
+    },
+    {
+      "epoch": 0.03449465332873405,
+      "grad_norm": 0.6836243867874146,
+      "learning_rate": 2.5e-05,
+      "loss": 10.3811,
+      "step": 25
+    },
+    {
+      "epoch": 0.03587443946188341,
+      "grad_norm": 0.3856373727321625,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 10.3743,
+      "step": 26
+    },
+    {
+      "epoch": 0.03725422559503277,
+      "grad_norm": 0.40399476885795593,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 10.3781,
+      "step": 27
+    },
+    {
+      "epoch": 0.03863401172818213,
+      "grad_norm": 0.45152705907821655,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 10.3788,
+      "step": 28
+    },
+    {
+      "epoch": 0.040013797861331496,
+      "grad_norm": 0.4663512110710144,
+      "learning_rate": 2.9e-05,
+      "loss": 10.3869,
+      "step": 29
+    },
+    {
+      "epoch": 0.041393583994480856,
+      "grad_norm": 0.494383305311203,
+      "learning_rate": 3e-05,
+      "loss": 10.3756,
+      "step": 30
+    },
+    {
+      "epoch": 0.04277337012763022,
+      "grad_norm": 0.48948773741722107,
+      "learning_rate": 3.1e-05,
+      "loss": 10.3787,
+      "step": 31
+    },
+    {
+      "epoch": 0.04415315626077958,
+      "grad_norm": 0.45743992924690247,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 10.3724,
+      "step": 32
+    },
+    {
+      "epoch": 0.04553294239392894,
+      "grad_norm": 0.4397124946117401,
+      "learning_rate": 3.3e-05,
+      "loss": 10.3667,
+      "step": 33
+    },
+    {
+      "epoch": 0.046912728527078305,
+      "grad_norm": 0.5066558122634888,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 10.3686,
+      "step": 34
+    },
+    {
+      "epoch": 0.048292514660227666,
+      "grad_norm": 0.5163968801498413,
+      "learning_rate": 3.5e-05,
+      "loss": 10.3699,
+      "step": 35
+    },
+    {
+      "epoch": 0.049672300793377026,
+      "grad_norm": 0.6014847159385681,
+      "learning_rate": 3.6e-05,
+      "loss": 10.373,
+      "step": 36
+    },
+    {
+      "epoch": 0.05105208692652639,
+      "grad_norm": 0.5788203477859497,
+      "learning_rate": 3.7e-05,
+      "loss": 10.3686,
+      "step": 37
+    },
+    {
+      "epoch": 0.05243187305967575,
+      "grad_norm": 0.4628985524177551,
+      "learning_rate": 3.8e-05,
+      "loss": 10.3772,
+      "step": 38
+    },
+    {
+      "epoch": 0.053811659192825115,
+      "grad_norm": 0.4443260133266449,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 10.3745,
+      "step": 39
+    },
+    {
+      "epoch": 0.055191445325974475,
+      "grad_norm": 0.42313191294670105,
+      "learning_rate": 4e-05,
+      "loss": 10.3679,
+      "step": 40
+    },
+    {
+      "epoch": 0.056571231459123836,
+      "grad_norm": 0.4354301691055298,
+      "learning_rate": 4.1e-05,
+      "loss": 10.3646,
+      "step": 41
+    },
+    {
+      "epoch": 0.057951017592273196,
+      "grad_norm": 0.45086437463760376,
+      "learning_rate": 4.2e-05,
+      "loss": 10.377,
+      "step": 42
+    },
+    {
+      "epoch": 0.05933080372542256,
+      "grad_norm": 0.4813697040081024,
+      "learning_rate": 4.3e-05,
+      "loss": 10.3761,
+      "step": 43
+    },
+    {
+      "epoch": 0.060710589858571924,
+      "grad_norm": 0.46686020493507385,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 10.3674,
+      "step": 44
+    },
+    {
+      "epoch": 0.062090375991721285,
+      "grad_norm": 0.5052739381790161,
+      "learning_rate": 4.5e-05,
+      "loss": 10.3637,
+      "step": 45
+    },
+    {
+      "epoch": 0.06347016212487064,
+      "grad_norm": 0.5201326012611389,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 10.3658,
+      "step": 46
+    },
+    {
+      "epoch": 0.06484994825802001,
+      "grad_norm": 0.536177933216095,
+      "learning_rate": 4.7e-05,
+      "loss": 10.3699,
+      "step": 47
+    },
+    {
+      "epoch": 0.06622973439116937,
+      "grad_norm": 0.5888517498970032,
+      "learning_rate": 4.8e-05,
+      "loss": 10.3689,
+      "step": 48
+    },
+    {
+      "epoch": 0.06760952052431873,
+      "grad_norm": 0.5909680724143982,
+      "learning_rate": 4.9e-05,
+      "loss": 10.3739,
+      "step": 49
+    },
+    {
+      "epoch": 0.0689893066574681,
+      "grad_norm": 0.7720197439193726,
+      "learning_rate": 5e-05,
+      "loss": 10.3599,
+      "step": 50
+    },
+    {
+      "epoch": 0.07036909279061745,
+      "grad_norm": 0.4170343279838562,
+      "learning_rate": 5.1000000000000006e-05,
+      "loss": 10.37,
+      "step": 51
+    },
+    {
+      "epoch": 0.07174887892376682,
+      "grad_norm": 0.45865100622177124,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 10.3616,
+      "step": 52
+    },
+    {
+      "epoch": 0.07312866505691618,
+      "grad_norm": 0.4740890562534332,
+      "learning_rate": 5.300000000000001e-05,
+      "loss": 10.3721,
+      "step": 53
+    },
+    {
+      "epoch": 0.07450845119006554,
+      "grad_norm": 0.44731295108795166,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 10.3611,
+      "step": 54
+    },
+    {
+      "epoch": 0.0758882373232149,
+      "grad_norm": 0.5211865305900574,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.359,
+      "step": 55
+    },
+    {
+      "epoch": 0.07726802345636426,
+      "grad_norm": 0.49909907579421997,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 10.3668,
+      "step": 56
+    },
+    {
+      "epoch": 0.07864780958951363,
+      "grad_norm": 0.5443109273910522,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 10.3489,
+      "step": 57
+    },
+    {
+      "epoch": 0.08002759572266299,
+      "grad_norm": 0.554502546787262,
+      "learning_rate": 5.8e-05,
+      "loss": 10.3692,
+      "step": 58
+    },
+    {
+      "epoch": 0.08140738185581235,
+      "grad_norm": 0.6308146119117737,
+      "learning_rate": 5.9e-05,
+      "loss": 10.3573,
+      "step": 59
+    },
+    {
+      "epoch": 0.08278716798896171,
+      "grad_norm": 0.6720134019851685,
+      "learning_rate": 6e-05,
+      "loss": 10.3514,
+      "step": 60
+    },
+    {
+      "epoch": 0.08416695412211107,
+      "grad_norm": 0.748083770275116,
+      "learning_rate": 6.1e-05,
+      "loss": 10.3545,
+      "step": 61
+    },
+    {
+      "epoch": 0.08554674025526043,
+      "grad_norm": 0.8078204989433289,
+      "learning_rate": 6.2e-05,
+      "loss": 10.3506,
+      "step": 62
+    },
+    {
+      "epoch": 0.0869265263884098,
+      "grad_norm": 0.5997583270072937,
+      "learning_rate": 6.3e-05,
+      "loss": 10.3588,
+      "step": 63
+    },
+    {
+      "epoch": 0.08830631252155915,
+      "grad_norm": 0.5249990820884705,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 10.3635,
+      "step": 64
+    },
+    {
+      "epoch": 0.08968609865470852,
+      "grad_norm": 0.5661075115203857,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 10.3594,
+      "step": 65
+    },
+    {
+      "epoch": 0.09106588478785788,
+      "grad_norm": 0.5764796137809753,
+      "learning_rate": 6.6e-05,
+      "loss": 10.351,
+      "step": 66
+    },
+    {
+      "epoch": 0.09244567092100725,
+      "grad_norm": 0.6323254108428955,
+      "learning_rate": 6.7e-05,
+      "loss": 10.357,
+      "step": 67
+    },
+    {
+      "epoch": 0.09382545705415661,
+      "grad_norm": 0.6489927172660828,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 10.3467,
+      "step": 68
+    },
+    {
+      "epoch": 0.09520524318730597,
+      "grad_norm": 0.7028964757919312,
+      "learning_rate": 6.9e-05,
+      "loss": 10.3459,
+      "step": 69
+    },
+    {
+      "epoch": 0.09658502932045533,
+      "grad_norm": 0.7597895264625549,
+      "learning_rate": 7e-05,
+      "loss": 10.3482,
+      "step": 70
+    },
+    {
+      "epoch": 0.09796481545360469,
+      "grad_norm": 0.8057466149330139,
+      "learning_rate": 7.1e-05,
+      "loss": 10.3374,
+      "step": 71
+    },
+    {
+      "epoch": 0.09934460158675405,
+      "grad_norm": 0.8530853390693665,
+      "learning_rate": 7.2e-05,
+      "loss": 10.3444,
+      "step": 72
+    },
+    {
+      "epoch": 0.10072438771990341,
+      "grad_norm": 0.9716468453407288,
+      "learning_rate": 7.3e-05,
+      "loss": 10.3242,
+      "step": 73
+    },
+    {
+      "epoch": 0.10210417385305277,
+      "grad_norm": 1.105352759361267,
+      "learning_rate": 7.4e-05,
+      "loss": 10.3172,
+      "step": 74
+    },
+    {
+      "epoch": 0.10348395998620213,
+      "grad_norm": 1.2654082775115967,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3131,
+      "step": 75
+    },
+    {
+      "epoch": 0.1048637461193515,
+      "grad_norm": 0.7005993723869324,
+      "learning_rate": 7.6e-05,
+      "loss": 10.3454,
+      "step": 76
+    },
+    {
+      "epoch": 0.10624353225250087,
+      "grad_norm": 0.8157169222831726,
+      "learning_rate": 7.7e-05,
+      "loss": 10.328,
+      "step": 77
+    },
+    {
+      "epoch": 0.10762331838565023,
+      "grad_norm": 0.8883787989616394,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 10.3259,
+      "step": 78
+    },
+    {
+      "epoch": 0.10900310451879959,
+      "grad_norm": 0.9492635130882263,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 10.3214,
+      "step": 79
+    },
+    {
+      "epoch": 0.11038289065194895,
+      "grad_norm": 0.8827070593833923,
+      "learning_rate": 8e-05,
+      "loss": 10.3172,
+      "step": 80
+    },
+    {
+      "epoch": 0.11176267678509831,
+      "grad_norm": 1.0507211685180664,
+      "learning_rate": 8.1e-05,
+      "loss": 10.3165,
+      "step": 81
+    },
+    {
+      "epoch": 0.11314246291824767,
+      "grad_norm": 1.1131185293197632,
+      "learning_rate": 8.2e-05,
+      "loss": 10.3091,
+      "step": 82
+    },
+    {
+      "epoch": 0.11452224905139703,
+      "grad_norm": 1.1873068809509277,
+      "learning_rate": 8.3e-05,
+      "loss": 10.2996,
+      "step": 83
+    },
+    {
+      "epoch": 0.11590203518454639,
+      "grad_norm": 1.1595804691314697,
+      "learning_rate": 8.4e-05,
+      "loss": 10.2908,
+      "step": 84
+    },
+    {
+      "epoch": 0.11728182131769575,
+      "grad_norm": 1.2971093654632568,
+      "learning_rate": 8.5e-05,
+      "loss": 10.2807,
+      "step": 85
+    },
+    {
+      "epoch": 0.11866160745084511,
+      "grad_norm": 1.3693597316741943,
+      "learning_rate": 8.6e-05,
+      "loss": 10.2609,
+      "step": 86
+    },
+    {
+      "epoch": 0.12004139358399447,
+      "grad_norm": 1.4227279424667358,
+      "learning_rate": 8.7e-05,
+      "loss": 10.237,
+      "step": 87
+    },
+    {
+      "epoch": 0.12142117971714385,
+      "grad_norm": 1.0355181694030762,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 10.2805,
+      "step": 88
+    },
+    {
+      "epoch": 0.12280096585029321,
+      "grad_norm": 1.0092841386795044,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 10.2912,
+      "step": 89
+    },
+    {
+      "epoch": 0.12418075198344257,
+      "grad_norm": 1.089247465133667,
+      "learning_rate": 9e-05,
+      "loss": 10.2767,
+      "step": 90
+    },
+    {
+      "epoch": 0.12556053811659193,
+      "grad_norm": 1.1349172592163086,
+      "learning_rate": 9.1e-05,
+      "loss": 10.2677,
+      "step": 91
+    },
+    {
+      "epoch": 0.12694032424974128,
+      "grad_norm": 1.1714922189712524,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 10.2609,
+      "step": 92
+    },
+    {
+      "epoch": 0.12832011038289065,
+      "grad_norm": 1.191255807876587,
+      "learning_rate": 9.300000000000001e-05,
+      "loss": 10.2532,
+      "step": 93
+    },
+    {
+      "epoch": 0.12969989651604003,
+      "grad_norm": 1.232477068901062,
+      "learning_rate": 9.4e-05,
+      "loss": 10.2439,
+      "step": 94
+    },
+    {
+      "epoch": 0.13107968264918937,
+      "grad_norm": 1.2855937480926514,
+      "learning_rate": 9.5e-05,
+      "loss": 10.2264,
+      "step": 95
+    },
+    {
+      "epoch": 0.13245946878233875,
+      "grad_norm": 1.232479453086853,
+      "learning_rate": 9.6e-05,
+      "loss": 10.2317,
+      "step": 96
+    },
+    {
+      "epoch": 0.1338392549154881,
+      "grad_norm": 1.3270705938339233,
+      "learning_rate": 9.7e-05,
+      "loss": 10.2043,
+      "step": 97
+    },
+    {
+      "epoch": 0.13521904104863747,
+      "grad_norm": 1.3535412549972534,
+      "learning_rate": 9.8e-05,
+      "loss": 10.1987,
+      "step": 98
+    },
+    {
+      "epoch": 0.1365988271817868,
+      "grad_norm": 1.473716378211975,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 10.183,
+      "step": 99
+    },
+    {
+      "epoch": 0.1379786133149362,
+      "grad_norm": 1.5545284748077393,
+      "learning_rate": 0.0001,
+      "loss": 10.1764,
+      "step": 100
+    },
+    {
+      "epoch": 0.13935839944808553,
+      "grad_norm": 0.9037075638771057,
+      "learning_rate": 9.999936632050037e-05,
+      "loss": 10.2408,
+      "step": 101
+    },
+    {
+      "epoch": 0.1407381855812349,
+      "grad_norm": 1.025711178779602,
+      "learning_rate": 9.999746529806349e-05,
+      "loss": 10.2258,
+      "step": 102
+    },
+    {
+      "epoch": 0.14211797171438428,
+      "grad_norm": 1.0868299007415771,
+      "learning_rate": 9.99942969808749e-05,
+      "loss": 10.219,
+      "step": 103
+    },
+    {
+      "epoch": 0.14349775784753363,
+      "grad_norm": 1.1319340467453003,
+      "learning_rate": 9.998986144924251e-05,
+      "loss": 10.2066,
+      "step": 104
+    },
+    {
+      "epoch": 0.144877543980683,
+      "grad_norm": 1.1912342309951782,
+      "learning_rate": 9.998415881559454e-05,
+      "loss": 10.1997,
+      "step": 105
+    },
+    {
+      "epoch": 0.14625733011383235,
+      "grad_norm": 1.1592702865600586,
+      "learning_rate": 9.997718922447667e-05,
+      "loss": 10.1898,
+      "step": 106
+    },
+    {
+      "epoch": 0.14763711624698173,
+      "grad_norm": 1.2085384130477905,
+      "learning_rate": 9.99689528525484e-05,
+      "loss": 10.1825,
+      "step": 107
+    },
+    {
+      "epoch": 0.14901690238013107,
+      "grad_norm": 1.211334466934204,
+      "learning_rate": 9.995944990857849e-05,
+      "loss": 10.1712,
+      "step": 108
+    },
+    {
+      "epoch": 0.15039668851328045,
+      "grad_norm": 1.3283801078796387,
+      "learning_rate": 9.994868063343981e-05,
+      "loss": 10.1671,
+      "step": 109
+    },
+    {
+      "epoch": 0.1517764746464298,
+      "grad_norm": 1.3618557453155518,
+      "learning_rate": 9.993664530010308e-05,
+      "loss": 10.1597,
+      "step": 110
+    },
+    {
+      "epoch": 0.15315626077957917,
+      "grad_norm": 1.3570090532302856,
+      "learning_rate": 9.99233442136301e-05,
+      "loss": 10.1517,
+      "step": 111
+    },
+    {
+      "epoch": 0.15453604691272851,
+      "grad_norm": 1.4205886125564575,
+      "learning_rate": 9.990877771116589e-05,
+      "loss": 10.1415,
+      "step": 112
+    },
+    {
+      "epoch": 0.1559158330458779,
+      "grad_norm": 1.2085868120193481,
+      "learning_rate": 9.989294616193017e-05,
+      "loss": 10.1706,
+      "step": 113
+    },
+    {
+      "epoch": 0.15729561917902726,
+      "grad_norm": 1.0051339864730835,
+      "learning_rate": 9.987584996720814e-05,
+      "loss": 10.1806,
+      "step": 114
+    },
+    {
+      "epoch": 0.1586754053121766,
+      "grad_norm": 1.044624924659729,
+      "learning_rate": 9.985748956034006e-05,
+      "loss": 10.1836,
+      "step": 115
+    },
+    {
+      "epoch": 0.16005519144532598,
+      "grad_norm": 1.1088407039642334,
+      "learning_rate": 9.983786540671051e-05,
+      "loss": 10.1793,
+      "step": 116
+    },
+    {
+      "epoch": 0.16143497757847533,
+      "grad_norm": 1.156091332435608,
+      "learning_rate": 9.981697800373642e-05,
+      "loss": 10.1542,
+      "step": 117
+    },
+    {
+      "epoch": 0.1628147637116247,
+      "grad_norm": 1.1839971542358398,
+      "learning_rate": 9.979482788085454e-05,
+      "loss": 10.1521,
+      "step": 118
+    },
+    {
+      "epoch": 0.16419454984477405,
+      "grad_norm": 1.257676362991333,
+      "learning_rate": 9.977141559950807e-05,
+      "loss": 10.146,
+      "step": 119
+    },
+    {
+      "epoch": 0.16557433597792343,
+      "grad_norm": 1.2359771728515625,
+      "learning_rate": 9.974674175313228e-05,
+      "loss": 10.1465,
+      "step": 120
+    },
+    {
+      "epoch": 0.16695412211107277,
+      "grad_norm": 1.3480055332183838,
+      "learning_rate": 9.972080696713961e-05,
+      "loss": 10.1324,
+      "step": 121
+    },
+    {
+      "epoch": 0.16833390824422215,
+      "grad_norm": 1.3127009868621826,
+      "learning_rate": 9.969361189890373e-05,
+      "loss": 10.1225,
+      "step": 122
+    },
+    {
+      "epoch": 0.16971369437737152,
+      "grad_norm": 1.369981050491333,
+      "learning_rate": 9.966515723774297e-05,
+      "loss": 10.108,
+      "step": 123
+    },
+    {
+      "epoch": 0.17109348051052087,
+      "grad_norm": 1.384888768196106,
+      "learning_rate": 9.96354437049027e-05,
+      "loss": 10.1046,
+      "step": 124
+    },
+    {
+      "epoch": 0.17247326664367024,
+      "grad_norm": 1.5264196395874023,
+      "learning_rate": 9.960447205353723e-05,
+      "loss": 10.0868,
+      "step": 125
+    },
+    {
+      "epoch": 0.1738530527768196,
+      "grad_norm": 0.9188018441200256,
+      "learning_rate": 9.957224306869053e-05,
+      "loss": 10.1521,
+      "step": 126
+    },
+    {
+      "epoch": 0.17523283890996896,
+      "grad_norm": 1.0055698156356812,
+      "learning_rate": 9.953875756727651e-05,
+      "loss": 10.1447,
+      "step": 127
+    },
+    {
+      "epoch": 0.1766126250431183,
+      "grad_norm": 1.115513563156128,
+      "learning_rate": 9.95040163980582e-05,
+      "loss": 10.1354,
+      "step": 128
+    },
+    {
+      "epoch": 0.17799241117626768,
+      "grad_norm": 1.0765373706817627,
+      "learning_rate": 9.946802044162629e-05,
+      "loss": 10.1282,
+      "step": 129
+    },
+    {
+      "epoch": 0.17937219730941703,
+      "grad_norm": 1.133651852607727,
+      "learning_rate": 9.943077061037671e-05,
+      "loss": 10.1215,
+      "step": 130
+    },
+    {
+      "epoch": 0.1807519834425664,
+      "grad_norm": 1.1984049081802368,
+      "learning_rate": 9.939226784848769e-05,
+      "loss": 10.1199,
+      "step": 131
+    },
+    {
+      "epoch": 0.18213176957571575,
+      "grad_norm": 1.1945085525512695,
+      "learning_rate": 9.935251313189564e-05,
+      "loss": 10.1057,
+      "step": 132
+    },
+    {
+      "epoch": 0.18351155570886513,
+      "grad_norm": 1.28304123878479,
+      "learning_rate": 9.931150746827054e-05,
+      "loss": 10.1038,
+      "step": 133
+    },
+    {
+      "epoch": 0.1848913418420145,
+      "grad_norm": 1.3560444116592407,
+      "learning_rate": 9.92692518969903e-05,
+      "loss": 10.0773,
+      "step": 134
+    },
+    {
+      "epoch": 0.18627112797516385,
+      "grad_norm": 1.2892886400222778,
+      "learning_rate": 9.922574748911448e-05,
+      "loss": 10.0791,
+      "step": 135
+    },
+    {
+      "epoch": 0.18765091410831322,
+      "grad_norm": 1.3138704299926758,
+      "learning_rate": 9.918099534735718e-05,
+      "loss": 10.0841,
+      "step": 136
+    },
+    {
+      "epoch": 0.18903070024146257,
+      "grad_norm": 1.466147541999817,
+      "learning_rate": 9.913499660605897e-05,
+      "loss": 10.0606,
+      "step": 137
+    },
+    {
+      "epoch": 0.19041048637461194,
+      "grad_norm": 1.1251062154769897,
+      "learning_rate": 9.908775243115821e-05,
+      "loss": 10.0973,
+      "step": 138
+    },
+    {
+      "epoch": 0.1917902725077613,
+      "grad_norm": 1.0003620386123657,
+      "learning_rate": 9.903926402016153e-05,
+      "loss": 10.1169,
+      "step": 139
+    },
+    {
+      "epoch": 0.19317005864091066,
+      "grad_norm": 1.0686968564987183,
+      "learning_rate": 9.898953260211338e-05,
+      "loss": 10.116,
+      "step": 140
+    },
+    {
+      "epoch": 0.19454984477406,
+      "grad_norm": 1.1628526449203491,
+      "learning_rate": 9.8938559437565e-05,
+      "loss": 10.0882,
+      "step": 141
+    },
+    {
+      "epoch": 0.19592963090720938,
+      "grad_norm": 1.116454005241394,
+      "learning_rate": 9.888634581854234e-05,
+      "loss": 10.0891,
+      "step": 142
+    },
+    {
+      "epoch": 0.19730941704035873,
+      "grad_norm": 1.2207541465759277,
+      "learning_rate": 9.883289306851342e-05,
+      "loss": 10.075,
+      "step": 143
+    },
+    {
+      "epoch": 0.1986892031735081,
+      "grad_norm": 1.2331547737121582,
+      "learning_rate": 9.877820254235471e-05,
+      "loss": 10.0643,
+      "step": 144
+    },
+    {
+      "epoch": 0.20006898930665748,
+      "grad_norm": 1.2393301725387573,
+      "learning_rate": 9.87222756263168e-05,
+      "loss": 10.0757,
+      "step": 145
+    },
+    {
+      "epoch": 0.20144877543980683,
+      "grad_norm": 1.288958191871643,
+      "learning_rate": 9.86651137379893e-05,
+      "loss": 10.0672,
+      "step": 146
+    },
+    {
+      "epoch": 0.2028285615729562,
+      "grad_norm": 1.3286681175231934,
+      "learning_rate": 9.86067183262649e-05,
+      "loss": 10.0466,
+      "step": 147
+    },
+    {
+      "epoch": 0.20420834770610555,
+      "grad_norm": 1.352874994277954,
+      "learning_rate": 9.85470908713026e-05,
+      "loss": 10.0367,
+      "step": 148
+    },
+    {
+      "epoch": 0.20558813383925492,
+      "grad_norm": 1.4209654331207275,
+      "learning_rate": 9.848623288449025e-05,
+      "loss": 10.0265,
+      "step": 149
+    },
+    {
+      "epoch": 0.20696791997240427,
+      "grad_norm": 1.5714178085327148,
+      "learning_rate": 9.842414590840617e-05,
+      "loss": 9.9945,
+      "step": 150
+    },
+    {
+      "epoch": 0.20834770610555364,
+      "grad_norm": 0.9352539777755737,
+      "learning_rate": 9.836083151678014e-05,
+      "loss": 10.0962,
+      "step": 151
+    },
+    {
+      "epoch": 0.209727492238703,
+      "grad_norm": 1.0083916187286377,
+      "learning_rate": 9.829629131445342e-05,
+      "loss": 10.0812,
+      "step": 152
+    },
+    {
+      "epoch": 0.21110727837185236,
+      "grad_norm": 1.155738353729248,
+      "learning_rate": 9.823052693733814e-05,
+      "loss": 10.0547,
+      "step": 153
+    },
+    {
+      "epoch": 0.21248706450500174,
+      "grad_norm": 1.1547437906265259,
+      "learning_rate": 9.816354005237583e-05,
+      "loss": 10.0552,
+      "step": 154
+    },
+    {
+      "epoch": 0.21386685063815108,
+      "grad_norm": 1.1641536951065063,
+      "learning_rate": 9.809533235749507e-05,
+      "loss": 10.061,
+      "step": 155
+    },
+    {
+      "epoch": 0.21524663677130046,
+      "grad_norm": 1.2230818271636963,
+      "learning_rate": 9.802590558156862e-05,
+      "loss": 10.0426,
+      "step": 156
+    },
+    {
+      "epoch": 0.2166264229044498,
+      "grad_norm": 1.2705639600753784,
+      "learning_rate": 9.795526148436944e-05,
+      "loss": 10.0289,
+      "step": 157
+    },
+    {
+      "epoch": 0.21800620903759918,
+      "grad_norm": 1.2639011144638062,
+      "learning_rate": 9.78834018565262e-05,
+      "loss": 10.0266,
+      "step": 158
+    },
+    {
+      "epoch": 0.21938599517074853,
+      "grad_norm": 1.295678973197937,
+      "learning_rate": 9.78103285194778e-05,
+      "loss": 10.0191,
+      "step": 159
+    },
+    {
+      "epoch": 0.2207657813038979,
+      "grad_norm": 1.3106251955032349,
+      "learning_rate": 9.773604332542729e-05,
+      "loss": 10.0146,
+      "step": 160
+    },
+    {
+      "epoch": 0.22214556743704725,
+      "grad_norm": 1.3326599597930908,
+      "learning_rate": 9.766054815729482e-05,
+      "loss": 10.0172,
+      "step": 161
+    },
+    {
+      "epoch": 0.22352535357019662,
+      "grad_norm": 1.4855268001556396,
+      "learning_rate": 9.758384492867003e-05,
+      "loss": 9.9864,
+      "step": 162
+    },
+    {
+      "epoch": 0.22490513970334597,
+      "grad_norm": 1.2385770082473755,
+      "learning_rate": 9.750593558376347e-05,
+      "loss": 10.0079,
+      "step": 163
+    },
+    {
+      "epoch": 0.22628492583649534,
+      "grad_norm": 1.0151700973510742,
+      "learning_rate": 9.742682209735727e-05,
+      "loss": 10.0535,
+      "step": 164
+    },
+    {
+      "epoch": 0.22766471196964472,
+      "grad_norm": 1.0624631643295288,
+      "learning_rate": 9.73465064747553e-05,
+      "loss": 10.0475,
+      "step": 165
+    },
+    {
+      "epoch": 0.22904449810279406,
+      "grad_norm": 1.0995757579803467,
+      "learning_rate": 9.726499075173201e-05,
+      "loss": 10.0349,
+      "step": 166
+    },
+    {
+      "epoch": 0.23042428423594344,
+      "grad_norm": 1.2015033960342407,
+      "learning_rate": 9.718227699448116e-05,
+      "loss": 10.0152,
+      "step": 167
+    },
+    {
+      "epoch": 0.23180407036909279,
+      "grad_norm": 1.1979053020477295,
+      "learning_rate": 9.709836729956325e-05,
+      "loss": 10.0255,
+      "step": 168
+    },
+    {
+      "epoch": 0.23318385650224216,
+      "grad_norm": 1.2255140542984009,
+      "learning_rate": 9.701326379385238e-05,
+      "loss": 10.0096,
+      "step": 169
+    },
+    {
+      "epoch": 0.2345636426353915,
+      "grad_norm": 1.2472561597824097,
+      "learning_rate": 9.692696863448245e-05,
+      "loss": 10.0073,
+      "step": 170
+    },
+    {
+      "epoch": 0.23594342876854088,
+      "grad_norm": 1.328076958656311,
+      "learning_rate": 9.68394840087924e-05,
+      "loss": 9.983,
+      "step": 171
+    },
+    {
+      "epoch": 0.23732321490169023,
+      "grad_norm": 1.318142294883728,
+      "learning_rate": 9.675081213427076e-05,
+      "loss": 9.9967,
+      "step": 172
+    },
+    {
+      "epoch": 0.2387030010348396,
+      "grad_norm": 1.432610034942627,
+      "learning_rate": 9.66609552584995e-05,
+      "loss": 9.9658,
+      "step": 173
+    },
+    {
+      "epoch": 0.24008278716798895,
+      "grad_norm": 1.4061625003814697,
+      "learning_rate": 9.656991565909704e-05,
+      "loss": 9.9669,
+      "step": 174
+    },
+    {
+      "epoch": 0.24146257330113832,
+      "grad_norm": 1.5450146198272705,
+      "learning_rate": 9.647769564366046e-05,
+      "loss": 9.9462,
+      "step": 175
+    },
+    {
+      "epoch": 0.2428423594342877,
+      "grad_norm": 0.9310745000839233,
+      "learning_rate": 9.638429754970715e-05,
+      "loss": 10.0483,
+      "step": 176
+    },
+    {
+      "epoch": 0.24422214556743704,
+      "grad_norm": 1.0601836442947388,
+      "learning_rate": 9.628972374461536e-05,
+      "loss": 10.0273,
+      "step": 177
+    },
+    {
+      "epoch": 0.24560193170058642,
+      "grad_norm": 1.1165393590927124,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 10.0129,
+      "step": 178
+    },
+    {
+      "epoch": 0.24698171783373576,
+      "grad_norm": 1.0721098184585571,
+      "learning_rate": 9.609705861947359e-05,
+      "loss": 10.0034,
+      "step": 179
+    },
+    {
+      "epoch": 0.24836150396688514,
+      "grad_norm": 1.1826632022857666,
+      "learning_rate": 9.599897218294122e-05,
+      "loss": 9.9898,
+      "step": 180
+    },
+    {
+      "epoch": 0.24974129010003449,
+      "grad_norm": 1.1779521703720093,
+      "learning_rate": 9.589971980218179e-05,
+      "loss": 9.9933,
+      "step": 181
+    },
+    {
+      "epoch": 0.25112107623318386,
+      "grad_norm": 1.261836051940918,
+      "learning_rate": 9.579930399296331e-05,
+      "loss": 9.9738,
+      "step": 182
+    },
+    {
+      "epoch": 0.25250086236633323,
+      "grad_norm": 1.2774072885513306,
+      "learning_rate": 9.569772730054329e-05,
+      "loss": 9.9662,
+      "step": 183
+    },
+    {
+      "epoch": 0.25388064849948255,
+      "grad_norm": 1.3094655275344849,
+      "learning_rate": 9.559499229960451e-05,
+      "loss": 9.962,
+      "step": 184
+    },
+    {
+      "epoch": 0.2552604346326319,
+      "grad_norm": 1.3480101823806763,
+      "learning_rate": 9.549110159418948e-05,
+      "loss": 9.9655,
+      "step": 185
+    },
+    {
+      "epoch": 0.2566402207657813,
+      "grad_norm": 1.3947056531906128,
+      "learning_rate": 9.538605781763463e-05,
+      "loss": 9.9447,
+      "step": 186
+    },
+    {
+      "epoch": 0.2580200068989307,
+      "grad_norm": 1.5284061431884766,
+      "learning_rate": 9.527986363250348e-05,
+      "loss": 9.9349,
+      "step": 187
+    },
+    {
+      "epoch": 0.25939979303208005,
+      "grad_norm": 1.1224453449249268,
+      "learning_rate": 9.517252173051911e-05,
+      "loss": 9.9821,
+      "step": 188
+    },
+    {
+      "epoch": 0.26077957916522937,
+      "grad_norm": 0.9561300873756409,
+      "learning_rate": 9.506403483249608e-05,
+      "loss": 10.0054,
+      "step": 189
+    },
+    {
+      "epoch": 0.26215936529837874,
+      "grad_norm": 1.0607901811599731,
+      "learning_rate": 9.495440568827129e-05,
+      "loss": 10.0007,
+      "step": 190
+    },
+    {
+      "epoch": 0.2635391514315281,
+      "grad_norm": 1.1778087615966797,
+      "learning_rate": 9.484363707663442e-05,
+      "loss": 9.9694,
+      "step": 191
+    },
+    {
+      "epoch": 0.2649189375646775,
+      "grad_norm": 1.1621663570404053,
+      "learning_rate": 9.473173180525737e-05,
+      "loss": 9.9717,
+      "step": 192
+    },
+    {
+      "epoch": 0.2662987236978268,
+      "grad_norm": 1.1913270950317383,
+      "learning_rate": 9.461869271062322e-05,
+      "loss": 9.9754,
+      "step": 193
+    },
+    {
+      "epoch": 0.2676785098309762,
+      "grad_norm": 1.207746982574463,
+      "learning_rate": 9.450452265795423e-05,
+      "loss": 9.9772,
+      "step": 194
+    },
+    {
+      "epoch": 0.26905829596412556,
+      "grad_norm": 1.3012892007827759,
+      "learning_rate": 9.438922454113928e-05,
+      "loss": 9.9452,
+      "step": 195
+    },
+    {
+      "epoch": 0.27043808209727493,
+      "grad_norm": 1.3070969581604004,
+      "learning_rate": 9.42728012826605e-05,
+      "loss": 9.9479,
+      "step": 196
+    },
+    {
+      "epoch": 0.2718178682304243,
+      "grad_norm": 1.2681845426559448,
+      "learning_rate": 9.415525583351916e-05,
+      "loss": 9.9496,
+      "step": 197
+    },
+    {
+      "epoch": 0.2731976543635736,
+      "grad_norm": 1.410770297050476,
+      "learning_rate": 9.403659117316093e-05,
+      "loss": 9.9055,
+      "step": 198
+    },
+    {
+      "epoch": 0.274577440496723,
+      "grad_norm": 1.4336166381835938,
+      "learning_rate": 9.391681030940031e-05,
+      "loss": 9.9137,
+      "step": 199
+    },
+    {
+      "epoch": 0.2759572266298724,
+      "grad_norm": 1.6375997066497803,
+      "learning_rate": 9.37959162783444e-05,
+      "loss": 9.8763,
+      "step": 200
+    },
+    {
+      "epoch": 0.27733701276302175,
+      "grad_norm": 0.9288918972015381,
+      "learning_rate": 9.367391214431598e-05,
+      "loss": 9.9892,
+      "step": 201
+    },
+    {
+      "epoch": 0.27871679889617107,
+      "grad_norm": 1.0222079753875732,
+      "learning_rate": 9.355080099977578e-05,
+      "loss": 9.9729,
+      "step": 202
+    },
+    {
+      "epoch": 0.28009658502932044,
+      "grad_norm": 1.1373820304870605,
+      "learning_rate": 9.342658596524416e-05,
+      "loss": 9.953,
+      "step": 203
+    },
+    {
+      "epoch": 0.2814763711624698,
+      "grad_norm": 1.1755473613739014,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 9.9483,
+      "step": 204
+    },
+    {
+      "epoch": 0.2828561572956192,
+      "grad_norm": 1.1603400707244873,
+      "learning_rate": 9.317485684811065e-05,
+      "loss": 9.9461,
+      "step": 205
+    },
+    {
+      "epoch": 0.28423594342876857,
+      "grad_norm": 1.2315527200698853,
+      "learning_rate": 9.3047349146132e-05,
+      "loss": 9.9464,
+      "step": 206
+    },
+    {
+      "epoch": 0.2856157295619179,
+      "grad_norm": 1.2375974655151367,
+      "learning_rate": 9.291875031524668e-05,
+      "loss": 9.9391,
+      "step": 207
+    },
+    {
+      "epoch": 0.28699551569506726,
+      "grad_norm": 1.3307669162750244,
+      "learning_rate": 9.278906361507238e-05,
+      "loss": 9.9194,
+      "step": 208
+    },
+    {
+      "epoch": 0.28837530182821663,
+      "grad_norm": 1.3934468030929565,
+      "learning_rate": 9.265829233280123e-05,
+      "loss": 9.9021,
+      "step": 209
+    },
+    {
+      "epoch": 0.289755087961366,
+      "grad_norm": 1.3561367988586426,
+      "learning_rate": 9.252643978311649e-05,
+      "loss": 9.9037,
+      "step": 210
+    },
+    {
+      "epoch": 0.29113487409451533,
+      "grad_norm": 1.3786364793777466,
+      "learning_rate": 9.239350930810843e-05,
+      "loss": 9.8974,
+      "step": 211
+    },
+    {
+      "epoch": 0.2925146602276647,
+      "grad_norm": 1.5267988443374634,
+      "learning_rate": 9.225950427718975e-05,
+      "loss": 9.8763,
+      "step": 212
+    },
+    {
+      "epoch": 0.2938944463608141,
+      "grad_norm": 1.1748323440551758,
+      "learning_rate": 9.212442808701007e-05,
+      "loss": 9.9215,
+      "step": 213
+    },
+    {
+      "epoch": 0.29527423249396345,
+      "grad_norm": 0.9960755705833435,
+      "learning_rate": 9.19882841613699e-05,
+      "loss": 9.9739,
+      "step": 214
+    },
+    {
+      "epoch": 0.29665401862711277,
+      "grad_norm": 1.1767911911010742,
+      "learning_rate": 9.185107595113384e-05,
+      "loss": 9.9264,
+      "step": 215
+    },
+    {
+      "epoch": 0.29803380476026214,
+      "grad_norm": 1.1542165279388428,
+      "learning_rate": 9.171280693414307e-05,
+      "loss": 9.9306,
+      "step": 216
+    },
+    {
+      "epoch": 0.2994135908934115,
+      "grad_norm": 1.1749402284622192,
+      "learning_rate": 9.157348061512727e-05,
+      "loss": 9.9255,
+      "step": 217
+    },
+    {
+      "epoch": 0.3007933770265609,
+      "grad_norm": 1.1707139015197754,
+      "learning_rate": 9.143310052561571e-05,
+      "loss": 9.9199,
+      "step": 218
+    },
+    {
+      "epoch": 0.30217316315971027,
+      "grad_norm": 1.2597498893737793,
+      "learning_rate": 9.129167022384779e-05,
+      "loss": 9.9216,
+      "step": 219
+    },
+    {
+      "epoch": 0.3035529492928596,
+      "grad_norm": 1.3159873485565186,
+      "learning_rate": 9.114919329468282e-05,
+      "loss": 9.9231,
+      "step": 220
+    },
+    {
+      "epoch": 0.30493273542600896,
+      "grad_norm": 1.36250638961792,
+      "learning_rate": 9.100567334950918e-05,
+      "loss": 9.9024,
+      "step": 221
+    },
+    {
+      "epoch": 0.30631252155915834,
+      "grad_norm": 1.3537706136703491,
+      "learning_rate": 9.086111402615273e-05,
+      "loss": 9.8925,
+      "step": 222
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 1.3712196350097656,
+      "learning_rate": 9.07155189887847e-05,
+      "loss": 9.8801,
+      "step": 223
+    },
+    {
+      "epoch": 0.30907209382545703,
+      "grad_norm": 1.4884405136108398,
+      "learning_rate": 9.056889192782866e-05,
+      "loss": 9.8664,
+      "step": 224
+    },
+    {
+      "epoch": 0.3104518799586064,
+      "grad_norm": 1.5910539627075195,
+      "learning_rate": 9.042123655986713e-05,
+      "loss": 9.8475,
+      "step": 225
+    },
+    {
+      "epoch": 0.3118316660917558,
+      "grad_norm": 0.9714315533638,
+      "learning_rate": 9.02725566275473e-05,
+      "loss": 9.9451,
+      "step": 226
+    },
+    {
+      "epoch": 0.31321145222490515,
+      "grad_norm": 1.1220028400421143,
+      "learning_rate": 9.012285589948617e-05,
+      "loss": 9.9377,
+      "step": 227
+    },
+    {
+      "epoch": 0.3145912383580545,
+      "grad_norm": 1.099237084388733,
+      "learning_rate": 8.997213817017507e-05,
+      "loss": 9.9214,
+      "step": 228
+    },
+    {
+      "epoch": 0.31597102449120384,
+      "grad_norm": 1.145241141319275,
+      "learning_rate": 8.982040725988336e-05,
+      "loss": 9.9099,
+      "step": 229
+    },
+    {
+      "epoch": 0.3173508106243532,
+      "grad_norm": 1.2392131090164185,
+      "learning_rate": 8.966766701456177e-05,
+      "loss": 9.8892,
+      "step": 230
+    },
+    {
+      "epoch": 0.3187305967575026,
+      "grad_norm": 1.1928961277008057,
+      "learning_rate": 8.951392130574477e-05,
+      "loss": 9.9052,
+      "step": 231
+    },
+    {
+      "epoch": 0.32011038289065197,
+      "grad_norm": 1.2984650135040283,
+      "learning_rate": 8.935917403045251e-05,
+      "loss": 9.8974,
+      "step": 232
+    },
+    {
+      "epoch": 0.3214901690238013,
+      "grad_norm": 1.3149031400680542,
+      "learning_rate": 8.920342911109206e-05,
+      "loss": 9.8815,
+      "step": 233
+    },
+    {
+      "epoch": 0.32286995515695066,
+      "grad_norm": 1.269370436668396,
+      "learning_rate": 8.904669049535789e-05,
+      "loss": 9.8841,
+      "step": 234
+    },
+    {
+      "epoch": 0.32424974129010004,
+      "grad_norm": 1.29131019115448,
+      "learning_rate": 8.888896215613191e-05,
+      "loss": 9.8848,
+      "step": 235
+    },
+    {
+      "epoch": 0.3256295274232494,
+      "grad_norm": 1.4416961669921875,
+      "learning_rate": 8.873024809138272e-05,
+      "loss": 9.8468,
+      "step": 236
+    },
+    {
+      "epoch": 0.3270093135563988,
+      "grad_norm": 1.495208978652954,
+      "learning_rate": 8.857055232406432e-05,
+      "loss": 9.8455,
+      "step": 237
+    },
+    {
+      "epoch": 0.3283890996895481,
+      "grad_norm": 1.190208911895752,
+      "learning_rate": 8.840987890201403e-05,
+      "loss": 9.8895,
+      "step": 238
+    },
+    {
+      "epoch": 0.3297688858226975,
+      "grad_norm": 1.0209683179855347,
+      "learning_rate": 8.824823189785e-05,
+      "loss": 9.9142,
+      "step": 239
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 724,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 239,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 198449773412352.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be147f8ce3c144c46d0e6b5e0d67862fb6846d56238903131a7e829e187c419d
+size 6840