Upload folder using huggingface_hub

22_128_e5_3e-5/checkpoint-1203/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ibm-granite/granite-3.3-8b-base
+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 0.15.2

22_128_e5_3e-5/checkpoint-1203/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

22_128_e5_3e-5/checkpoint-1203/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fef2d69dc6a19196331fdd035b806bf0a6ef57abfa683b5b100c09641b5479f
+size 791751704

22_128_e5_3e-5/checkpoint-1203/latest

@@ -0,0 +1 @@
+global_step1203

22_128_e5_3e-5/checkpoint-1203/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f981fc3b281d74f706851bf19e3004f13757b3f68398ebf85753a1592ffae4d1
+size 15920

22_128_e5_3e-5/checkpoint-1203/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98e99af424ac627042f90049874f1fd0043ffd97d69af2ac0000ab6e01fc3fe
+size 15920

22_128_e5_3e-5/checkpoint-1203/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46310bd5a0b83a54818b72fb5275c4ae1c477433be9b24334bc279d5fb65b97f
+size 15920

22_128_e5_3e-5/checkpoint-1203/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7a459684ccfba165355a3a96f67749dfaf6e4045241620d3b9d068bb5b3a7a
+size 15920

22_128_e5_3e-5/checkpoint-1203/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1724cbfd06b503cb416d5f9f95bb83f1f966a66fc449397f65d4b548be9aa6ca
+size 15920

22_128_e5_3e-5/checkpoint-1203/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604bde1de65381cd166510927b75da7f30988d9848b83409ccaf6103f864e9fc
+size 15920

22_128_e5_3e-5/checkpoint-1203/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aab086e98298e6c4f6012f9004f8ed04bee5fadefb39e9d2b2253c8a95fc28f
+size 15920

22_128_e5_3e-5/checkpoint-1203/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c068d1ad0ba4683d6c9cd1d0eab4af92e4e56c093c9948115c74b5b0f668f00
+size 15920

22_128_e5_3e-5/checkpoint-1203/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d5d2a4a9bd26cead6506267ea5e17cba7fea239d97f92ae2ab717432c6aa78
+size 1064

22_128_e5_3e-5/checkpoint-1203/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

22_128_e5_3e-5/checkpoint-1203/tokenizer_config.json

@@ -0,0 +1,188 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

22_128_e5_3e-5/checkpoint-1203/trainer_state.json

@@ -0,0 +1,1714 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1203,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012484394506866416,
+      "grad_norm": 1.250030279159546,
+      "learning_rate": 1.1881188118811881e-06,
+      "loss": 1.3024,
+      "step": 5
+    },
+    {
+      "epoch": 0.024968789013732832,
+      "grad_norm": 1.0841675996780396,
+      "learning_rate": 2.673267326732673e-06,
+      "loss": 1.3147,
+      "step": 10
+    },
+    {
+      "epoch": 0.03745318352059925,
+      "grad_norm": 0.6254027485847473,
+      "learning_rate": 4.158415841584159e-06,
+      "loss": 1.2397,
+      "step": 15
+    },
+    {
+      "epoch": 0.049937578027465665,
+      "grad_norm": 0.5402944684028625,
+      "learning_rate": 5.643564356435644e-06,
+      "loss": 1.2073,
+      "step": 20
+    },
+    {
+      "epoch": 0.062421972534332085,
+      "grad_norm": 0.47610044479370117,
+      "learning_rate": 7.128712871287129e-06,
+      "loss": 1.2178,
+      "step": 25
+    },
+    {
+      "epoch": 0.0749063670411985,
+      "grad_norm": 0.5858327746391296,
+      "learning_rate": 8.613861386138613e-06,
+      "loss": 1.238,
+      "step": 30
+    },
+    {
+      "epoch": 0.08739076154806492,
+      "grad_norm": 0.5472700595855713,
+      "learning_rate": 1.00990099009901e-05,
+      "loss": 1.2016,
+      "step": 35
+    },
+    {
+      "epoch": 0.09987515605493133,
+      "grad_norm": 0.44305941462516785,
+      "learning_rate": 1.1584158415841584e-05,
+      "loss": 1.184,
+      "step": 40
+    },
+    {
+      "epoch": 0.11235955056179775,
+      "grad_norm": 0.4975726902484894,
+      "learning_rate": 1.306930693069307e-05,
+      "loss": 1.2251,
+      "step": 45
+    },
+    {
+      "epoch": 0.12484394506866417,
+      "grad_norm": 0.43187275528907776,
+      "learning_rate": 1.4554455445544554e-05,
+      "loss": 1.1542,
+      "step": 50
+    },
+    {
+      "epoch": 0.1373283395755306,
+      "grad_norm": 0.4613569974899292,
+      "learning_rate": 1.6039603960396042e-05,
+      "loss": 1.1681,
+      "step": 55
+    },
+    {
+      "epoch": 0.149812734082397,
+      "grad_norm": 0.44121506810188293,
+      "learning_rate": 1.7524752475247524e-05,
+      "loss": 1.1475,
+      "step": 60
+    },
+    {
+      "epoch": 0.16229712858926343,
+      "grad_norm": 0.4488328993320465,
+      "learning_rate": 1.900990099009901e-05,
+      "loss": 1.1619,
+      "step": 65
+    },
+    {
+      "epoch": 0.17478152309612985,
+      "grad_norm": 0.44015923142433167,
+      "learning_rate": 2.0495049504950496e-05,
+      "loss": 1.0965,
+      "step": 70
+    },
+    {
+      "epoch": 0.18726591760299627,
+      "grad_norm": 0.44825753569602966,
+      "learning_rate": 2.198019801980198e-05,
+      "loss": 1.1127,
+      "step": 75
+    },
+    {
+      "epoch": 0.19975031210986266,
+      "grad_norm": 0.4191741347312927,
+      "learning_rate": 2.3465346534653467e-05,
+      "loss": 1.1326,
+      "step": 80
+    },
+    {
+      "epoch": 0.21223470661672908,
+      "grad_norm": 0.47760850191116333,
+      "learning_rate": 2.495049504950495e-05,
+      "loss": 1.1003,
+      "step": 85
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 0.5718854069709778,
+      "learning_rate": 2.6435643564356436e-05,
+      "loss": 1.1227,
+      "step": 90
+    },
+    {
+      "epoch": 0.23720349563046192,
+      "grad_norm": 0.6666268110275269,
+      "learning_rate": 2.792079207920792e-05,
+      "loss": 1.1288,
+      "step": 95
+    },
+    {
+      "epoch": 0.24968789013732834,
+      "grad_norm": 0.44064071774482727,
+      "learning_rate": 2.9405940594059407e-05,
+      "loss": 1.065,
+      "step": 100
+    },
+    {
+      "epoch": 0.26217228464419473,
+      "grad_norm": 0.5092717409133911,
+      "learning_rate": 2.999981623248469e-05,
+      "loss": 1.0766,
+      "step": 105
+    },
+    {
+      "epoch": 0.2746566791510612,
+      "grad_norm": 0.5116708278656006,
+      "learning_rate": 2.9998693225086163e-05,
+      "loss": 1.0636,
+      "step": 110
+    },
+    {
+      "epoch": 0.28714107365792757,
+      "grad_norm": 0.5135843753814697,
+      "learning_rate": 2.9996549379694418e-05,
+      "loss": 1.0543,
+      "step": 115
+    },
+    {
+      "epoch": 0.299625468164794,
+      "grad_norm": 0.5474386811256409,
+      "learning_rate": 2.9993384842223426e-05,
+      "loss": 1.0784,
+      "step": 120
+    },
+    {
+      "epoch": 0.3121098626716604,
+      "grad_norm": 0.5349007844924927,
+      "learning_rate": 2.998919982805729e-05,
+      "loss": 1.0306,
+      "step": 125
+    },
+    {
+      "epoch": 0.32459425717852686,
+      "grad_norm": 0.5236003994941711,
+      "learning_rate": 2.998399462203559e-05,
+      "loss": 1.0462,
+      "step": 130
+    },
+    {
+      "epoch": 0.33707865168539325,
+      "grad_norm": 0.5239087343215942,
+      "learning_rate": 2.9977769578433987e-05,
+      "loss": 1.0233,
+      "step": 135
+    },
+    {
+      "epoch": 0.3495630461922597,
+      "grad_norm": 0.6136004328727722,
+      "learning_rate": 2.9970525120940132e-05,
+      "loss": 0.9779,
+      "step": 140
+    },
+    {
+      "epoch": 0.3620474406991261,
+      "grad_norm": 0.6154010891914368,
+      "learning_rate": 2.9962261742624813e-05,
+      "loss": 0.9944,
+      "step": 145
+    },
+    {
+      "epoch": 0.37453183520599254,
+      "grad_norm": 0.5972864627838135,
+      "learning_rate": 2.995298000590839e-05,
+      "loss": 1.0074,
+      "step": 150
+    },
+    {
+      "epoch": 0.38701622971285893,
+      "grad_norm": 0.5776309370994568,
+      "learning_rate": 2.9942680542522535e-05,
+      "loss": 0.9963,
+      "step": 155
+    },
+    {
+      "epoch": 0.3995006242197253,
+      "grad_norm": 0.6151773929595947,
+      "learning_rate": 2.993136405346722e-05,
+      "loss": 0.9857,
+      "step": 160
+    },
+    {
+      "epoch": 0.41198501872659177,
+      "grad_norm": 0.6129782795906067,
+      "learning_rate": 2.991903130896301e-05,
+      "loss": 1.0118,
+      "step": 165
+    },
+    {
+      "epoch": 0.42446941323345816,
+      "grad_norm": 0.6217514872550964,
+      "learning_rate": 2.9905683148398642e-05,
+      "loss": 0.9757,
+      "step": 170
+    },
+    {
+      "epoch": 0.4369538077403246,
+      "grad_norm": 0.6364917755126953,
+      "learning_rate": 2.9891320480273886e-05,
+      "loss": 0.9542,
+      "step": 175
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 0.6444506049156189,
+      "learning_rate": 2.9875944282137734e-05,
+      "loss": 0.968,
+      "step": 180
+    },
+    {
+      "epoch": 0.46192259675405745,
+      "grad_norm": 0.6949779987335205,
+      "learning_rate": 2.9859555600521838e-05,
+      "loss": 0.9255,
+      "step": 185
+    },
+    {
+      "epoch": 0.47440699126092384,
+      "grad_norm": 0.719308614730835,
+      "learning_rate": 2.9842155550869294e-05,
+      "loss": 0.9439,
+      "step": 190
+    },
+    {
+      "epoch": 0.4868913857677903,
+      "grad_norm": 0.6572843194007874,
+      "learning_rate": 2.982374531745873e-05,
+      "loss": 0.9059,
+      "step": 195
+    },
+    {
+      "epoch": 0.4993757802746567,
+      "grad_norm": 0.7524131536483765,
+      "learning_rate": 2.9804326153323683e-05,
+      "loss": 0.9322,
+      "step": 200
+    },
+    {
+      "epoch": 0.5118601747815231,
+      "grad_norm": 0.7650299072265625,
+      "learning_rate": 2.9783899380167345e-05,
+      "loss": 0.9085,
+      "step": 205
+    },
+    {
+      "epoch": 0.5243445692883895,
+      "grad_norm": 0.7098513841629028,
+      "learning_rate": 2.976246638827257e-05,
+      "loss": 0.9223,
+      "step": 210
+    },
+    {
+      "epoch": 0.5368289637952559,
+      "grad_norm": 0.8576691150665283,
+      "learning_rate": 2.974002863640727e-05,
+      "loss": 0.9254,
+      "step": 215
+    },
+    {
+      "epoch": 0.5493133583021224,
+      "grad_norm": 0.7496089339256287,
+      "learning_rate": 2.9716587651725134e-05,
+      "loss": 0.9314,
+      "step": 220
+    },
+    {
+      "epoch": 0.5617977528089888,
+      "grad_norm": 0.6800470948219299,
+      "learning_rate": 2.9692145029661664e-05,
+      "loss": 0.8435,
+      "step": 225
+    },
+    {
+      "epoch": 0.5742821473158551,
+      "grad_norm": 0.8700007796287537,
+      "learning_rate": 2.9666702433825614e-05,
+      "loss": 0.9101,
+      "step": 230
+    },
+    {
+      "epoch": 0.5867665418227216,
+      "grad_norm": 0.6640142798423767,
+      "learning_rate": 2.9640261595885735e-05,
+      "loss": 0.875,
+      "step": 235
+    },
+    {
+      "epoch": 0.599250936329588,
+      "grad_norm": 0.8278601169586182,
+      "learning_rate": 2.9612824315452943e-05,
+      "loss": 0.8479,
+      "step": 240
+    },
+    {
+      "epoch": 0.6117353308364545,
+      "grad_norm": 0.9126909375190735,
+      "learning_rate": 2.958439245995781e-05,
+      "loss": 0.8526,
+      "step": 245
+    },
+    {
+      "epoch": 0.6242197253433208,
+      "grad_norm": 0.8736037015914917,
+      "learning_rate": 2.955496796452347e-05,
+      "loss": 0.8113,
+      "step": 250
+    },
+    {
+      "epoch": 0.6367041198501873,
+      "grad_norm": 0.8721530437469482,
+      "learning_rate": 2.9524552831833924e-05,
+      "loss": 0.8612,
+      "step": 255
+    },
+    {
+      "epoch": 0.6491885143570537,
+      "grad_norm": 0.8261131048202515,
+      "learning_rate": 2.9493149131997713e-05,
+      "loss": 0.7762,
+      "step": 260
+    },
+    {
+      "epoch": 0.66167290886392,
+      "grad_norm": 0.8957151174545288,
+      "learning_rate": 2.946075900240704e-05,
+      "loss": 0.832,
+      "step": 265
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 0.916682779788971,
+      "learning_rate": 2.942738464759229e-05,
+      "loss": 0.8213,
+      "step": 270
+    },
+    {
+      "epoch": 0.686641697877653,
+      "grad_norm": 0.7609239220619202,
+      "learning_rate": 2.939302833907197e-05,
+      "loss": 0.8061,
+      "step": 275
+    },
+    {
+      "epoch": 0.6991260923845194,
+      "grad_norm": 0.8781178593635559,
+      "learning_rate": 2.9357692415198136e-05,
+      "loss": 0.7798,
+      "step": 280
+    },
+    {
+      "epoch": 0.7116104868913857,
+      "grad_norm": 0.8101415038108826,
+      "learning_rate": 2.932137928099722e-05,
+      "loss": 0.8564,
+      "step": 285
+    },
+    {
+      "epoch": 0.7240948813982522,
+      "grad_norm": 0.8110167980194092,
+      "learning_rate": 2.928409140800634e-05,
+      "loss": 0.8175,
+      "step": 290
+    },
+    {
+      "epoch": 0.7365792759051186,
+      "grad_norm": 0.7818710803985596,
+      "learning_rate": 2.9245831334105084e-05,
+      "loss": 0.7912,
+      "step": 295
+    },
+    {
+      "epoch": 0.7490636704119851,
+      "grad_norm": 0.8244704008102417,
+      "learning_rate": 2.9206601663342786e-05,
+      "loss": 0.7646,
+      "step": 300
+    },
+    {
+      "epoch": 0.7615480649188514,
+      "grad_norm": 0.8379747867584229,
+      "learning_rate": 2.916640506576128e-05,
+      "loss": 0.7671,
+      "step": 305
+    },
+    {
+      "epoch": 0.7740324594257179,
+      "grad_norm": 0.8790676593780518,
+      "learning_rate": 2.9125244277213176e-05,
+      "loss": 0.7688,
+      "step": 310
+    },
+    {
+      "epoch": 0.7865168539325843,
+      "grad_norm": 0.9378462433815002,
+      "learning_rate": 2.908312209917565e-05,
+      "loss": 0.7718,
+      "step": 315
+    },
+    {
+      "epoch": 0.7990012484394506,
+      "grad_norm": 0.8543297052383423,
+      "learning_rate": 2.904004139855978e-05,
+      "loss": 0.7663,
+      "step": 320
+    },
+    {
+      "epoch": 0.8114856429463171,
+      "grad_norm": 0.8526532053947449,
+      "learning_rate": 2.8996005107515405e-05,
+      "loss": 0.7911,
+      "step": 325
+    },
+    {
+      "epoch": 0.8239700374531835,
+      "grad_norm": 0.8875757455825806,
+      "learning_rate": 2.8951016223231567e-05,
+      "loss": 0.7511,
+      "step": 330
+    },
+    {
+      "epoch": 0.83645443196005,
+      "grad_norm": 0.8844619393348694,
+      "learning_rate": 2.890507780773252e-05,
+      "loss": 0.7234,
+      "step": 335
+    },
+    {
+      "epoch": 0.8489388264669163,
+      "grad_norm": 0.896385908126831,
+      "learning_rate": 2.8858192987669303e-05,
+      "loss": 0.699,
+      "step": 340
+    },
+    {
+      "epoch": 0.8614232209737828,
+      "grad_norm": 1.157642126083374,
+      "learning_rate": 2.881036495410696e-05,
+      "loss": 0.7825,
+      "step": 345
+    },
+    {
+      "epoch": 0.8739076154806492,
+      "grad_norm": 0.9201584458351135,
+      "learning_rate": 2.8761596962307343e-05,
+      "loss": 0.6774,
+      "step": 350
+    },
+    {
+      "epoch": 0.8863920099875156,
+      "grad_norm": 0.924287736415863,
+      "learning_rate": 2.871189233150754e-05,
+      "loss": 0.7057,
+      "step": 355
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.9572568535804749,
+      "learning_rate": 2.8661254444693975e-05,
+      "loss": 0.7201,
+      "step": 360
+    },
+    {
+      "epoch": 0.9113607990012484,
+      "grad_norm": 1.010705828666687,
+      "learning_rate": 2.8609686748372155e-05,
+      "loss": 0.776,
+      "step": 365
+    },
+    {
+      "epoch": 0.9238451935081149,
+      "grad_norm": 0.8497414588928223,
+      "learning_rate": 2.8557192752332082e-05,
+      "loss": 0.7348,
+      "step": 370
+    },
+    {
+      "epoch": 0.9363295880149812,
+      "grad_norm": 0.9973917603492737,
+      "learning_rate": 2.8503776029409398e-05,
+      "loss": 0.6799,
+      "step": 375
+    },
+    {
+      "epoch": 0.9488139825218477,
+      "grad_norm": 1.0082824230194092,
+      "learning_rate": 2.844944021524217e-05,
+      "loss": 0.6975,
+      "step": 380
+    },
+    {
+      "epoch": 0.9612983770287141,
+      "grad_norm": 1.0351635217666626,
+      "learning_rate": 2.8394189008023482e-05,
+      "loss": 0.715,
+      "step": 385
+    },
+    {
+      "epoch": 0.9737827715355806,
+      "grad_norm": 0.9392898082733154,
+      "learning_rate": 2.833802616824972e-05,
+      "loss": 0.7083,
+      "step": 390
+    },
+    {
+      "epoch": 0.9862671660424469,
+      "grad_norm": 0.9130701422691345,
+      "learning_rate": 2.8280955518464587e-05,
+      "loss": 0.671,
+      "step": 395
+    },
+    {
+      "epoch": 0.9987515605493134,
+      "grad_norm": 0.8589998483657837,
+      "learning_rate": 2.8222980942999005e-05,
+      "loss": 0.6443,
+      "step": 400
+    },
+    {
+      "epoch": 1.0099875156054932,
+      "grad_norm": 1.179226279258728,
+      "learning_rate": 2.8164106387706675e-05,
+      "loss": 0.5978,
+      "step": 405
+    },
+    {
+      "epoch": 1.0224719101123596,
+      "grad_norm": 1.1383295059204102,
+      "learning_rate": 2.8104335859695545e-05,
+      "loss": 0.6234,
+      "step": 410
+    },
+    {
+      "epoch": 1.034956304619226,
+      "grad_norm": 1.0137205123901367,
+      "learning_rate": 2.8043673427055076e-05,
+      "loss": 0.5565,
+      "step": 415
+    },
+    {
+      "epoch": 1.0474406991260923,
+      "grad_norm": 0.9573396444320679,
+      "learning_rate": 2.7982123218579373e-05,
+      "loss": 0.5922,
+      "step": 420
+    },
+    {
+      "epoch": 1.0599250936329587,
+      "grad_norm": 0.9142056107521057,
+      "learning_rate": 2.7919689423486136e-05,
+      "loss": 0.5344,
+      "step": 425
+    },
+    {
+      "epoch": 1.0724094881398252,
+      "grad_norm": 1.0959941148757935,
+      "learning_rate": 2.785637629113157e-05,
+      "loss": 0.5991,
+      "step": 430
+    },
+    {
+      "epoch": 1.0848938826466916,
+      "grad_norm": 1.0628936290740967,
+      "learning_rate": 2.779218813072116e-05,
+      "loss": 0.6041,
+      "step": 435
+    },
+    {
+      "epoch": 1.097378277153558,
+      "grad_norm": 1.1268197298049927,
+      "learning_rate": 2.7727129311016346e-05,
+      "loss": 0.5696,
+      "step": 440
+    },
+    {
+      "epoch": 1.1098626716604245,
+      "grad_norm": 1.011999249458313,
+      "learning_rate": 2.7661204260037234e-05,
+      "loss": 0.5735,
+      "step": 445
+    },
+    {
+      "epoch": 1.122347066167291,
+      "grad_norm": 0.9339777827262878,
+      "learning_rate": 2.7594417464761165e-05,
+      "loss": 0.5435,
+      "step": 450
+    },
+    {
+      "epoch": 1.1348314606741572,
+      "grad_norm": 0.9832940697669983,
+      "learning_rate": 2.7526773470817353e-05,
+      "loss": 0.5349,
+      "step": 455
+    },
+    {
+      "epoch": 1.1473158551810236,
+      "grad_norm": 0.9407443404197693,
+      "learning_rate": 2.745827688217749e-05,
+      "loss": 0.5582,
+      "step": 460
+    },
+    {
+      "epoch": 1.15980024968789,
+      "grad_norm": 1.006485939025879,
+      "learning_rate": 2.7388932360842394e-05,
+      "loss": 0.5492,
+      "step": 465
+    },
+    {
+      "epoch": 1.1722846441947565,
+      "grad_norm": 0.997183084487915,
+      "learning_rate": 2.7318744626524704e-05,
+      "loss": 0.5265,
+      "step": 470
+    },
+    {
+      "epoch": 1.184769038701623,
+      "grad_norm": 0.9414803385734558,
+      "learning_rate": 2.7247718456327656e-05,
+      "loss": 0.5636,
+      "step": 475
+    },
+    {
+      "epoch": 1.1972534332084894,
+      "grad_norm": 0.9664161801338196,
+      "learning_rate": 2.717585868441992e-05,
+      "loss": 0.5622,
+      "step": 480
+    },
+    {
+      "epoch": 1.2097378277153559,
+      "grad_norm": 1.2472707033157349,
+      "learning_rate": 2.7103170201706615e-05,
+      "loss": 0.517,
+      "step": 485
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 1.0070255994796753,
+      "learning_rate": 2.7029657955496392e-05,
+      "loss": 0.538,
+      "step": 490
+    },
+    {
+      "epoch": 1.2347066167290885,
+      "grad_norm": 1.0936633348464966,
+      "learning_rate": 2.6955326949164738e-05,
+      "loss": 0.5338,
+      "step": 495
+    },
+    {
+      "epoch": 1.247191011235955,
+      "grad_norm": 1.0601006746292114,
+      "learning_rate": 2.688018224181341e-05,
+      "loss": 0.5381,
+      "step": 500
+    },
+    {
+      "epoch": 1.2596754057428214,
+      "grad_norm": 1.0741894245147705,
+      "learning_rate": 2.6804228947926125e-05,
+      "loss": 0.4972,
+      "step": 505
+    },
+    {
+      "epoch": 1.2721598002496879,
+      "grad_norm": 0.8921645283699036,
+      "learning_rate": 2.672747223702045e-05,
+      "loss": 0.5096,
+      "step": 510
+    },
+    {
+      "epoch": 1.2846441947565543,
+      "grad_norm": 0.9685996174812317,
+      "learning_rate": 2.6649917333295956e-05,
+      "loss": 0.5174,
+      "step": 515
+    },
+    {
+      "epoch": 1.2971285892634208,
+      "grad_norm": 0.9764025807380676,
+      "learning_rate": 2.657156951527865e-05,
+      "loss": 0.5165,
+      "step": 520
+    },
+    {
+      "epoch": 1.309612983770287,
+      "grad_norm": 1.0654433965682983,
+      "learning_rate": 2.649243411546171e-05,
+      "loss": 0.5041,
+      "step": 525
+    },
+    {
+      "epoch": 1.3220973782771535,
+      "grad_norm": 1.050934910774231,
+      "learning_rate": 2.6412516519942554e-05,
+      "loss": 0.5104,
+      "step": 530
+    },
+    {
+      "epoch": 1.33458177278402,
+      "grad_norm": 1.0428624153137207,
+      "learning_rate": 2.6331822168056234e-05,
+      "loss": 0.4698,
+      "step": 535
+    },
+    {
+      "epoch": 1.3470661672908864,
+      "grad_norm": 1.0803771018981934,
+      "learning_rate": 2.6250356552005234e-05,
+      "loss": 0.4493,
+      "step": 540
+    },
+    {
+      "epoch": 1.3595505617977528,
+      "grad_norm": 1.0904477834701538,
+      "learning_rate": 2.6168125216485666e-05,
+      "loss": 0.4573,
+      "step": 545
+    },
+    {
+      "epoch": 1.3720349563046192,
+      "grad_norm": 1.0958645343780518,
+      "learning_rate": 2.6085133758309887e-05,
+      "loss": 0.5288,
+      "step": 550
+    },
+    {
+      "epoch": 1.3845193508114857,
+      "grad_norm": 1.12440824508667,
+      "learning_rate": 2.6001387826025564e-05,
+      "loss": 0.485,
+      "step": 555
+    },
+    {
+      "epoch": 1.3970037453183521,
+      "grad_norm": 1.0093923807144165,
+      "learning_rate": 2.591689311953122e-05,
+      "loss": 0.4735,
+      "step": 560
+    },
+    {
+      "epoch": 1.4094881398252186,
+      "grad_norm": 0.8993324041366577,
+      "learning_rate": 2.5831655389688308e-05,
+      "loss": 0.4851,
+      "step": 565
+    },
+    {
+      "epoch": 1.4219725343320848,
+      "grad_norm": 1.028627634048462,
+      "learning_rate": 2.5745680437929774e-05,
+      "loss": 0.4648,
+      "step": 570
+    },
+    {
+      "epoch": 1.4344569288389513,
+      "grad_norm": 1.0453159809112549,
+      "learning_rate": 2.565897411586522e-05,
+      "loss": 0.4848,
+      "step": 575
+    },
+    {
+      "epoch": 1.4469413233458177,
+      "grad_norm": 1.0226070880889893,
+      "learning_rate": 2.557154232488261e-05,
+      "loss": 0.4758,
+      "step": 580
+    },
+    {
+      "epoch": 1.4594257178526842,
+      "grad_norm": 1.1143102645874023,
+      "learning_rate": 2.548339101574664e-05,
+      "loss": 0.4989,
+      "step": 585
+    },
+    {
+      "epoch": 1.4719101123595506,
+      "grad_norm": 1.159244179725647,
+      "learning_rate": 2.5394526188193706e-05,
+      "loss": 0.476,
+      "step": 590
+    },
+    {
+      "epoch": 1.484394506866417,
+      "grad_norm": 1.282088041305542,
+      "learning_rate": 2.5304953890523526e-05,
+      "loss": 0.492,
+      "step": 595
+    },
+    {
+      "epoch": 1.4968789013732833,
+      "grad_norm": 1.136864423751831,
+      "learning_rate": 2.521468021918753e-05,
+      "loss": 0.4168,
+      "step": 600
+    },
+    {
+      "epoch": 1.5093632958801497,
+      "grad_norm": 1.0521190166473389,
+      "learning_rate": 2.5123711318373886e-05,
+      "loss": 0.4764,
+      "step": 605
+    },
+    {
+      "epoch": 1.5218476903870162,
+      "grad_norm": 1.1445989608764648,
+      "learning_rate": 2.5032053379589327e-05,
+      "loss": 0.4669,
+      "step": 610
+    },
+    {
+      "epoch": 1.5343320848938826,
+      "grad_norm": 1.2416304349899292,
+      "learning_rate": 2.493971264123776e-05,
+      "loss": 0.4868,
+      "step": 615
+    },
+    {
+      "epoch": 1.546816479400749,
+      "grad_norm": 1.0602422952651978,
+      "learning_rate": 2.484669538819564e-05,
+      "loss": 0.4246,
+      "step": 620
+    },
+    {
+      "epoch": 1.5593008739076155,
+      "grad_norm": 1.0995105504989624,
+      "learning_rate": 2.4753007951384236e-05,
+      "loss": 0.4557,
+      "step": 625
+    },
+    {
+      "epoch": 1.571785268414482,
+      "grad_norm": 1.056087851524353,
+      "learning_rate": 2.4658656707338733e-05,
+      "loss": 0.4376,
+      "step": 630
+    },
+    {
+      "epoch": 1.5842696629213484,
+      "grad_norm": 1.069985270500183,
+      "learning_rate": 2.4563648077774217e-05,
+      "loss": 0.4328,
+      "step": 635
+    },
+    {
+      "epoch": 1.5967540574282149,
+      "grad_norm": 1.0622888803482056,
+      "learning_rate": 2.446798852914862e-05,
+      "loss": 0.4295,
+      "step": 640
+    },
+    {
+      "epoch": 1.6092384519350813,
+      "grad_norm": 1.1215320825576782,
+      "learning_rate": 2.4371684572222596e-05,
+      "loss": 0.4429,
+      "step": 645
+    },
+    {
+      "epoch": 1.6217228464419475,
+      "grad_norm": 0.973064661026001,
+      "learning_rate": 2.427474276161637e-05,
+      "loss": 0.4127,
+      "step": 650
+    },
+    {
+      "epoch": 1.634207240948814,
+      "grad_norm": 1.140210747718811,
+      "learning_rate": 2.417716969536365e-05,
+      "loss": 0.4128,
+      "step": 655
+    },
+    {
+      "epoch": 1.6466916354556804,
+      "grad_norm": 0.985823929309845,
+      "learning_rate": 2.4078972014462533e-05,
+      "loss": 0.4305,
+      "step": 660
+    },
+    {
+      "epoch": 1.6591760299625467,
+      "grad_norm": 1.1081101894378662,
+      "learning_rate": 2.398015640242351e-05,
+      "loss": 0.4178,
+      "step": 665
+    },
+    {
+      "epoch": 1.671660424469413,
+      "grad_norm": 0.9790671467781067,
+      "learning_rate": 2.3880729584814575e-05,
+      "loss": 0.4562,
+      "step": 670
+    },
+    {
+      "epoch": 1.6841448189762795,
+      "grad_norm": 1.1061886548995972,
+      "learning_rate": 2.3780698328803467e-05,
+      "loss": 0.407,
+      "step": 675
+    },
+    {
+      "epoch": 1.696629213483146,
+      "grad_norm": 0.9817659854888916,
+      "learning_rate": 2.368006944269709e-05,
+      "loss": 0.4274,
+      "step": 680
+    },
+    {
+      "epoch": 1.7091136079900124,
+      "grad_norm": 1.0625079870224,
+      "learning_rate": 2.3578849775478124e-05,
+      "loss": 0.3839,
+      "step": 685
+    },
+    {
+      "epoch": 1.7215980024968789,
+      "grad_norm": 1.0568345785140991,
+      "learning_rate": 2.3477046216338877e-05,
+      "loss": 0.3915,
+      "step": 690
+    },
+    {
+      "epoch": 1.7340823970037453,
+      "grad_norm": 1.054922342300415,
+      "learning_rate": 2.337466569421239e-05,
+      "loss": 0.426,
+      "step": 695
+    },
+    {
+      "epoch": 1.7465667915106118,
+      "grad_norm": 1.109113097190857,
+      "learning_rate": 2.327171517730084e-05,
+      "loss": 0.4058,
+      "step": 700
+    },
+    {
+      "epoch": 1.7590511860174782,
+      "grad_norm": 1.0435470342636108,
+      "learning_rate": 2.3168201672601263e-05,
+      "loss": 0.4703,
+      "step": 705
+    },
+    {
+      "epoch": 1.7715355805243447,
+      "grad_norm": 1.0479152202606201,
+      "learning_rate": 2.306413222542866e-05,
+      "loss": 0.3692,
+      "step": 710
+    },
+    {
+      "epoch": 1.7840199750312111,
+      "grad_norm": 1.0771406888961792,
+      "learning_rate": 2.2959513918936488e-05,
+      "loss": 0.397,
+      "step": 715
+    },
+    {
+      "epoch": 1.7965043695380774,
+      "grad_norm": 1.0804780721664429,
+      "learning_rate": 2.2854353873634536e-05,
+      "loss": 0.3722,
+      "step": 720
+    },
+    {
+      "epoch": 1.8089887640449438,
+      "grad_norm": 1.2521559000015259,
+      "learning_rate": 2.274865924690432e-05,
+      "loss": 0.426,
+      "step": 725
+    },
+    {
+      "epoch": 1.8214731585518102,
+      "grad_norm": 0.9907971024513245,
+      "learning_rate": 2.2642437232511926e-05,
+      "loss": 0.3528,
+      "step": 730
+    },
+    {
+      "epoch": 1.8339575530586767,
+      "grad_norm": 1.2269495725631714,
+      "learning_rate": 2.2535695060118392e-05,
+      "loss": 0.3983,
+      "step": 735
+    },
+    {
+      "epoch": 1.846441947565543,
+      "grad_norm": 0.960803210735321,
+      "learning_rate": 2.242843999478764e-05,
+      "loss": 0.3916,
+      "step": 740
+    },
+    {
+      "epoch": 1.8589263420724094,
+      "grad_norm": 1.123892068862915,
+      "learning_rate": 2.2320679336492e-05,
+      "loss": 0.3705,
+      "step": 745
+    },
+    {
+      "epoch": 1.8714107365792758,
+      "grad_norm": 0.9948912858963013,
+      "learning_rate": 2.221242041961539e-05,
+      "loss": 0.3702,
+      "step": 750
+    },
+    {
+      "epoch": 1.8838951310861423,
+      "grad_norm": 1.0175302028656006,
+      "learning_rate": 2.210367061245408e-05,
+      "loss": 0.3855,
+      "step": 755
+    },
+    {
+      "epoch": 1.8963795255930087,
+      "grad_norm": 0.9982346892356873,
+      "learning_rate": 2.199443731671522e-05,
+      "loss": 0.354,
+      "step": 760
+    },
+    {
+      "epoch": 1.9088639200998752,
+      "grad_norm": 1.0150700807571411,
+      "learning_rate": 2.1884727967013065e-05,
+      "loss": 0.413,
+      "step": 765
+    },
+    {
+      "epoch": 1.9213483146067416,
+      "grad_norm": 1.300173282623291,
+      "learning_rate": 2.1774550030362956e-05,
+      "loss": 0.352,
+      "step": 770
+    },
+    {
+      "epoch": 1.933832709113608,
+      "grad_norm": 0.9992619752883911,
+      "learning_rate": 2.1663911005673092e-05,
+      "loss": 0.4219,
+      "step": 775
+    },
+    {
+      "epoch": 1.9463171036204745,
+      "grad_norm": 1.2440812587738037,
+      "learning_rate": 2.1552818423234175e-05,
+      "loss": 0.3394,
+      "step": 780
+    },
+    {
+      "epoch": 1.958801498127341,
+      "grad_norm": 1.0696502923965454,
+      "learning_rate": 2.1441279844206846e-05,
+      "loss": 0.3864,
+      "step": 785
+    },
+    {
+      "epoch": 1.9712858926342074,
+      "grad_norm": 1.016789436340332,
+      "learning_rate": 2.1329302860107065e-05,
+      "loss": 0.3774,
+      "step": 790
+    },
+    {
+      "epoch": 1.9837702871410736,
+      "grad_norm": 1.07418692111969,
+      "learning_rate": 2.1216895092289457e-05,
+      "loss": 0.3181,
+      "step": 795
+    },
+    {
+      "epoch": 1.99625468164794,
+      "grad_norm": 0.966789186000824,
+      "learning_rate": 2.1104064191428533e-05,
+      "loss": 0.3103,
+      "step": 800
+    },
+    {
+      "epoch": 2.00749063670412,
+      "grad_norm": 1.002647042274475,
+      "learning_rate": 2.099081783699801e-05,
+      "loss": 0.3005,
+      "step": 805
+    },
+    {
+      "epoch": 2.0199750312109863,
+      "grad_norm": 1.0245938301086426,
+      "learning_rate": 2.087716373674813e-05,
+      "loss": 0.3047,
+      "step": 810
+    },
+    {
+      "epoch": 2.0324594257178528,
+      "grad_norm": 1.0427420139312744,
+      "learning_rate": 2.076310962618103e-05,
+      "loss": 0.3121,
+      "step": 815
+    },
+    {
+      "epoch": 2.044943820224719,
+      "grad_norm": 1.3296570777893066,
+      "learning_rate": 2.0648663268024277e-05,
+      "loss": 0.3192,
+      "step": 820
+    },
+    {
+      "epoch": 2.0574282147315857,
+      "grad_norm": 0.9476227760314941,
+      "learning_rate": 2.0533832451702515e-05,
+      "loss": 0.296,
+      "step": 825
+    },
+    {
+      "epoch": 2.069912609238452,
+      "grad_norm": 1.121168851852417,
+      "learning_rate": 2.0418624992807297e-05,
+      "loss": 0.2905,
+      "step": 830
+    },
+    {
+      "epoch": 2.0823970037453186,
+      "grad_norm": 1.1799355745315552,
+      "learning_rate": 2.0303048732565138e-05,
+      "loss": 0.2915,
+      "step": 835
+    },
+    {
+      "epoch": 2.0948813982521846,
+      "grad_norm": 0.994766354560852,
+      "learning_rate": 2.0187111537303863e-05,
+      "loss": 0.2932,
+      "step": 840
+    },
+    {
+      "epoch": 2.107365792759051,
+      "grad_norm": 1.1018110513687134,
+      "learning_rate": 2.007082129791715e-05,
+      "loss": 0.3032,
+      "step": 845
+    },
+    {
+      "epoch": 2.1198501872659175,
+      "grad_norm": 1.4354578256607056,
+      "learning_rate": 1.995418592932751e-05,
+      "loss": 0.247,
+      "step": 850
+    },
+    {
+      "epoch": 2.132334581772784,
+      "grad_norm": 1.0885084867477417,
+      "learning_rate": 1.983721336994756e-05,
+      "loss": 0.2556,
+      "step": 855
+    },
+    {
+      "epoch": 2.1448189762796503,
+      "grad_norm": 1.0800628662109375,
+      "learning_rate": 1.9719911581139745e-05,
+      "loss": 0.2729,
+      "step": 860
+    },
+    {
+      "epoch": 2.157303370786517,
+      "grad_norm": 1.06325101852417,
+      "learning_rate": 1.9602288546674428e-05,
+      "loss": 0.2811,
+      "step": 865
+    },
+    {
+      "epoch": 2.1697877652933832,
+      "grad_norm": 1.0482604503631592,
+      "learning_rate": 1.9484352272186555e-05,
+      "loss": 0.2618,
+      "step": 870
+    },
+    {
+      "epoch": 2.1822721598002497,
+      "grad_norm": 1.141526222229004,
+      "learning_rate": 1.9366110784630737e-05,
+      "loss": 0.2702,
+      "step": 875
+    },
+    {
+      "epoch": 2.194756554307116,
+      "grad_norm": 1.198039174079895,
+      "learning_rate": 1.9247572131734937e-05,
+      "loss": 0.3,
+      "step": 880
+    },
+    {
+      "epoch": 2.2072409488139826,
+      "grad_norm": 1.1142116785049438,
+      "learning_rate": 1.912874438145272e-05,
+      "loss": 0.2682,
+      "step": 885
+    },
+    {
+      "epoch": 2.219725343320849,
+      "grad_norm": 1.2313395738601685,
+      "learning_rate": 1.9009635621414152e-05,
+      "loss": 0.2852,
+      "step": 890
+    },
+    {
+      "epoch": 2.2322097378277155,
+      "grad_norm": 1.0495308637619019,
+      "learning_rate": 1.8890253958375305e-05,
+      "loss": 0.2299,
+      "step": 895
+    },
+    {
+      "epoch": 2.244694132334582,
+      "grad_norm": 1.21982741355896,
+      "learning_rate": 1.8770607517666542e-05,
+      "loss": 0.2623,
+      "step": 900
+    },
+    {
+      "epoch": 2.2571785268414484,
+      "grad_norm": 1.0054216384887695,
+      "learning_rate": 1.8650704442639457e-05,
+      "loss": 0.2545,
+      "step": 905
+    },
+    {
+      "epoch": 2.2696629213483144,
+      "grad_norm": 1.060891032218933,
+      "learning_rate": 1.8530552894112638e-05,
+      "loss": 0.2593,
+      "step": 910
+    },
+    {
+      "epoch": 2.2821473158551813,
+      "grad_norm": 1.1009420156478882,
+      "learning_rate": 1.8410161049816232e-05,
+      "loss": 0.2509,
+      "step": 915
+    },
+    {
+      "epoch": 2.2946317103620473,
+      "grad_norm": 1.0419282913208008,
+      "learning_rate": 1.828953710383534e-05,
+      "loss": 0.2715,
+      "step": 920
+    },
+    {
+      "epoch": 2.3071161048689137,
+      "grad_norm": 1.0459412336349487,
+      "learning_rate": 1.8168689266052318e-05,
+      "loss": 0.2371,
+      "step": 925
+    },
+    {
+      "epoch": 2.31960049937578,
+      "grad_norm": 1.1189764738082886,
+      "learning_rate": 1.8047625761588016e-05,
+      "loss": 0.2476,
+      "step": 930
+    },
+    {
+      "epoch": 2.3320848938826466,
+      "grad_norm": 1.1009725332260132,
+      "learning_rate": 1.7926354830241928e-05,
+      "loss": 0.2687,
+      "step": 935
+    },
+    {
+      "epoch": 2.344569288389513,
+      "grad_norm": 0.9328509569168091,
+      "learning_rate": 1.7804884725931396e-05,
+      "loss": 0.2356,
+      "step": 940
+    },
+    {
+      "epoch": 2.3570536828963795,
+      "grad_norm": 1.1894066333770752,
+      "learning_rate": 1.768322371612985e-05,
+      "loss": 0.2763,
+      "step": 945
+    },
+    {
+      "epoch": 2.369538077403246,
+      "grad_norm": 1.03666090965271,
+      "learning_rate": 1.7561380081304063e-05,
+      "loss": 0.2759,
+      "step": 950
+    },
+    {
+      "epoch": 2.3820224719101124,
+      "grad_norm": 1.088082194328308,
+      "learning_rate": 1.7439362114350617e-05,
+      "loss": 0.269,
+      "step": 955
+    },
+    {
+      "epoch": 2.394506866416979,
+      "grad_norm": 0.9877581596374512,
+      "learning_rate": 1.7317178120031447e-05,
+      "loss": 0.2476,
+      "step": 960
+    },
+    {
+      "epoch": 2.4069912609238453,
+      "grad_norm": 1.363715410232544,
+      "learning_rate": 1.7194836414408595e-05,
+      "loss": 0.2374,
+      "step": 965
+    },
+    {
+      "epoch": 2.4194756554307117,
+      "grad_norm": 1.0909315347671509,
+      "learning_rate": 1.7072345324278235e-05,
+      "loss": 0.2122,
+      "step": 970
+    },
+    {
+      "epoch": 2.431960049937578,
+      "grad_norm": 1.0661542415618896,
+      "learning_rate": 1.694971318660391e-05,
+      "loss": 0.2136,
+      "step": 975
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 1.0175883769989014,
+      "learning_rate": 1.6826948347949108e-05,
+      "loss": 0.2514,
+      "step": 980
+    },
+    {
+      "epoch": 2.4569288389513106,
+      "grad_norm": 1.17929208278656,
+      "learning_rate": 1.6704059163909206e-05,
+      "loss": 0.2341,
+      "step": 985
+    },
+    {
+      "epoch": 2.469413233458177,
+      "grad_norm": 1.0460587739944458,
+      "learning_rate": 1.6581053998542717e-05,
+      "loss": 0.2205,
+      "step": 990
+    },
+    {
+      "epoch": 2.4818976279650435,
+      "grad_norm": 1.2029474973678589,
+      "learning_rate": 1.6457941223802082e-05,
+      "loss": 0.2463,
+      "step": 995
+    },
+    {
+      "epoch": 2.49438202247191,
+      "grad_norm": 1.276589035987854,
+      "learning_rate": 1.6334729218963808e-05,
+      "loss": 0.2004,
+      "step": 1000
+    },
+    {
+      "epoch": 2.5068664169787764,
+      "grad_norm": 0.982111394405365,
+      "learning_rate": 1.6211426370058195e-05,
+      "loss": 0.2419,
+      "step": 1005
+    },
+    {
+      "epoch": 2.519350811485643,
+      "grad_norm": 1.0901743173599243,
+      "learning_rate": 1.6088041069298538e-05,
+      "loss": 0.2491,
+      "step": 1010
+    },
+    {
+      "epoch": 2.5318352059925093,
+      "grad_norm": 1.1286723613739014,
+      "learning_rate": 1.5964581714509975e-05,
+      "loss": 0.2398,
+      "step": 1015
+    },
+    {
+      "epoch": 2.5443196004993758,
+      "grad_norm": 0.9738107919692993,
+      "learning_rate": 1.5841056708557876e-05,
+      "loss": 0.2439,
+      "step": 1020
+    },
+    {
+      "epoch": 2.5568039950062422,
+      "grad_norm": 1.0739282369613647,
+      "learning_rate": 1.571747445877596e-05,
+      "loss": 0.2299,
+      "step": 1025
+    },
+    {
+      "epoch": 2.5692883895131087,
+      "grad_norm": 1.1265177726745605,
+      "learning_rate": 1.5593843376394043e-05,
+      "loss": 0.1978,
+      "step": 1030
+    },
+    {
+      "epoch": 2.581772784019975,
+      "grad_norm": 1.1717891693115234,
+      "learning_rate": 1.54701718759656e-05,
+      "loss": 0.2171,
+      "step": 1035
+    },
+    {
+      "epoch": 2.5942571785268416,
+      "grad_norm": 1.0216491222381592,
+      "learning_rate": 1.534646837479502e-05,
+      "loss": 0.2356,
+      "step": 1040
+    },
+    {
+      "epoch": 2.606741573033708,
+      "grad_norm": 0.9864731431007385,
+      "learning_rate": 1.522274129236471e-05,
+      "loss": 0.2043,
+      "step": 1045
+    },
+    {
+      "epoch": 2.619225967540574,
+      "grad_norm": 1.1087095737457275,
+      "learning_rate": 1.5098999049762084e-05,
+      "loss": 0.2098,
+      "step": 1050
+    },
+    {
+      "epoch": 2.631710362047441,
+      "grad_norm": 1.025351643562317,
+      "learning_rate": 1.4975250069106366e-05,
+      "loss": 0.2198,
+      "step": 1055
+    },
+    {
+      "epoch": 2.644194756554307,
+      "grad_norm": 1.0059807300567627,
+      "learning_rate": 1.4851502772975383e-05,
+      "loss": 0.2231,
+      "step": 1060
+    },
+    {
+      "epoch": 2.656679151061174,
+      "grad_norm": 1.0516254901885986,
+      "learning_rate": 1.472776558383232e-05,
+      "loss": 0.212,
+      "step": 1065
+    },
+    {
+      "epoch": 2.66916354556804,
+      "grad_norm": 0.9578256607055664,
+      "learning_rate": 1.460404692345246e-05,
+      "loss": 0.1921,
+      "step": 1070
+    },
+    {
+      "epoch": 2.6816479400749063,
+      "grad_norm": 1.1407796144485474,
+      "learning_rate": 1.4480355212349979e-05,
+      "loss": 0.2078,
+      "step": 1075
+    },
+    {
+      "epoch": 2.6941323345817727,
+      "grad_norm": 1.0777312517166138,
+      "learning_rate": 1.435669886920484e-05,
+      "loss": 0.2346,
+      "step": 1080
+    },
+    {
+      "epoch": 2.706616729088639,
+      "grad_norm": 1.1339551210403442,
+      "learning_rate": 1.4233086310289798e-05,
+      "loss": 0.2182,
+      "step": 1085
+    },
+    {
+      "epoch": 2.7191011235955056,
+      "grad_norm": 1.1140717267990112,
+      "learning_rate": 1.410952594889759e-05,
+      "loss": 0.2152,
+      "step": 1090
+    },
+    {
+      "epoch": 2.731585518102372,
+      "grad_norm": 1.208130955696106,
+      "learning_rate": 1.3986026194768273e-05,
+      "loss": 0.1886,
+      "step": 1095
+    },
+    {
+      "epoch": 2.7440699126092385,
+      "grad_norm": 1.0361547470092773,
+      "learning_rate": 1.3862595453516876e-05,
+      "loss": 0.2171,
+      "step": 1100
+    },
+    {
+      "epoch": 2.756554307116105,
+      "grad_norm": 1.1660590171813965,
+      "learning_rate": 1.3739242126061288e-05,
+      "loss": 0.2041,
+      "step": 1105
+    },
+    {
+      "epoch": 2.7690387016229714,
+      "grad_norm": 1.0942457914352417,
+      "learning_rate": 1.3615974608050472e-05,
+      "loss": 0.2038,
+      "step": 1110
+    },
+    {
+      "epoch": 2.781523096129838,
+      "grad_norm": 1.0340149402618408,
+      "learning_rate": 1.349280128929305e-05,
+      "loss": 0.1896,
+      "step": 1115
+    },
+    {
+      "epoch": 2.7940074906367043,
+      "grad_norm": 1.1459697484970093,
+      "learning_rate": 1.336973055318627e-05,
+      "loss": 0.2054,
+      "step": 1120
+    },
+    {
+      "epoch": 2.8064918851435703,
+      "grad_norm": 1.2883628606796265,
+      "learning_rate": 1.3246770776145422e-05,
+      "loss": 0.2078,
+      "step": 1125
+    },
+    {
+      "epoch": 2.818976279650437,
+      "grad_norm": 0.9940454959869385,
+      "learning_rate": 1.3123930327033729e-05,
+      "loss": 0.1785,
+      "step": 1130
+    },
+    {
+      "epoch": 2.831460674157303,
+      "grad_norm": 1.1339962482452393,
+      "learning_rate": 1.300121756659273e-05,
+      "loss": 0.2039,
+      "step": 1135
+    },
+    {
+      "epoch": 2.8439450686641696,
+      "grad_norm": 1.2658766508102417,
+      "learning_rate": 1.287864084687325e-05,
+      "loss": 0.1922,
+      "step": 1140
+    },
+    {
+      "epoch": 2.856429463171036,
+      "grad_norm": 1.1540396213531494,
+      "learning_rate": 1.2756208510666933e-05,
+      "loss": 0.2285,
+      "step": 1145
+    },
+    {
+      "epoch": 2.8689138576779025,
+      "grad_norm": 0.9347926378250122,
+      "learning_rate": 1.2633928890938437e-05,
+      "loss": 0.1796,
+      "step": 1150
+    },
+    {
+      "epoch": 2.881398252184769,
+      "grad_norm": 1.0262902975082397,
+      "learning_rate": 1.2511810310258245e-05,
+      "loss": 0.1985,
+      "step": 1155
+    },
+    {
+      "epoch": 2.8938826466916354,
+      "grad_norm": 0.8934952616691589,
+      "learning_rate": 1.2389861080236241e-05,
+      "loss": 0.1873,
+      "step": 1160
+    },
+    {
+      "epoch": 2.906367041198502,
+      "grad_norm": 1.1181169748306274,
+      "learning_rate": 1.2268089500955997e-05,
+      "loss": 0.1812,
+      "step": 1165
+    },
+    {
+      "epoch": 2.9188514357053683,
+      "grad_norm": 0.9653885364532471,
+      "learning_rate": 1.2146503860409855e-05,
+      "loss": 0.2124,
+      "step": 1170
+    },
+    {
+      "epoch": 2.9313358302122348,
+      "grad_norm": 1.0950244665145874,
+      "learning_rate": 1.2025112433934839e-05,
+      "loss": 0.1761,
+      "step": 1175
+    },
+    {
+      "epoch": 2.943820224719101,
+      "grad_norm": 1.0934033393859863,
+      "learning_rate": 1.1903923483649407e-05,
+      "loss": 0.1927,
+      "step": 1180
+    },
+    {
+      "epoch": 2.9563046192259677,
+      "grad_norm": 1.1389161348342896,
+      "learning_rate": 1.1782945257891129e-05,
+      "loss": 0.1846,
+      "step": 1185
+    },
+    {
+      "epoch": 2.968789013732834,
+      "grad_norm": 1.0164865255355835,
+      "learning_rate": 1.1662185990655285e-05,
+      "loss": 0.1746,
+      "step": 1190
+    },
+    {
+      "epoch": 2.9812734082397006,
+      "grad_norm": 0.8818990588188171,
+      "learning_rate": 1.1541653901034445e-05,
+      "loss": 0.1812,
+      "step": 1195
+    },
+    {
+      "epoch": 2.9937578027465666,
+      "grad_norm": 1.1407787799835205,
+      "learning_rate": 1.142135719265906e-05,
+      "loss": 0.2039,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2005,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9210329290189046e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

22_128_e5_3e-5/checkpoint-1203/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab908394fcc15545e42e27e85e35e75bf6a764a2a43772c9d28a145a1ae5c580
+size 7736

22_128_e5_3e-5/checkpoint-1203/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

22_128_e5_3e-5/checkpoint-1604/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ibm-granite/granite-3.3-8b-base
+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 0.15.2

22_128_e5_3e-5/checkpoint-1604/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

22_128_e5_3e-5/checkpoint-1604/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ccb4b0efc163593c826f736ae4262562a72dc859762bd6927a502bfaedb28e
+size 791751704

22_128_e5_3e-5/checkpoint-1604/latest

@@ -0,0 +1 @@
+global_step1604

22_128_e5_3e-5/checkpoint-1604/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b13006da3d12044d3960f55fd276250ee9786069f5bd66f490e778780ebcbe
+size 15920

22_128_e5_3e-5/checkpoint-1604/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631b85da41ed59a7a7f01bbb3e00a210b8e1947427f9e4478b5fe655fdc5cc05
+size 15920

22_128_e5_3e-5/checkpoint-1604/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0b62967f9de9a18bd507f2afceba66740385f8729eee9717d7265f64da9719
+size 15920

22_128_e5_3e-5/checkpoint-1604/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b140ed7af9e31e616c794411c3084d48aaf52a9978abf9dea83e4f0dbef12c1f
+size 15920

22_128_e5_3e-5/checkpoint-1604/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b7306ca80b582039dbe491121502eb92d83b66613656c47082f460033b67d2
+size 15920

22_128_e5_3e-5/checkpoint-1604/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f423f179c1e79ac50922e9cbe36e2d0bc24110ab0963676506c11c6f4b34fa
+size 15920

22_128_e5_3e-5/checkpoint-1604/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7537b243bdb77910ac75057ff32ed3a16275819bc94a11d7574adbe76369727b
+size 15920

22_128_e5_3e-5/checkpoint-1604/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba4496b67add0d62fb59e37cba3f6a0390feba255fd9fa7efaee6f1a7c9909b
+size 15920

22_128_e5_3e-5/checkpoint-1604/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea8222501a10195e5971de0c080e52b457881fb5b81b44746e854ad91ce78b5d
+size 1064

22_128_e5_3e-5/checkpoint-1604/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

22_128_e5_3e-5/checkpoint-1604/tokenizer_config.json

@@ -0,0 +1,188 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

22_128_e5_3e-5/checkpoint-1604/trainer_state.json

@@ -0,0 +1,2274 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1604,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012484394506866416,
+      "grad_norm": 1.250030279159546,
+      "learning_rate": 1.1881188118811881e-06,
+      "loss": 1.3024,
+      "step": 5
+    },
+    {
+      "epoch": 0.024968789013732832,
+      "grad_norm": 1.0841675996780396,
+      "learning_rate": 2.673267326732673e-06,
+      "loss": 1.3147,
+      "step": 10
+    },
+    {
+      "epoch": 0.03745318352059925,
+      "grad_norm": 0.6254027485847473,
+      "learning_rate": 4.158415841584159e-06,
+      "loss": 1.2397,
+      "step": 15
+    },
+    {
+      "epoch": 0.049937578027465665,
+      "grad_norm": 0.5402944684028625,
+      "learning_rate": 5.643564356435644e-06,
+      "loss": 1.2073,
+      "step": 20
+    },
+    {
+      "epoch": 0.062421972534332085,
+      "grad_norm": 0.47610044479370117,
+      "learning_rate": 7.128712871287129e-06,
+      "loss": 1.2178,
+      "step": 25
+    },
+    {
+      "epoch": 0.0749063670411985,
+      "grad_norm": 0.5858327746391296,
+      "learning_rate": 8.613861386138613e-06,
+      "loss": 1.238,
+      "step": 30
+    },
+    {
+      "epoch": 0.08739076154806492,
+      "grad_norm": 0.5472700595855713,
+      "learning_rate": 1.00990099009901e-05,
+      "loss": 1.2016,
+      "step": 35
+    },
+    {
+      "epoch": 0.09987515605493133,
+      "grad_norm": 0.44305941462516785,
+      "learning_rate": 1.1584158415841584e-05,
+      "loss": 1.184,
+      "step": 40
+    },
+    {
+      "epoch": 0.11235955056179775,
+      "grad_norm": 0.4975726902484894,
+      "learning_rate": 1.306930693069307e-05,
+      "loss": 1.2251,
+      "step": 45
+    },
+    {
+      "epoch": 0.12484394506866417,
+      "grad_norm": 0.43187275528907776,
+      "learning_rate": 1.4554455445544554e-05,
+      "loss": 1.1542,
+      "step": 50
+    },
+    {
+      "epoch": 0.1373283395755306,
+      "grad_norm": 0.4613569974899292,
+      "learning_rate": 1.6039603960396042e-05,
+      "loss": 1.1681,
+      "step": 55
+    },
+    {
+      "epoch": 0.149812734082397,
+      "grad_norm": 0.44121506810188293,
+      "learning_rate": 1.7524752475247524e-05,
+      "loss": 1.1475,
+      "step": 60
+    },
+    {
+      "epoch": 0.16229712858926343,
+      "grad_norm": 0.4488328993320465,
+      "learning_rate": 1.900990099009901e-05,
+      "loss": 1.1619,
+      "step": 65
+    },
+    {
+      "epoch": 0.17478152309612985,
+      "grad_norm": 0.44015923142433167,
+      "learning_rate": 2.0495049504950496e-05,
+      "loss": 1.0965,
+      "step": 70
+    },
+    {
+      "epoch": 0.18726591760299627,
+      "grad_norm": 0.44825753569602966,
+      "learning_rate": 2.198019801980198e-05,
+      "loss": 1.1127,
+      "step": 75
+    },
+    {
+      "epoch": 0.19975031210986266,
+      "grad_norm": 0.4191741347312927,
+      "learning_rate": 2.3465346534653467e-05,
+      "loss": 1.1326,
+      "step": 80
+    },
+    {
+      "epoch": 0.21223470661672908,
+      "grad_norm": 0.47760850191116333,
+      "learning_rate": 2.495049504950495e-05,
+      "loss": 1.1003,
+      "step": 85
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 0.5718854069709778,
+      "learning_rate": 2.6435643564356436e-05,
+      "loss": 1.1227,
+      "step": 90
+    },
+    {
+      "epoch": 0.23720349563046192,
+      "grad_norm": 0.6666268110275269,
+      "learning_rate": 2.792079207920792e-05,
+      "loss": 1.1288,
+      "step": 95
+    },
+    {
+      "epoch": 0.24968789013732834,
+      "grad_norm": 0.44064071774482727,
+      "learning_rate": 2.9405940594059407e-05,
+      "loss": 1.065,
+      "step": 100
+    },
+    {
+      "epoch": 0.26217228464419473,
+      "grad_norm": 0.5092717409133911,
+      "learning_rate": 2.999981623248469e-05,
+      "loss": 1.0766,
+      "step": 105
+    },
+    {
+      "epoch": 0.2746566791510612,
+      "grad_norm": 0.5116708278656006,
+      "learning_rate": 2.9998693225086163e-05,
+      "loss": 1.0636,
+      "step": 110
+    },
+    {
+      "epoch": 0.28714107365792757,
+      "grad_norm": 0.5135843753814697,
+      "learning_rate": 2.9996549379694418e-05,
+      "loss": 1.0543,
+      "step": 115
+    },
+    {
+      "epoch": 0.299625468164794,
+      "grad_norm": 0.5474386811256409,
+      "learning_rate": 2.9993384842223426e-05,
+      "loss": 1.0784,
+      "step": 120
+    },
+    {
+      "epoch": 0.3121098626716604,
+      "grad_norm": 0.5349007844924927,
+      "learning_rate": 2.998919982805729e-05,
+      "loss": 1.0306,
+      "step": 125
+    },
+    {
+      "epoch": 0.32459425717852686,
+      "grad_norm": 0.5236003994941711,
+      "learning_rate": 2.998399462203559e-05,
+      "loss": 1.0462,
+      "step": 130
+    },
+    {
+      "epoch": 0.33707865168539325,
+      "grad_norm": 0.5239087343215942,
+      "learning_rate": 2.9977769578433987e-05,
+      "loss": 1.0233,
+      "step": 135
+    },
+    {
+      "epoch": 0.3495630461922597,
+      "grad_norm": 0.6136004328727722,
+      "learning_rate": 2.9970525120940132e-05,
+      "loss": 0.9779,
+      "step": 140
+    },
+    {
+      "epoch": 0.3620474406991261,
+      "grad_norm": 0.6154010891914368,
+      "learning_rate": 2.9962261742624813e-05,
+      "loss": 0.9944,
+      "step": 145
+    },
+    {
+      "epoch": 0.37453183520599254,
+      "grad_norm": 0.5972864627838135,
+      "learning_rate": 2.995298000590839e-05,
+      "loss": 1.0074,
+      "step": 150
+    },
+    {
+      "epoch": 0.38701622971285893,
+      "grad_norm": 0.5776309370994568,
+      "learning_rate": 2.9942680542522535e-05,
+      "loss": 0.9963,
+      "step": 155
+    },
+    {
+      "epoch": 0.3995006242197253,
+      "grad_norm": 0.6151773929595947,
+      "learning_rate": 2.993136405346722e-05,
+      "loss": 0.9857,
+      "step": 160
+    },
+    {
+      "epoch": 0.41198501872659177,
+      "grad_norm": 0.6129782795906067,
+      "learning_rate": 2.991903130896301e-05,
+      "loss": 1.0118,
+      "step": 165
+    },
+    {
+      "epoch": 0.42446941323345816,
+      "grad_norm": 0.6217514872550964,
+      "learning_rate": 2.9905683148398642e-05,
+      "loss": 0.9757,
+      "step": 170
+    },
+    {
+      "epoch": 0.4369538077403246,
+      "grad_norm": 0.6364917755126953,
+      "learning_rate": 2.9891320480273886e-05,
+      "loss": 0.9542,
+      "step": 175
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 0.6444506049156189,
+      "learning_rate": 2.9875944282137734e-05,
+      "loss": 0.968,
+      "step": 180
+    },
+    {
+      "epoch": 0.46192259675405745,
+      "grad_norm": 0.6949779987335205,
+      "learning_rate": 2.9859555600521838e-05,
+      "loss": 0.9255,
+      "step": 185
+    },
+    {
+      "epoch": 0.47440699126092384,
+      "grad_norm": 0.719308614730835,
+      "learning_rate": 2.9842155550869294e-05,
+      "loss": 0.9439,
+      "step": 190
+    },
+    {
+      "epoch": 0.4868913857677903,
+      "grad_norm": 0.6572843194007874,
+      "learning_rate": 2.982374531745873e-05,
+      "loss": 0.9059,
+      "step": 195
+    },
+    {
+      "epoch": 0.4993757802746567,
+      "grad_norm": 0.7524131536483765,
+      "learning_rate": 2.9804326153323683e-05,
+      "loss": 0.9322,
+      "step": 200
+    },
+    {
+      "epoch": 0.5118601747815231,
+      "grad_norm": 0.7650299072265625,
+      "learning_rate": 2.9783899380167345e-05,
+      "loss": 0.9085,
+      "step": 205
+    },
+    {
+      "epoch": 0.5243445692883895,
+      "grad_norm": 0.7098513841629028,
+      "learning_rate": 2.976246638827257e-05,
+      "loss": 0.9223,
+      "step": 210
+    },
+    {
+      "epoch": 0.5368289637952559,
+      "grad_norm": 0.8576691150665283,
+      "learning_rate": 2.974002863640727e-05,
+      "loss": 0.9254,
+      "step": 215
+    },
+    {
+      "epoch": 0.5493133583021224,
+      "grad_norm": 0.7496089339256287,
+      "learning_rate": 2.9716587651725134e-05,
+      "loss": 0.9314,
+      "step": 220
+    },
+    {
+      "epoch": 0.5617977528089888,
+      "grad_norm": 0.6800470948219299,
+      "learning_rate": 2.9692145029661664e-05,
+      "loss": 0.8435,
+      "step": 225
+    },
+    {
+      "epoch": 0.5742821473158551,
+      "grad_norm": 0.8700007796287537,
+      "learning_rate": 2.9666702433825614e-05,
+      "loss": 0.9101,
+      "step": 230
+    },
+    {
+      "epoch": 0.5867665418227216,
+      "grad_norm": 0.6640142798423767,
+      "learning_rate": 2.9640261595885735e-05,
+      "loss": 0.875,
+      "step": 235
+    },
+    {
+      "epoch": 0.599250936329588,
+      "grad_norm": 0.8278601169586182,
+      "learning_rate": 2.9612824315452943e-05,
+      "loss": 0.8479,
+      "step": 240
+    },
+    {
+      "epoch": 0.6117353308364545,
+      "grad_norm": 0.9126909375190735,
+      "learning_rate": 2.958439245995781e-05,
+      "loss": 0.8526,
+      "step": 245
+    },
+    {
+      "epoch": 0.6242197253433208,
+      "grad_norm": 0.8736037015914917,
+      "learning_rate": 2.955496796452347e-05,
+      "loss": 0.8113,
+      "step": 250
+    },
+    {
+      "epoch": 0.6367041198501873,
+      "grad_norm": 0.8721530437469482,
+      "learning_rate": 2.9524552831833924e-05,
+      "loss": 0.8612,
+      "step": 255
+    },
+    {
+      "epoch": 0.6491885143570537,
+      "grad_norm": 0.8261131048202515,
+      "learning_rate": 2.9493149131997713e-05,
+      "loss": 0.7762,
+      "step": 260
+    },
+    {
+      "epoch": 0.66167290886392,
+      "grad_norm": 0.8957151174545288,
+      "learning_rate": 2.946075900240704e-05,
+      "loss": 0.832,
+      "step": 265
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 0.916682779788971,
+      "learning_rate": 2.942738464759229e-05,
+      "loss": 0.8213,
+      "step": 270
+    },
+    {
+      "epoch": 0.686641697877653,
+      "grad_norm": 0.7609239220619202,
+      "learning_rate": 2.939302833907197e-05,
+      "loss": 0.8061,
+      "step": 275
+    },
+    {
+      "epoch": 0.6991260923845194,
+      "grad_norm": 0.8781178593635559,
+      "learning_rate": 2.9357692415198136e-05,
+      "loss": 0.7798,
+      "step": 280
+    },
+    {
+      "epoch": 0.7116104868913857,
+      "grad_norm": 0.8101415038108826,
+      "learning_rate": 2.932137928099722e-05,
+      "loss": 0.8564,
+      "step": 285
+    },
+    {
+      "epoch": 0.7240948813982522,
+      "grad_norm": 0.8110167980194092,
+      "learning_rate": 2.928409140800634e-05,
+      "loss": 0.8175,
+      "step": 290
+    },
+    {
+      "epoch": 0.7365792759051186,
+      "grad_norm": 0.7818710803985596,
+      "learning_rate": 2.9245831334105084e-05,
+      "loss": 0.7912,
+      "step": 295
+    },
+    {
+      "epoch": 0.7490636704119851,
+      "grad_norm": 0.8244704008102417,
+      "learning_rate": 2.9206601663342786e-05,
+      "loss": 0.7646,
+      "step": 300
+    },
+    {
+      "epoch": 0.7615480649188514,
+      "grad_norm": 0.8379747867584229,
+      "learning_rate": 2.916640506576128e-05,
+      "loss": 0.7671,
+      "step": 305
+    },
+    {
+      "epoch": 0.7740324594257179,
+      "grad_norm": 0.8790676593780518,
+      "learning_rate": 2.9125244277213176e-05,
+      "loss": 0.7688,
+      "step": 310
+    },
+    {
+      "epoch": 0.7865168539325843,
+      "grad_norm": 0.9378462433815002,
+      "learning_rate": 2.908312209917565e-05,
+      "loss": 0.7718,
+      "step": 315
+    },
+    {
+      "epoch": 0.7990012484394506,
+      "grad_norm": 0.8543297052383423,
+      "learning_rate": 2.904004139855978e-05,
+      "loss": 0.7663,
+      "step": 320
+    },
+    {
+      "epoch": 0.8114856429463171,
+      "grad_norm": 0.8526532053947449,
+      "learning_rate": 2.8996005107515405e-05,
+      "loss": 0.7911,
+      "step": 325
+    },
+    {
+      "epoch": 0.8239700374531835,
+      "grad_norm": 0.8875757455825806,
+      "learning_rate": 2.8951016223231567e-05,
+      "loss": 0.7511,
+      "step": 330
+    },
+    {
+      "epoch": 0.83645443196005,
+      "grad_norm": 0.8844619393348694,
+      "learning_rate": 2.890507780773252e-05,
+      "loss": 0.7234,
+      "step": 335
+    },
+    {
+      "epoch": 0.8489388264669163,
+      "grad_norm": 0.896385908126831,
+      "learning_rate": 2.8858192987669303e-05,
+      "loss": 0.699,
+      "step": 340
+    },
+    {
+      "epoch": 0.8614232209737828,
+      "grad_norm": 1.157642126083374,
+      "learning_rate": 2.881036495410696e-05,
+      "loss": 0.7825,
+      "step": 345
+    },
+    {
+      "epoch": 0.8739076154806492,
+      "grad_norm": 0.9201584458351135,
+      "learning_rate": 2.8761596962307343e-05,
+      "loss": 0.6774,
+      "step": 350
+    },
+    {
+      "epoch": 0.8863920099875156,
+      "grad_norm": 0.924287736415863,
+      "learning_rate": 2.871189233150754e-05,
+      "loss": 0.7057,
+      "step": 355
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.9572568535804749,
+      "learning_rate": 2.8661254444693975e-05,
+      "loss": 0.7201,
+      "step": 360
+    },
+    {
+      "epoch": 0.9113607990012484,
+      "grad_norm": 1.010705828666687,
+      "learning_rate": 2.8609686748372155e-05,
+      "loss": 0.776,
+      "step": 365
+    },
+    {
+      "epoch": 0.9238451935081149,
+      "grad_norm": 0.8497414588928223,
+      "learning_rate": 2.8557192752332082e-05,
+      "loss": 0.7348,
+      "step": 370
+    },
+    {
+      "epoch": 0.9363295880149812,
+      "grad_norm": 0.9973917603492737,
+      "learning_rate": 2.8503776029409398e-05,
+      "loss": 0.6799,
+      "step": 375
+    },
+    {
+      "epoch": 0.9488139825218477,
+      "grad_norm": 1.0082824230194092,
+      "learning_rate": 2.844944021524217e-05,
+      "loss": 0.6975,
+      "step": 380
+    },
+    {
+      "epoch": 0.9612983770287141,
+      "grad_norm": 1.0351635217666626,
+      "learning_rate": 2.8394189008023482e-05,
+      "loss": 0.715,
+      "step": 385
+    },
+    {
+      "epoch": 0.9737827715355806,
+      "grad_norm": 0.9392898082733154,
+      "learning_rate": 2.833802616824972e-05,
+      "loss": 0.7083,
+      "step": 390
+    },
+    {
+      "epoch": 0.9862671660424469,
+      "grad_norm": 0.9130701422691345,
+      "learning_rate": 2.8280955518464587e-05,
+      "loss": 0.671,
+      "step": 395
+    },
+    {
+      "epoch": 0.9987515605493134,
+      "grad_norm": 0.8589998483657837,
+      "learning_rate": 2.8222980942999005e-05,
+      "loss": 0.6443,
+      "step": 400
+    },
+    {
+      "epoch": 1.0099875156054932,
+      "grad_norm": 1.179226279258728,
+      "learning_rate": 2.8164106387706675e-05,
+      "loss": 0.5978,
+      "step": 405
+    },
+    {
+      "epoch": 1.0224719101123596,
+      "grad_norm": 1.1383295059204102,
+      "learning_rate": 2.8104335859695545e-05,
+      "loss": 0.6234,
+      "step": 410
+    },
+    {
+      "epoch": 1.034956304619226,
+      "grad_norm": 1.0137205123901367,
+      "learning_rate": 2.8043673427055076e-05,
+      "loss": 0.5565,
+      "step": 415
+    },
+    {
+      "epoch": 1.0474406991260923,
+      "grad_norm": 0.9573396444320679,
+      "learning_rate": 2.7982123218579373e-05,
+      "loss": 0.5922,
+      "step": 420
+    },
+    {
+      "epoch": 1.0599250936329587,
+      "grad_norm": 0.9142056107521057,
+      "learning_rate": 2.7919689423486136e-05,
+      "loss": 0.5344,
+      "step": 425
+    },
+    {
+      "epoch": 1.0724094881398252,
+      "grad_norm": 1.0959941148757935,
+      "learning_rate": 2.785637629113157e-05,
+      "loss": 0.5991,
+      "step": 430
+    },
+    {
+      "epoch": 1.0848938826466916,
+      "grad_norm": 1.0628936290740967,
+      "learning_rate": 2.779218813072116e-05,
+      "loss": 0.6041,
+      "step": 435
+    },
+    {
+      "epoch": 1.097378277153558,
+      "grad_norm": 1.1268197298049927,
+      "learning_rate": 2.7727129311016346e-05,
+      "loss": 0.5696,
+      "step": 440
+    },
+    {
+      "epoch": 1.1098626716604245,
+      "grad_norm": 1.011999249458313,
+      "learning_rate": 2.7661204260037234e-05,
+      "loss": 0.5735,
+      "step": 445
+    },
+    {
+      "epoch": 1.122347066167291,
+      "grad_norm": 0.9339777827262878,
+      "learning_rate": 2.7594417464761165e-05,
+      "loss": 0.5435,
+      "step": 450
+    },
+    {
+      "epoch": 1.1348314606741572,
+      "grad_norm": 0.9832940697669983,
+      "learning_rate": 2.7526773470817353e-05,
+      "loss": 0.5349,
+      "step": 455
+    },
+    {
+      "epoch": 1.1473158551810236,
+      "grad_norm": 0.9407443404197693,
+      "learning_rate": 2.745827688217749e-05,
+      "loss": 0.5582,
+      "step": 460
+    },
+    {
+      "epoch": 1.15980024968789,
+      "grad_norm": 1.006485939025879,
+      "learning_rate": 2.7388932360842394e-05,
+      "loss": 0.5492,
+      "step": 465
+    },
+    {
+      "epoch": 1.1722846441947565,
+      "grad_norm": 0.997183084487915,
+      "learning_rate": 2.7318744626524704e-05,
+      "loss": 0.5265,
+      "step": 470
+    },
+    {
+      "epoch": 1.184769038701623,
+      "grad_norm": 0.9414803385734558,
+      "learning_rate": 2.7247718456327656e-05,
+      "loss": 0.5636,
+      "step": 475
+    },
+    {
+      "epoch": 1.1972534332084894,
+      "grad_norm": 0.9664161801338196,
+      "learning_rate": 2.717585868441992e-05,
+      "loss": 0.5622,
+      "step": 480
+    },
+    {
+      "epoch": 1.2097378277153559,
+      "grad_norm": 1.2472707033157349,
+      "learning_rate": 2.7103170201706615e-05,
+      "loss": 0.517,
+      "step": 485
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 1.0070255994796753,
+      "learning_rate": 2.7029657955496392e-05,
+      "loss": 0.538,
+      "step": 490
+    },
+    {
+      "epoch": 1.2347066167290885,
+      "grad_norm": 1.0936633348464966,
+      "learning_rate": 2.6955326949164738e-05,
+      "loss": 0.5338,
+      "step": 495
+    },
+    {
+      "epoch": 1.247191011235955,
+      "grad_norm": 1.0601006746292114,
+      "learning_rate": 2.688018224181341e-05,
+      "loss": 0.5381,
+      "step": 500
+    },
+    {
+      "epoch": 1.2596754057428214,
+      "grad_norm": 1.0741894245147705,
+      "learning_rate": 2.6804228947926125e-05,
+      "loss": 0.4972,
+      "step": 505
+    },
+    {
+      "epoch": 1.2721598002496879,
+      "grad_norm": 0.8921645283699036,
+      "learning_rate": 2.672747223702045e-05,
+      "loss": 0.5096,
+      "step": 510
+    },
+    {
+      "epoch": 1.2846441947565543,
+      "grad_norm": 0.9685996174812317,
+      "learning_rate": 2.6649917333295956e-05,
+      "loss": 0.5174,
+      "step": 515
+    },
+    {
+      "epoch": 1.2971285892634208,
+      "grad_norm": 0.9764025807380676,
+      "learning_rate": 2.657156951527865e-05,
+      "loss": 0.5165,
+      "step": 520
+    },
+    {
+      "epoch": 1.309612983770287,
+      "grad_norm": 1.0654433965682983,
+      "learning_rate": 2.649243411546171e-05,
+      "loss": 0.5041,
+      "step": 525
+    },
+    {
+      "epoch": 1.3220973782771535,
+      "grad_norm": 1.050934910774231,
+      "learning_rate": 2.6412516519942554e-05,
+      "loss": 0.5104,
+      "step": 530
+    },
+    {
+      "epoch": 1.33458177278402,
+      "grad_norm": 1.0428624153137207,
+      "learning_rate": 2.6331822168056234e-05,
+      "loss": 0.4698,
+      "step": 535
+    },
+    {
+      "epoch": 1.3470661672908864,
+      "grad_norm": 1.0803771018981934,
+      "learning_rate": 2.6250356552005234e-05,
+      "loss": 0.4493,
+      "step": 540
+    },
+    {
+      "epoch": 1.3595505617977528,
+      "grad_norm": 1.0904477834701538,
+      "learning_rate": 2.6168125216485666e-05,
+      "loss": 0.4573,
+      "step": 545
+    },
+    {
+      "epoch": 1.3720349563046192,
+      "grad_norm": 1.0958645343780518,
+      "learning_rate": 2.6085133758309887e-05,
+      "loss": 0.5288,
+      "step": 550
+    },
+    {
+      "epoch": 1.3845193508114857,
+      "grad_norm": 1.12440824508667,
+      "learning_rate": 2.6001387826025564e-05,
+      "loss": 0.485,
+      "step": 555
+    },
+    {
+      "epoch": 1.3970037453183521,
+      "grad_norm": 1.0093923807144165,
+      "learning_rate": 2.591689311953122e-05,
+      "loss": 0.4735,
+      "step": 560
+    },
+    {
+      "epoch": 1.4094881398252186,
+      "grad_norm": 0.8993324041366577,
+      "learning_rate": 2.5831655389688308e-05,
+      "loss": 0.4851,
+      "step": 565
+    },
+    {
+      "epoch": 1.4219725343320848,
+      "grad_norm": 1.028627634048462,
+      "learning_rate": 2.5745680437929774e-05,
+      "loss": 0.4648,
+      "step": 570
+    },
+    {
+      "epoch": 1.4344569288389513,
+      "grad_norm": 1.0453159809112549,
+      "learning_rate": 2.565897411586522e-05,
+      "loss": 0.4848,
+      "step": 575
+    },
+    {
+      "epoch": 1.4469413233458177,
+      "grad_norm": 1.0226070880889893,
+      "learning_rate": 2.557154232488261e-05,
+      "loss": 0.4758,
+      "step": 580
+    },
+    {
+      "epoch": 1.4594257178526842,
+      "grad_norm": 1.1143102645874023,
+      "learning_rate": 2.548339101574664e-05,
+      "loss": 0.4989,
+      "step": 585
+    },
+    {
+      "epoch": 1.4719101123595506,
+      "grad_norm": 1.159244179725647,
+      "learning_rate": 2.5394526188193706e-05,
+      "loss": 0.476,
+      "step": 590
+    },
+    {
+      "epoch": 1.484394506866417,
+      "grad_norm": 1.282088041305542,
+      "learning_rate": 2.5304953890523526e-05,
+      "loss": 0.492,
+      "step": 595
+    },
+    {
+      "epoch": 1.4968789013732833,
+      "grad_norm": 1.136864423751831,
+      "learning_rate": 2.521468021918753e-05,
+      "loss": 0.4168,
+      "step": 600
+    },
+    {
+      "epoch": 1.5093632958801497,
+      "grad_norm": 1.0521190166473389,
+      "learning_rate": 2.5123711318373886e-05,
+      "loss": 0.4764,
+      "step": 605
+    },
+    {
+      "epoch": 1.5218476903870162,
+      "grad_norm": 1.1445989608764648,
+      "learning_rate": 2.5032053379589327e-05,
+      "loss": 0.4669,
+      "step": 610
+    },
+    {
+      "epoch": 1.5343320848938826,
+      "grad_norm": 1.2416304349899292,
+      "learning_rate": 2.493971264123776e-05,
+      "loss": 0.4868,
+      "step": 615
+    },
+    {
+      "epoch": 1.546816479400749,
+      "grad_norm": 1.0602422952651978,
+      "learning_rate": 2.484669538819564e-05,
+      "loss": 0.4246,
+      "step": 620
+    },
+    {
+      "epoch": 1.5593008739076155,
+      "grad_norm": 1.0995105504989624,
+      "learning_rate": 2.4753007951384236e-05,
+      "loss": 0.4557,
+      "step": 625
+    },
+    {
+      "epoch": 1.571785268414482,
+      "grad_norm": 1.056087851524353,
+      "learning_rate": 2.4658656707338733e-05,
+      "loss": 0.4376,
+      "step": 630
+    },
+    {
+      "epoch": 1.5842696629213484,
+      "grad_norm": 1.069985270500183,
+      "learning_rate": 2.4563648077774217e-05,
+      "loss": 0.4328,
+      "step": 635
+    },
+    {
+      "epoch": 1.5967540574282149,
+      "grad_norm": 1.0622888803482056,
+      "learning_rate": 2.446798852914862e-05,
+      "loss": 0.4295,
+      "step": 640
+    },
+    {
+      "epoch": 1.6092384519350813,
+      "grad_norm": 1.1215320825576782,
+      "learning_rate": 2.4371684572222596e-05,
+      "loss": 0.4429,
+      "step": 645
+    },
+    {
+      "epoch": 1.6217228464419475,
+      "grad_norm": 0.973064661026001,
+      "learning_rate": 2.427474276161637e-05,
+      "loss": 0.4127,
+      "step": 650
+    },
+    {
+      "epoch": 1.634207240948814,
+      "grad_norm": 1.140210747718811,
+      "learning_rate": 2.417716969536365e-05,
+      "loss": 0.4128,
+      "step": 655
+    },
+    {
+      "epoch": 1.6466916354556804,
+      "grad_norm": 0.985823929309845,
+      "learning_rate": 2.4078972014462533e-05,
+      "loss": 0.4305,
+      "step": 660
+    },
+    {
+      "epoch": 1.6591760299625467,
+      "grad_norm": 1.1081101894378662,
+      "learning_rate": 2.398015640242351e-05,
+      "loss": 0.4178,
+      "step": 665
+    },
+    {
+      "epoch": 1.671660424469413,
+      "grad_norm": 0.9790671467781067,
+      "learning_rate": 2.3880729584814575e-05,
+      "loss": 0.4562,
+      "step": 670
+    },
+    {
+      "epoch": 1.6841448189762795,
+      "grad_norm": 1.1061886548995972,
+      "learning_rate": 2.3780698328803467e-05,
+      "loss": 0.407,
+      "step": 675
+    },
+    {
+      "epoch": 1.696629213483146,
+      "grad_norm": 0.9817659854888916,
+      "learning_rate": 2.368006944269709e-05,
+      "loss": 0.4274,
+      "step": 680
+    },
+    {
+      "epoch": 1.7091136079900124,
+      "grad_norm": 1.0625079870224,
+      "learning_rate": 2.3578849775478124e-05,
+      "loss": 0.3839,
+      "step": 685
+    },
+    {
+      "epoch": 1.7215980024968789,
+      "grad_norm": 1.0568345785140991,
+      "learning_rate": 2.3477046216338877e-05,
+      "loss": 0.3915,
+      "step": 690
+    },
+    {
+      "epoch": 1.7340823970037453,
+      "grad_norm": 1.054922342300415,
+      "learning_rate": 2.337466569421239e-05,
+      "loss": 0.426,
+      "step": 695
+    },
+    {
+      "epoch": 1.7465667915106118,
+      "grad_norm": 1.109113097190857,
+      "learning_rate": 2.327171517730084e-05,
+      "loss": 0.4058,
+      "step": 700
+    },
+    {
+      "epoch": 1.7590511860174782,
+      "grad_norm": 1.0435470342636108,
+      "learning_rate": 2.3168201672601263e-05,
+      "loss": 0.4703,
+      "step": 705
+    },
+    {
+      "epoch": 1.7715355805243447,
+      "grad_norm": 1.0479152202606201,
+      "learning_rate": 2.306413222542866e-05,
+      "loss": 0.3692,
+      "step": 710
+    },
+    {
+      "epoch": 1.7840199750312111,
+      "grad_norm": 1.0771406888961792,
+      "learning_rate": 2.2959513918936488e-05,
+      "loss": 0.397,
+      "step": 715
+    },
+    {
+      "epoch": 1.7965043695380774,
+      "grad_norm": 1.0804780721664429,
+      "learning_rate": 2.2854353873634536e-05,
+      "loss": 0.3722,
+      "step": 720
+    },
+    {
+      "epoch": 1.8089887640449438,
+      "grad_norm": 1.2521559000015259,
+      "learning_rate": 2.274865924690432e-05,
+      "loss": 0.426,
+      "step": 725
+    },
+    {
+      "epoch": 1.8214731585518102,
+      "grad_norm": 0.9907971024513245,
+      "learning_rate": 2.2642437232511926e-05,
+      "loss": 0.3528,
+      "step": 730
+    },
+    {
+      "epoch": 1.8339575530586767,
+      "grad_norm": 1.2269495725631714,
+      "learning_rate": 2.2535695060118392e-05,
+      "loss": 0.3983,
+      "step": 735
+    },
+    {
+      "epoch": 1.846441947565543,
+      "grad_norm": 0.960803210735321,
+      "learning_rate": 2.242843999478764e-05,
+      "loss": 0.3916,
+      "step": 740
+    },
+    {
+      "epoch": 1.8589263420724094,
+      "grad_norm": 1.123892068862915,
+      "learning_rate": 2.2320679336492e-05,
+      "loss": 0.3705,
+      "step": 745
+    },
+    {
+      "epoch": 1.8714107365792758,
+      "grad_norm": 0.9948912858963013,
+      "learning_rate": 2.221242041961539e-05,
+      "loss": 0.3702,
+      "step": 750
+    },
+    {
+      "epoch": 1.8838951310861423,
+      "grad_norm": 1.0175302028656006,
+      "learning_rate": 2.210367061245408e-05,
+      "loss": 0.3855,
+      "step": 755
+    },
+    {
+      "epoch": 1.8963795255930087,
+      "grad_norm": 0.9982346892356873,
+      "learning_rate": 2.199443731671522e-05,
+      "loss": 0.354,
+      "step": 760
+    },
+    {
+      "epoch": 1.9088639200998752,
+      "grad_norm": 1.0150700807571411,
+      "learning_rate": 2.1884727967013065e-05,
+      "loss": 0.413,
+      "step": 765
+    },
+    {
+      "epoch": 1.9213483146067416,
+      "grad_norm": 1.300173282623291,
+      "learning_rate": 2.1774550030362956e-05,
+      "loss": 0.352,
+      "step": 770
+    },
+    {
+      "epoch": 1.933832709113608,
+      "grad_norm": 0.9992619752883911,
+      "learning_rate": 2.1663911005673092e-05,
+      "loss": 0.4219,
+      "step": 775
+    },
+    {
+      "epoch": 1.9463171036204745,
+      "grad_norm": 1.2440812587738037,
+      "learning_rate": 2.1552818423234175e-05,
+      "loss": 0.3394,
+      "step": 780
+    },
+    {
+      "epoch": 1.958801498127341,
+      "grad_norm": 1.0696502923965454,
+      "learning_rate": 2.1441279844206846e-05,
+      "loss": 0.3864,
+      "step": 785
+    },
+    {
+      "epoch": 1.9712858926342074,
+      "grad_norm": 1.016789436340332,
+      "learning_rate": 2.1329302860107065e-05,
+      "loss": 0.3774,
+      "step": 790
+    },
+    {
+      "epoch": 1.9837702871410736,
+      "grad_norm": 1.07418692111969,
+      "learning_rate": 2.1216895092289457e-05,
+      "loss": 0.3181,
+      "step": 795
+    },
+    {
+      "epoch": 1.99625468164794,
+      "grad_norm": 0.966789186000824,
+      "learning_rate": 2.1104064191428533e-05,
+      "loss": 0.3103,
+      "step": 800
+    },
+    {
+      "epoch": 2.00749063670412,
+      "grad_norm": 1.002647042274475,
+      "learning_rate": 2.099081783699801e-05,
+      "loss": 0.3005,
+      "step": 805
+    },
+    {
+      "epoch": 2.0199750312109863,
+      "grad_norm": 1.0245938301086426,
+      "learning_rate": 2.087716373674813e-05,
+      "loss": 0.3047,
+      "step": 810
+    },
+    {
+      "epoch": 2.0324594257178528,
+      "grad_norm": 1.0427420139312744,
+      "learning_rate": 2.076310962618103e-05,
+      "loss": 0.3121,
+      "step": 815
+    },
+    {
+      "epoch": 2.044943820224719,
+      "grad_norm": 1.3296570777893066,
+      "learning_rate": 2.0648663268024277e-05,
+      "loss": 0.3192,
+      "step": 820
+    },
+    {
+      "epoch": 2.0574282147315857,
+      "grad_norm": 0.9476227760314941,
+      "learning_rate": 2.0533832451702515e-05,
+      "loss": 0.296,
+      "step": 825
+    },
+    {
+      "epoch": 2.069912609238452,
+      "grad_norm": 1.121168851852417,
+      "learning_rate": 2.0418624992807297e-05,
+      "loss": 0.2905,
+      "step": 830
+    },
+    {
+      "epoch": 2.0823970037453186,
+      "grad_norm": 1.1799355745315552,
+      "learning_rate": 2.0303048732565138e-05,
+      "loss": 0.2915,
+      "step": 835
+    },
+    {
+      "epoch": 2.0948813982521846,
+      "grad_norm": 0.994766354560852,
+      "learning_rate": 2.0187111537303863e-05,
+      "loss": 0.2932,
+      "step": 840
+    },
+    {
+      "epoch": 2.107365792759051,
+      "grad_norm": 1.1018110513687134,
+      "learning_rate": 2.007082129791715e-05,
+      "loss": 0.3032,
+      "step": 845
+    },
+    {
+      "epoch": 2.1198501872659175,
+      "grad_norm": 1.4354578256607056,
+      "learning_rate": 1.995418592932751e-05,
+      "loss": 0.247,
+      "step": 850
+    },
+    {
+      "epoch": 2.132334581772784,
+      "grad_norm": 1.0885084867477417,
+      "learning_rate": 1.983721336994756e-05,
+      "loss": 0.2556,
+      "step": 855
+    },
+    {
+      "epoch": 2.1448189762796503,
+      "grad_norm": 1.0800628662109375,
+      "learning_rate": 1.9719911581139745e-05,
+      "loss": 0.2729,
+      "step": 860
+    },
+    {
+      "epoch": 2.157303370786517,
+      "grad_norm": 1.06325101852417,
+      "learning_rate": 1.9602288546674428e-05,
+      "loss": 0.2811,
+      "step": 865
+    },
+    {
+      "epoch": 2.1697877652933832,
+      "grad_norm": 1.0482604503631592,
+      "learning_rate": 1.9484352272186555e-05,
+      "loss": 0.2618,
+      "step": 870
+    },
+    {
+      "epoch": 2.1822721598002497,
+      "grad_norm": 1.141526222229004,
+      "learning_rate": 1.9366110784630737e-05,
+      "loss": 0.2702,
+      "step": 875
+    },
+    {
+      "epoch": 2.194756554307116,
+      "grad_norm": 1.198039174079895,
+      "learning_rate": 1.9247572131734937e-05,
+      "loss": 0.3,
+      "step": 880
+    },
+    {
+      "epoch": 2.2072409488139826,
+      "grad_norm": 1.1142116785049438,
+      "learning_rate": 1.912874438145272e-05,
+      "loss": 0.2682,
+      "step": 885
+    },
+    {
+      "epoch": 2.219725343320849,
+      "grad_norm": 1.2313395738601685,
+      "learning_rate": 1.9009635621414152e-05,
+      "loss": 0.2852,
+      "step": 890
+    },
+    {
+      "epoch": 2.2322097378277155,
+      "grad_norm": 1.0495308637619019,
+      "learning_rate": 1.8890253958375305e-05,
+      "loss": 0.2299,
+      "step": 895
+    },
+    {
+      "epoch": 2.244694132334582,
+      "grad_norm": 1.21982741355896,
+      "learning_rate": 1.8770607517666542e-05,
+      "loss": 0.2623,
+      "step": 900
+    },
+    {
+      "epoch": 2.2571785268414484,
+      "grad_norm": 1.0054216384887695,
+      "learning_rate": 1.8650704442639457e-05,
+      "loss": 0.2545,
+      "step": 905
+    },
+    {
+      "epoch": 2.2696629213483144,
+      "grad_norm": 1.060891032218933,
+      "learning_rate": 1.8530552894112638e-05,
+      "loss": 0.2593,
+      "step": 910
+    },
+    {
+      "epoch": 2.2821473158551813,
+      "grad_norm": 1.1009420156478882,
+      "learning_rate": 1.8410161049816232e-05,
+      "loss": 0.2509,
+      "step": 915
+    },
+    {
+      "epoch": 2.2946317103620473,
+      "grad_norm": 1.0419282913208008,
+      "learning_rate": 1.828953710383534e-05,
+      "loss": 0.2715,
+      "step": 920
+    },
+    {
+      "epoch": 2.3071161048689137,
+      "grad_norm": 1.0459412336349487,
+      "learning_rate": 1.8168689266052318e-05,
+      "loss": 0.2371,
+      "step": 925
+    },
+    {
+      "epoch": 2.31960049937578,
+      "grad_norm": 1.1189764738082886,
+      "learning_rate": 1.8047625761588016e-05,
+      "loss": 0.2476,
+      "step": 930
+    },
+    {
+      "epoch": 2.3320848938826466,
+      "grad_norm": 1.1009725332260132,
+      "learning_rate": 1.7926354830241928e-05,
+      "loss": 0.2687,
+      "step": 935
+    },
+    {
+      "epoch": 2.344569288389513,
+      "grad_norm": 0.9328509569168091,
+      "learning_rate": 1.7804884725931396e-05,
+      "loss": 0.2356,
+      "step": 940
+    },
+    {
+      "epoch": 2.3570536828963795,
+      "grad_norm": 1.1894066333770752,
+      "learning_rate": 1.768322371612985e-05,
+      "loss": 0.2763,
+      "step": 945
+    },
+    {
+      "epoch": 2.369538077403246,
+      "grad_norm": 1.03666090965271,
+      "learning_rate": 1.7561380081304063e-05,
+      "loss": 0.2759,
+      "step": 950
+    },
+    {
+      "epoch": 2.3820224719101124,
+      "grad_norm": 1.088082194328308,
+      "learning_rate": 1.7439362114350617e-05,
+      "loss": 0.269,
+      "step": 955
+    },
+    {
+      "epoch": 2.394506866416979,
+      "grad_norm": 0.9877581596374512,
+      "learning_rate": 1.7317178120031447e-05,
+      "loss": 0.2476,
+      "step": 960
+    },
+    {
+      "epoch": 2.4069912609238453,
+      "grad_norm": 1.363715410232544,
+      "learning_rate": 1.7194836414408595e-05,
+      "loss": 0.2374,
+      "step": 965
+    },
+    {
+      "epoch": 2.4194756554307117,
+      "grad_norm": 1.0909315347671509,
+      "learning_rate": 1.7072345324278235e-05,
+      "loss": 0.2122,
+      "step": 970
+    },
+    {
+      "epoch": 2.431960049937578,
+      "grad_norm": 1.0661542415618896,
+      "learning_rate": 1.694971318660391e-05,
+      "loss": 0.2136,
+      "step": 975
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 1.0175883769989014,
+      "learning_rate": 1.6826948347949108e-05,
+      "loss": 0.2514,
+      "step": 980
+    },
+    {
+      "epoch": 2.4569288389513106,
+      "grad_norm": 1.17929208278656,
+      "learning_rate": 1.6704059163909206e-05,
+      "loss": 0.2341,
+      "step": 985
+    },
+    {
+      "epoch": 2.469413233458177,
+      "grad_norm": 1.0460587739944458,
+      "learning_rate": 1.6581053998542717e-05,
+      "loss": 0.2205,
+      "step": 990
+    },
+    {
+      "epoch": 2.4818976279650435,
+      "grad_norm": 1.2029474973678589,
+      "learning_rate": 1.6457941223802082e-05,
+      "loss": 0.2463,
+      "step": 995
+    },
+    {
+      "epoch": 2.49438202247191,
+      "grad_norm": 1.276589035987854,
+      "learning_rate": 1.6334729218963808e-05,
+      "loss": 0.2004,
+      "step": 1000
+    },
+    {
+      "epoch": 2.5068664169787764,
+      "grad_norm": 0.982111394405365,
+      "learning_rate": 1.6211426370058195e-05,
+      "loss": 0.2419,
+      "step": 1005
+    },
+    {
+      "epoch": 2.519350811485643,
+      "grad_norm": 1.0901743173599243,
+      "learning_rate": 1.6088041069298538e-05,
+      "loss": 0.2491,
+      "step": 1010
+    },
+    {
+      "epoch": 2.5318352059925093,
+      "grad_norm": 1.1286723613739014,
+      "learning_rate": 1.5964581714509975e-05,
+      "loss": 0.2398,
+      "step": 1015
+    },
+    {
+      "epoch": 2.5443196004993758,
+      "grad_norm": 0.9738107919692993,
+      "learning_rate": 1.5841056708557876e-05,
+      "loss": 0.2439,
+      "step": 1020
+    },
+    {
+      "epoch": 2.5568039950062422,
+      "grad_norm": 1.0739282369613647,
+      "learning_rate": 1.571747445877596e-05,
+      "loss": 0.2299,
+      "step": 1025
+    },
+    {
+      "epoch": 2.5692883895131087,
+      "grad_norm": 1.1265177726745605,
+      "learning_rate": 1.5593843376394043e-05,
+      "loss": 0.1978,
+      "step": 1030
+    },
+    {
+      "epoch": 2.581772784019975,
+      "grad_norm": 1.1717891693115234,
+      "learning_rate": 1.54701718759656e-05,
+      "loss": 0.2171,
+      "step": 1035
+    },
+    {
+      "epoch": 2.5942571785268416,
+      "grad_norm": 1.0216491222381592,
+      "learning_rate": 1.534646837479502e-05,
+      "loss": 0.2356,
+      "step": 1040
+    },
+    {
+      "epoch": 2.606741573033708,
+      "grad_norm": 0.9864731431007385,
+      "learning_rate": 1.522274129236471e-05,
+      "loss": 0.2043,
+      "step": 1045
+    },
+    {
+      "epoch": 2.619225967540574,
+      "grad_norm": 1.1087095737457275,
+      "learning_rate": 1.5098999049762084e-05,
+      "loss": 0.2098,
+      "step": 1050
+    },
+    {
+      "epoch": 2.631710362047441,
+      "grad_norm": 1.025351643562317,
+      "learning_rate": 1.4975250069106366e-05,
+      "loss": 0.2198,
+      "step": 1055
+    },
+    {
+      "epoch": 2.644194756554307,
+      "grad_norm": 1.0059807300567627,
+      "learning_rate": 1.4851502772975383e-05,
+      "loss": 0.2231,
+      "step": 1060
+    },
+    {
+      "epoch": 2.656679151061174,
+      "grad_norm": 1.0516254901885986,
+      "learning_rate": 1.472776558383232e-05,
+      "loss": 0.212,
+      "step": 1065
+    },
+    {
+      "epoch": 2.66916354556804,
+      "grad_norm": 0.9578256607055664,
+      "learning_rate": 1.460404692345246e-05,
+      "loss": 0.1921,
+      "step": 1070
+    },
+    {
+      "epoch": 2.6816479400749063,
+      "grad_norm": 1.1407796144485474,
+      "learning_rate": 1.4480355212349979e-05,
+      "loss": 0.2078,
+      "step": 1075
+    },
+    {
+      "epoch": 2.6941323345817727,
+      "grad_norm": 1.0777312517166138,
+      "learning_rate": 1.435669886920484e-05,
+      "loss": 0.2346,
+      "step": 1080
+    },
+    {
+      "epoch": 2.706616729088639,
+      "grad_norm": 1.1339551210403442,
+      "learning_rate": 1.4233086310289798e-05,
+      "loss": 0.2182,
+      "step": 1085
+    },
+    {
+      "epoch": 2.7191011235955056,
+      "grad_norm": 1.1140717267990112,
+      "learning_rate": 1.410952594889759e-05,
+      "loss": 0.2152,
+      "step": 1090
+    },
+    {
+      "epoch": 2.731585518102372,
+      "grad_norm": 1.208130955696106,
+      "learning_rate": 1.3986026194768273e-05,
+      "loss": 0.1886,
+      "step": 1095
+    },
+    {
+      "epoch": 2.7440699126092385,
+      "grad_norm": 1.0361547470092773,
+      "learning_rate": 1.3862595453516876e-05,
+      "loss": 0.2171,
+      "step": 1100
+    },
+    {
+      "epoch": 2.756554307116105,
+      "grad_norm": 1.1660590171813965,
+      "learning_rate": 1.3739242126061288e-05,
+      "loss": 0.2041,
+      "step": 1105
+    },
+    {
+      "epoch": 2.7690387016229714,
+      "grad_norm": 1.0942457914352417,
+      "learning_rate": 1.3615974608050472e-05,
+      "loss": 0.2038,
+      "step": 1110
+    },
+    {
+      "epoch": 2.781523096129838,
+      "grad_norm": 1.0340149402618408,
+      "learning_rate": 1.349280128929305e-05,
+      "loss": 0.1896,
+      "step": 1115
+    },
+    {
+      "epoch": 2.7940074906367043,
+      "grad_norm": 1.1459697484970093,
+      "learning_rate": 1.336973055318627e-05,
+      "loss": 0.2054,
+      "step": 1120
+    },
+    {
+      "epoch": 2.8064918851435703,
+      "grad_norm": 1.2883628606796265,
+      "learning_rate": 1.3246770776145422e-05,
+      "loss": 0.2078,
+      "step": 1125
+    },
+    {
+      "epoch": 2.818976279650437,
+      "grad_norm": 0.9940454959869385,
+      "learning_rate": 1.3123930327033729e-05,
+      "loss": 0.1785,
+      "step": 1130
+    },
+    {
+      "epoch": 2.831460674157303,
+      "grad_norm": 1.1339962482452393,
+      "learning_rate": 1.300121756659273e-05,
+      "loss": 0.2039,
+      "step": 1135
+    },
+    {
+      "epoch": 2.8439450686641696,
+      "grad_norm": 1.2658766508102417,
+      "learning_rate": 1.287864084687325e-05,
+      "loss": 0.1922,
+      "step": 1140
+    },
+    {
+      "epoch": 2.856429463171036,
+      "grad_norm": 1.1540396213531494,
+      "learning_rate": 1.2756208510666933e-05,
+      "loss": 0.2285,
+      "step": 1145
+    },
+    {
+      "epoch": 2.8689138576779025,
+      "grad_norm": 0.9347926378250122,
+      "learning_rate": 1.2633928890938437e-05,
+      "loss": 0.1796,
+      "step": 1150
+    },
+    {
+      "epoch": 2.881398252184769,
+      "grad_norm": 1.0262902975082397,
+      "learning_rate": 1.2511810310258245e-05,
+      "loss": 0.1985,
+      "step": 1155
+    },
+    {
+      "epoch": 2.8938826466916354,
+      "grad_norm": 0.8934952616691589,
+      "learning_rate": 1.2389861080236241e-05,
+      "loss": 0.1873,
+      "step": 1160
+    },
+    {
+      "epoch": 2.906367041198502,
+      "grad_norm": 1.1181169748306274,
+      "learning_rate": 1.2268089500955997e-05,
+      "loss": 0.1812,
+      "step": 1165
+    },
+    {
+      "epoch": 2.9188514357053683,
+      "grad_norm": 0.9653885364532471,
+      "learning_rate": 1.2146503860409855e-05,
+      "loss": 0.2124,
+      "step": 1170
+    },
+    {
+      "epoch": 2.9313358302122348,
+      "grad_norm": 1.0950244665145874,
+      "learning_rate": 1.2025112433934839e-05,
+      "loss": 0.1761,
+      "step": 1175
+    },
+    {
+      "epoch": 2.943820224719101,
+      "grad_norm": 1.0934033393859863,
+      "learning_rate": 1.1903923483649407e-05,
+      "loss": 0.1927,
+      "step": 1180
+    },
+    {
+      "epoch": 2.9563046192259677,
+      "grad_norm": 1.1389161348342896,
+      "learning_rate": 1.1782945257891129e-05,
+      "loss": 0.1846,
+      "step": 1185
+    },
+    {
+      "epoch": 2.968789013732834,
+      "grad_norm": 1.0164865255355835,
+      "learning_rate": 1.1662185990655285e-05,
+      "loss": 0.1746,
+      "step": 1190
+    },
+    {
+      "epoch": 2.9812734082397006,
+      "grad_norm": 0.8818990588188171,
+      "learning_rate": 1.1541653901034445e-05,
+      "loss": 0.1812,
+      "step": 1195
+    },
+    {
+      "epoch": 2.9937578027465666,
+      "grad_norm": 1.1407787799835205,
+      "learning_rate": 1.142135719265906e-05,
+      "loss": 0.2039,
+      "step": 1200
+    },
+    {
+      "epoch": 3.0049937578027466,
+      "grad_norm": 0.9839046001434326,
+      "learning_rate": 1.1301304053139106e-05,
+      "loss": 0.156,
+      "step": 1205
+    },
+    {
+      "epoch": 3.017478152309613,
+      "grad_norm": 1.0844690799713135,
+      "learning_rate": 1.1181502653506842e-05,
+      "loss": 0.1308,
+      "step": 1210
+    },
+    {
+      "epoch": 3.0299625468164795,
+      "grad_norm": 0.935778796672821,
+      "learning_rate": 1.1061961147660642e-05,
+      "loss": 0.1559,
+      "step": 1215
+    },
+    {
+      "epoch": 3.042446941323346,
+      "grad_norm": 0.934255063533783,
+      "learning_rate": 1.0942687671810049e-05,
+      "loss": 0.1503,
+      "step": 1220
+    },
+    {
+      "epoch": 3.0549313358302124,
+      "grad_norm": 1.151432991027832,
+      "learning_rate": 1.0823690343922001e-05,
+      "loss": 0.142,
+      "step": 1225
+    },
+    {
+      "epoch": 3.067415730337079,
+      "grad_norm": 1.0379838943481445,
+      "learning_rate": 1.0704977263168312e-05,
+      "loss": 0.1445,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0799001248439453,
+      "grad_norm": 0.8675345778465271,
+      "learning_rate": 1.0586556509374421e-05,
+      "loss": 0.1423,
+      "step": 1235
+    },
+    {
+      "epoch": 3.0923845193508113,
+      "grad_norm": 1.1241868734359741,
+      "learning_rate": 1.046843614246948e-05,
+      "loss": 0.1541,
+      "step": 1240
+    },
+    {
+      "epoch": 3.1048689138576777,
+      "grad_norm": 1.1239725351333618,
+      "learning_rate": 1.0350624201937758e-05,
+      "loss": 0.1503,
+      "step": 1245
+    },
+    {
+      "epoch": 3.117353308364544,
+      "grad_norm": 0.8907927870750427,
+      "learning_rate": 1.0233128706271476e-05,
+      "loss": 0.1275,
+      "step": 1250
+    },
+    {
+      "epoch": 3.1298377028714106,
+      "grad_norm": 1.0988825559616089,
+      "learning_rate": 1.0115957652425052e-05,
+      "loss": 0.1632,
+      "step": 1255
+    },
+    {
+      "epoch": 3.142322097378277,
+      "grad_norm": 0.9812394976615906,
+      "learning_rate": 9.999119015270804e-06,
+      "loss": 0.1672,
+      "step": 1260
+    },
+    {
+      "epoch": 3.1548064918851435,
+      "grad_norm": 0.9748430252075195,
+      "learning_rate": 9.882620747056177e-06,
+      "loss": 0.1339,
+      "step": 1265
+    },
+    {
+      "epoch": 3.16729088639201,
+      "grad_norm": 0.9555484056472778,
+      "learning_rate": 9.7664707768625e-06,
+      "loss": 0.1308,
+      "step": 1270
+    },
+    {
+      "epoch": 3.1797752808988764,
+      "grad_norm": 0.9945836663246155,
+      "learning_rate": 9.650677010065305e-06,
+      "loss": 0.1407,
+      "step": 1275
+    },
+    {
+      "epoch": 3.192259675405743,
+      "grad_norm": 1.0227880477905273,
+      "learning_rate": 9.535247327796287e-06,
+      "loss": 0.1431,
+      "step": 1280
+    },
+    {
+      "epoch": 3.2047440699126093,
+      "grad_norm": 1.0980782508850098,
+      "learning_rate": 9.420189586406888e-06,
+      "loss": 0.1291,
+      "step": 1285
+    },
+    {
+      "epoch": 3.2172284644194757,
+      "grad_norm": 1.00570809841156,
+      "learning_rate": 9.305511616933594e-06,
+      "loss": 0.1304,
+      "step": 1290
+    },
+    {
+      "epoch": 3.229712858926342,
+      "grad_norm": 0.8916246294975281,
+      "learning_rate": 9.191221224564924e-06,
+      "loss": 0.1383,
+      "step": 1295
+    },
+    {
+      "epoch": 3.2421972534332086,
+      "grad_norm": 1.1261245012283325,
+      "learning_rate": 9.077326188110212e-06,
+      "loss": 0.1292,
+      "step": 1300
+    },
+    {
+      "epoch": 3.254681647940075,
+      "grad_norm": 0.9364612698554993,
+      "learning_rate": 8.963834259470151e-06,
+      "loss": 0.1299,
+      "step": 1305
+    },
+    {
+      "epoch": 3.2671660424469415,
+      "grad_norm": 1.0052834749221802,
+      "learning_rate": 8.850753163109197e-06,
+      "loss": 0.1448,
+      "step": 1310
+    },
+    {
+      "epoch": 3.2796504369538075,
+      "grad_norm": 0.9539122581481934,
+      "learning_rate": 8.738090595529822e-06,
+      "loss": 0.1405,
+      "step": 1315
+    },
+    {
+      "epoch": 3.292134831460674,
+      "grad_norm": 0.9300239086151123,
+      "learning_rate": 8.625854224748675e-06,
+      "loss": 0.1421,
+      "step": 1320
+    },
+    {
+      "epoch": 3.3046192259675404,
+      "grad_norm": 0.9610300064086914,
+      "learning_rate": 8.514051689774682e-06,
+      "loss": 0.1328,
+      "step": 1325
+    },
+    {
+      "epoch": 3.317103620474407,
+      "grad_norm": 1.0681661367416382,
+      "learning_rate": 8.402690600089146e-06,
+      "loss": 0.1363,
+      "step": 1330
+    },
+    {
+      "epoch": 3.3295880149812733,
+      "grad_norm": 1.0237016677856445,
+      "learning_rate": 8.291778535127786e-06,
+      "loss": 0.1352,
+      "step": 1335
+    },
+    {
+      "epoch": 3.3420724094881398,
+      "grad_norm": 1.0339200496673584,
+      "learning_rate": 8.181323043764907e-06,
+      "loss": 0.138,
+      "step": 1340
+    },
+    {
+      "epoch": 3.354556803995006,
+      "grad_norm": 0.9328847527503967,
+      "learning_rate": 8.071331643799584e-06,
+      "loss": 0.1237,
+      "step": 1345
+    },
+    {
+      "epoch": 3.3670411985018727,
+      "grad_norm": 1.1585133075714111,
+      "learning_rate": 7.961811821444008e-06,
+      "loss": 0.1184,
+      "step": 1350
+    },
+    {
+      "epoch": 3.379525593008739,
+      "grad_norm": 0.9595779180526733,
+      "learning_rate": 7.852771030813943e-06,
+      "loss": 0.1423,
+      "step": 1355
+    },
+    {
+      "epoch": 3.3920099875156056,
+      "grad_norm": 0.8613550662994385,
+      "learning_rate": 7.744216693421403e-06,
+      "loss": 0.1202,
+      "step": 1360
+    },
+    {
+      "epoch": 3.404494382022472,
+      "grad_norm": 1.0013712644577026,
+      "learning_rate": 7.636156197669514e-06,
+      "loss": 0.1249,
+      "step": 1365
+    },
+    {
+      "epoch": 3.4169787765293385,
+      "grad_norm": 1.0520949363708496,
+      "learning_rate": 7.528596898349654e-06,
+      "loss": 0.1381,
+      "step": 1370
+    },
+    {
+      "epoch": 3.429463171036205,
+      "grad_norm": 1.0483559370040894,
+      "learning_rate": 7.421546116140875e-06,
+      "loss": 0.1386,
+      "step": 1375
+    },
+    {
+      "epoch": 3.4419475655430714,
+      "grad_norm": 1.051727294921875,
+      "learning_rate": 7.315011137111637e-06,
+      "loss": 0.132,
+      "step": 1380
+    },
+    {
+      "epoch": 3.454431960049938,
+      "grad_norm": 0.9860464334487915,
+      "learning_rate": 7.208999212223906e-06,
+      "loss": 0.129,
+      "step": 1385
+    },
+    {
+      "epoch": 3.466916354556804,
+      "grad_norm": 0.939782440662384,
+      "learning_rate": 7.103517556839661e-06,
+      "loss": 0.1375,
+      "step": 1390
+    },
+    {
+      "epoch": 3.4794007490636703,
+      "grad_norm": 0.9558472633361816,
+      "learning_rate": 6.998573350229772e-06,
+      "loss": 0.113,
+      "step": 1395
+    },
+    {
+      "epoch": 3.4918851435705367,
+      "grad_norm": 0.7732594013214111,
+      "learning_rate": 6.89417373508538e-06,
+      "loss": 0.1112,
+      "step": 1400
+    },
+    {
+      "epoch": 3.504369538077403,
+      "grad_norm": 0.9193195700645447,
+      "learning_rate": 6.790325817031758e-06,
+      "loss": 0.1136,
+      "step": 1405
+    },
+    {
+      "epoch": 3.5168539325842696,
+      "grad_norm": 0.9787277579307556,
+      "learning_rate": 6.687036664144681e-06,
+      "loss": 0.1254,
+      "step": 1410
+    },
+    {
+      "epoch": 3.529338327091136,
+      "grad_norm": 0.9023634195327759,
+      "learning_rate": 6.584313306469368e-06,
+      "loss": 0.1207,
+      "step": 1415
+    },
+    {
+      "epoch": 3.5418227215980025,
+      "grad_norm": 0.9657783508300781,
+      "learning_rate": 6.482162735541994e-06,
+      "loss": 0.1337,
+      "step": 1420
+    },
+    {
+      "epoch": 3.554307116104869,
+      "grad_norm": 1.069941759109497,
+      "learning_rate": 6.380591903913845e-06,
+      "loss": 0.1143,
+      "step": 1425
+    },
+    {
+      "epoch": 3.5667915106117354,
+      "grad_norm": 0.9561287760734558,
+      "learning_rate": 6.2796077246781046e-06,
+      "loss": 0.1098,
+      "step": 1430
+    },
+    {
+      "epoch": 3.579275905118602,
+      "grad_norm": 1.0385304689407349,
+      "learning_rate": 6.1792170709993425e-06,
+      "loss": 0.1374,
+      "step": 1435
+    },
+    {
+      "epoch": 3.5917602996254683,
+      "grad_norm": 0.9717304110527039,
+      "learning_rate": 6.079426775645719e-06,
+      "loss": 0.1272,
+      "step": 1440
+    },
+    {
+      "epoch": 3.6042446941323347,
+      "grad_norm": 0.8659917712211609,
+      "learning_rate": 5.980243630523911e-06,
+      "loss": 0.112,
+      "step": 1445
+    },
+    {
+      "epoch": 3.616729088639201,
+      "grad_norm": 0.9216773509979248,
+      "learning_rate": 5.88167438621689e-06,
+      "loss": 0.1165,
+      "step": 1450
+    },
+    {
+      "epoch": 3.629213483146067,
+      "grad_norm": 1.0962101221084595,
+      "learning_rate": 5.78372575152441e-06,
+      "loss": 0.1046,
+      "step": 1455
+    },
+    {
+      "epoch": 3.641697877652934,
+      "grad_norm": 0.884564995765686,
+      "learning_rate": 5.6864043930064294e-06,
+      "loss": 0.1111,
+      "step": 1460
+    },
+    {
+      "epoch": 3.6541822721598,
+      "grad_norm": 1.046434998512268,
+      "learning_rate": 5.589716934529366e-06,
+      "loss": 0.1158,
+      "step": 1465
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.8804394006729126,
+      "learning_rate": 5.493669956815258e-06,
+      "loss": 0.1326,
+      "step": 1470
+    },
+    {
+      "epoch": 3.679151061173533,
+      "grad_norm": 1.0113619565963745,
+      "learning_rate": 5.398269996993874e-06,
+      "loss": 0.1386,
+      "step": 1475
+    },
+    {
+      "epoch": 3.6916354556803994,
+      "grad_norm": 1.0351091623306274,
+      "learning_rate": 5.303523548157786e-06,
+      "loss": 0.1128,
+      "step": 1480
+    },
+    {
+      "epoch": 3.704119850187266,
+      "grad_norm": 1.0016862154006958,
+      "learning_rate": 5.209437058920431e-06,
+      "loss": 0.1268,
+      "step": 1485
+    },
+    {
+      "epoch": 3.7166042446941323,
+      "grad_norm": 0.9053155183792114,
+      "learning_rate": 5.116016932977213e-06,
+      "loss": 0.116,
+      "step": 1490
+    },
+    {
+      "epoch": 3.7290886392009988,
+      "grad_norm": 0.9530736207962036,
+      "learning_rate": 5.023269528669653e-06,
+      "loss": 0.1012,
+      "step": 1495
+    },
+    {
+      "epoch": 3.741573033707865,
+      "grad_norm": 0.9552151560783386,
+      "learning_rate": 4.9312011585526285e-06,
+      "loss": 0.1136,
+      "step": 1500
+    },
+    {
+      "epoch": 3.7540574282147317,
+      "grad_norm": 0.9136233329772949,
+      "learning_rate": 4.839818088964728e-06,
+      "loss": 0.113,
+      "step": 1505
+    },
+    {
+      "epoch": 3.766541822721598,
+      "grad_norm": 1.0911128520965576,
+      "learning_rate": 4.74912653960177e-06,
+      "loss": 0.1276,
+      "step": 1510
+    },
+    {
+      "epoch": 3.7790262172284645,
+      "grad_norm": 0.8215835690498352,
+      "learning_rate": 4.659132683093447e-06,
+      "loss": 0.1088,
+      "step": 1515
+    },
+    {
+      "epoch": 3.791510611735331,
+      "grad_norm": 0.7746003270149231,
+      "learning_rate": 4.56984264458323e-06,
+      "loss": 0.1354,
+      "step": 1520
+    },
+    {
+      "epoch": 3.8039950062421974,
+      "grad_norm": 1.094029188156128,
+      "learning_rate": 4.4812625013114735e-06,
+      "loss": 0.1186,
+      "step": 1525
+    },
+    {
+      "epoch": 3.8164794007490634,
+      "grad_norm": 0.9142665266990662,
+      "learning_rate": 4.393398282201788e-06,
+      "loss": 0.1187,
+      "step": 1530
+    },
+    {
+      "epoch": 3.8289637952559303,
+      "grad_norm": 0.8042116165161133,
+      "learning_rate": 4.3062559674506976e-06,
+      "loss": 0.1067,
+      "step": 1535
+    },
+    {
+      "epoch": 3.8414481897627963,
+      "grad_norm": 0.9037071466445923,
+      "learning_rate": 4.219841488120623e-06,
+      "loss": 0.1238,
+      "step": 1540
+    },
+    {
+      "epoch": 3.853932584269663,
+      "grad_norm": 0.7936645746231079,
+      "learning_rate": 4.134160725736193e-06,
+      "loss": 0.1126,
+      "step": 1545
+    },
+    {
+      "epoch": 3.8664169787765292,
+      "grad_norm": 0.812650740146637,
+      "learning_rate": 4.04921951188395e-06,
+      "loss": 0.0966,
+      "step": 1550
+    },
+    {
+      "epoch": 3.8789013732833957,
+      "grad_norm": 0.8300634026527405,
+      "learning_rate": 3.965023627815436e-06,
+      "loss": 0.1114,
+      "step": 1555
+    },
+    {
+      "epoch": 3.891385767790262,
+      "grad_norm": 0.9958987832069397,
+      "learning_rate": 3.881578804053697e-06,
+      "loss": 0.1301,
+      "step": 1560
+    },
+    {
+      "epoch": 3.9038701622971286,
+      "grad_norm": 0.9100111126899719,
+      "learning_rate": 3.7988907200032865e-06,
+      "loss": 0.1204,
+      "step": 1565
+    },
+    {
+      "epoch": 3.916354556803995,
+      "grad_norm": 0.919417679309845,
+      "learning_rate": 3.7169650035636783e-06,
+      "loss": 0.11,
+      "step": 1570
+    },
+    {
+      "epoch": 3.9288389513108615,
+      "grad_norm": 0.8537059426307678,
+      "learning_rate": 3.6358072307462447e-06,
+      "loss": 0.1041,
+      "step": 1575
+    },
+    {
+      "epoch": 3.941323345817728,
+      "grad_norm": 0.8566038608551025,
+      "learning_rate": 3.555422925294732e-06,
+      "loss": 0.0977,
+      "step": 1580
+    },
+    {
+      "epoch": 3.9538077403245944,
+      "grad_norm": 0.8823874592781067,
+      "learning_rate": 3.475817558309312e-06,
+      "loss": 0.1058,
+      "step": 1585
+    },
+    {
+      "epoch": 3.966292134831461,
+      "grad_norm": 0.880647599697113,
+      "learning_rate": 3.3969965478742038e-06,
+      "loss": 0.1089,
+      "step": 1590
+    },
+    {
+      "epoch": 3.978776529338327,
+      "grad_norm": 0.8337644338607788,
+      "learning_rate": 3.318965258688913e-06,
+      "loss": 0.1073,
+      "step": 1595
+    },
+    {
+      "epoch": 3.9912609238451937,
+      "grad_norm": 0.7652395963668823,
+      "learning_rate": 3.241729001703098e-06,
+      "loss": 0.1051,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2005,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5617067334162186e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

22_128_e5_3e-5/checkpoint-1604/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab908394fcc15545e42e27e85e35e75bf6a764a2a43772c9d28a145a1ae5c580
+size 7736

22_128_e5_3e-5/checkpoint-1604/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

22_128_e5_3e-5/checkpoint-2005/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ibm-granite/granite-3.3-8b-base
+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 0.15.2

22_128_e5_3e-5/checkpoint-2005/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

22_128_e5_3e-5/checkpoint-2005/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da9759274b5659ae68b0b0eec2b64d2fe172aae8ed4546ae5d6e5020a0fc21a
+size 791751704

22_128_e5_3e-5/checkpoint-2005/latest

@@ -0,0 +1 @@
+global_step2005

22_128_e5_3e-5/checkpoint-2005/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c819f2ee361daba8421ea535a5d20215b84f14a89c85e648250875fcaed375
+size 15920

22_128_e5_3e-5/checkpoint-2005/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c085bf1d000e379e765d566d2456804eff0c8ac24f57a61b988aed10b74ff3
+size 15920

22_128_e5_3e-5/checkpoint-2005/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea9846d323d6b0aba81399830263e84aa234716332cb9c13ff73aa3bb629596a
+size 15920