initial_commit

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+library_name: peft
+base_model: microsoft/Phi-3-mini-4k-instruct
+---
+
+# 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 0.11.1

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "qkv_proj",
-    "gate_up_proj",
+    "o_proj",
     "down_proj",
-    "o_proj"
+    "gate_up_proj",
+    "qkv_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "total_flos": 8.07158446678868e+17,
-    "train_loss": 0.007153803548112083,
-    "train_runtime": 33886.5214,
-    "train_samples_per_second": 0.517,
-    "train_steps_per_second": 0.129
+    "total_flos": 3.1269503354535936e+16,
+    "train_loss": 0.19359449498793657,
+    "train_runtime": 1514.0603,
+    "train_samples_per_second": 0.448,
+    "train_steps_per_second": 0.112
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "total_flos": 8.07158446678868e+17,
-    "train_loss": 0.007153803548112083,
-    "train_runtime": 33886.5214,
-    "train_samples_per_second": 0.517,
-    "train_steps_per_second": 0.129
+    "total_flos": 3.1269503354535936e+16,
+    "train_loss": 0.19359449498793657,
+    "train_runtime": 1514.0603,
+    "train_samples_per_second": 0.448,
+    "train_steps_per_second": 0.112
 }

trainer_state.json

@@ -3,632 +3,44 @@
   "best_model_checkpoint": null,
   "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 4382,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.011410314924691922,
+      "epoch": 0.29411764705882354,
       "grad_norm": NaN,
-      "learning_rate": 2.850627137970354e-07,
-      "loss": 0.627,
+      "learning_rate": 4.83118057351089e-06,
+      "loss": 0.6582,
       "step": 50
     },
     {
-      "epoch": 0.022820629849383843,
+      "epoch": 0.5882352941176471,
       "grad_norm": NaN,
-      "learning_rate": 5.701254275940708e-07,
+      "learning_rate": 2.6154586466143495e-06,
       "loss": 0.0,
       "step": 100
     },
     {
-      "epoch": 0.03423094477407576,
+      "epoch": 0.8823529411764706,
       "grad_norm": NaN,
-      "learning_rate": 8.551881413911062e-07,
+      "learning_rate": 2.620917716123444e-07,
       "loss": 0.0,
       "step": 150
     },
-    {
-      "epoch": 0.045641259698767686,
-      "grad_norm": NaN,
-      "learning_rate": 1.1402508551881415e-06,
-      "loss": 0.0,
-      "step": 200
-    },
-    {
-      "epoch": 0.057051574623459604,
-      "grad_norm": NaN,
-      "learning_rate": 1.4253135689851768e-06,
-      "loss": 0.0,
-      "step": 250
-    },
-    {
-      "epoch": 0.06846188954815152,
-      "grad_norm": NaN,
-      "learning_rate": 1.7103762827822124e-06,
-      "loss": 0.0,
-      "step": 300
-    },
-    {
-      "epoch": 0.07987220447284345,
-      "grad_norm": NaN,
-      "learning_rate": 1.9954389965792477e-06,
-      "loss": 0.0,
-      "step": 350
-    },
-    {
-      "epoch": 0.09128251939753537,
-      "grad_norm": NaN,
-      "learning_rate": 2.280501710376283e-06,
-      "loss": 0.0,
-      "step": 400
-    },
-    {
-      "epoch": 0.1026928343222273,
-      "grad_norm": NaN,
-      "learning_rate": 2.5655644241733184e-06,
-      "loss": 0.0,
-      "step": 450
-    },
-    {
-      "epoch": 0.11410314924691921,
-      "grad_norm": NaN,
-      "learning_rate": 2.8506271379703537e-06,
-      "loss": 0.0,
-      "step": 500
-    },
-    {
-      "epoch": 0.12551346417161113,
-      "grad_norm": NaN,
-      "learning_rate": 3.135689851767389e-06,
-      "loss": 0.0,
-      "step": 550
-    },
-    {
-      "epoch": 0.13692377909630304,
-      "grad_norm": NaN,
-      "learning_rate": 3.4207525655644248e-06,
-      "loss": 0.0,
-      "step": 600
-    },
-    {
-      "epoch": 0.14833409402099498,
-      "grad_norm": NaN,
-      "learning_rate": 3.70581527936146e-06,
-      "loss": 0.0,
-      "step": 650
-    },
-    {
-      "epoch": 0.1597444089456869,
-      "grad_norm": NaN,
-      "learning_rate": 3.990877993158495e-06,
-      "loss": 0.0,
-      "step": 700
-    },
-    {
-      "epoch": 0.17115472387037883,
-      "grad_norm": NaN,
-      "learning_rate": 4.27594070695553e-06,
-      "loss": 0.0,
-      "step": 750
-    },
-    {
-      "epoch": 0.18256503879507074,
-      "grad_norm": NaN,
-      "learning_rate": 4.561003420752566e-06,
-      "loss": 0.0,
-      "step": 800
-    },
-    {
-      "epoch": 0.19397535371976266,
-      "grad_norm": NaN,
-      "learning_rate": 4.846066134549601e-06,
-      "loss": 0.0,
-      "step": 850
-    },
-    {
-      "epoch": 0.2053856686444546,
-      "grad_norm": NaN,
-      "learning_rate": 4.9994687805047495e-06,
-      "loss": 0.0,
-      "step": 900
-    },
-    {
-      "epoch": 0.2167959835691465,
-      "grad_norm": NaN,
-      "learning_rate": 4.994650360888966e-06,
-      "loss": 0.0,
-      "step": 950
-    },
-    {
-      "epoch": 0.22820629849383842,
-      "grad_norm": NaN,
-      "learning_rate": 4.984822368325914e-06,
-      "loss": 0.0,
-      "step": 1000
-    },
-    {
-      "epoch": 0.23961661341853036,
-      "grad_norm": NaN,
-      "learning_rate": 4.970004538665729e-06,
-      "loss": 0.0,
-      "step": 1050
-    },
-    {
-      "epoch": 0.25102692834322227,
-      "grad_norm": NaN,
-      "learning_rate": 4.950226627981557e-06,
-      "loss": 0.0,
-      "step": 1100
-    },
-    {
-      "epoch": 0.2624372432679142,
-      "grad_norm": NaN,
-      "learning_rate": 4.925528352815589e-06,
-      "loss": 0.0,
-      "step": 1150
-    },
-    {
-      "epoch": 0.2738475581926061,
-      "grad_norm": NaN,
-      "learning_rate": 4.895959310423238e-06,
-      "loss": 0.0,
-      "step": 1200
-    },
-    {
-      "epoch": 0.28525787311729806,
-      "grad_norm": NaN,
-      "learning_rate": 4.861578879175587e-06,
-      "loss": 0.0,
-      "step": 1250
-    },
-    {
-      "epoch": 0.29666818804198997,
-      "grad_norm": NaN,
-      "learning_rate": 4.822456099320115e-06,
-      "loss": 0.0,
-      "step": 1300
-    },
-    {
-      "epoch": 0.3080785029666819,
-      "grad_norm": NaN,
-      "learning_rate": 4.778669534339168e-06,
-      "loss": 0.0,
-      "step": 1350
-    },
-    {
-      "epoch": 0.3194888178913738,
-      "grad_norm": NaN,
-      "learning_rate": 4.730307113184564e-06,
-      "loss": 0.0,
-      "step": 1400
-    },
-    {
-      "epoch": 0.3308991328160657,
-      "grad_norm": NaN,
-      "learning_rate": 4.67746595370515e-06,
-      "loss": 0.0,
-      "step": 1450
-    },
-    {
-      "epoch": 0.34230944774075767,
-      "grad_norm": NaN,
-      "learning_rate": 4.620252167621905e-06,
-      "loss": 0.0,
-      "step": 1500
-    },
-    {
-      "epoch": 0.3537197626654496,
-      "grad_norm": NaN,
-      "learning_rate": 4.558780647442198e-06,
-      "loss": 0.0,
-      "step": 1550
-    },
-    {
-      "epoch": 0.3651300775901415,
-      "grad_norm": NaN,
-      "learning_rate": 4.4931748357411275e-06,
-      "loss": 0.0,
-      "step": 1600
-    },
-    {
-      "epoch": 0.3765403925148334,
-      "grad_norm": NaN,
-      "learning_rate": 4.423566477273245e-06,
-      "loss": 0.0,
-      "step": 1650
-    },
-    {
-      "epoch": 0.3879507074395253,
-      "grad_norm": NaN,
-      "learning_rate": 4.350095354412442e-06,
-      "loss": 0.0,
-      "step": 1700
-    },
-    {
-      "epoch": 0.3993610223642173,
-      "grad_norm": NaN,
-      "learning_rate": 4.272909006451306e-06,
-      "loss": 0.0,
-      "step": 1750
-    },
-    {
-      "epoch": 0.4107713372889092,
-      "grad_norm": NaN,
-      "learning_rate": 4.192162433323576e-06,
-      "loss": 0.0,
-      "step": 1800
-    },
-    {
-      "epoch": 0.4221816522136011,
-      "grad_norm": NaN,
-      "learning_rate": 4.10801778434471e-06,
-      "loss": 0.0,
-      "step": 1850
-    },
-    {
-      "epoch": 0.433591967138293,
-      "grad_norm": NaN,
-      "learning_rate": 4.020644032595583e-06,
-      "loss": 0.0,
-      "step": 1900
-    },
-    {
-      "epoch": 0.4450022820629849,
-      "grad_norm": NaN,
-      "learning_rate": 3.930216635603199e-06,
-      "loss": 0.0,
-      "step": 1950
-    },
-    {
-      "epoch": 0.45641259698767683,
-      "grad_norm": NaN,
-      "learning_rate": 3.836917182999823e-06,
-      "loss": 0.0,
-      "step": 2000
-    },
-    {
-      "epoch": 0.4678229119123688,
-      "grad_norm": NaN,
-      "learning_rate": 3.7409330318680704e-06,
-      "loss": 0.0,
-      "step": 2050
-    },
-    {
-      "epoch": 0.4792332268370607,
-      "grad_norm": NaN,
-      "learning_rate": 3.64245693050422e-06,
-      "loss": 0.0,
-      "step": 2100
-    },
-    {
-      "epoch": 0.4906435417617526,
-      "grad_norm": NaN,
-      "learning_rate": 3.5416866313553e-06,
-      "loss": 0.0,
-      "step": 2150
-    },
-    {
-      "epoch": 0.5020538566864445,
-      "grad_norm": NaN,
-      "learning_rate": 3.4388244939072e-06,
-      "loss": 0.0,
-      "step": 2200
-    },
-    {
-      "epoch": 0.5134641716111364,
-      "grad_norm": NaN,
-      "learning_rate": 3.3340770783212716e-06,
-      "loss": 0.0,
-      "step": 2250
-    },
-    {
-      "epoch": 0.5248744865358284,
-      "grad_norm": NaN,
-      "learning_rate": 3.227654730635437e-06,
-      "loss": 0.0,
-      "step": 2300
-    },
-    {
-      "epoch": 0.5362848014605203,
-      "grad_norm": NaN,
-      "learning_rate": 3.1197711603627844e-06,
-      "loss": 0.0,
-      "step": 2350
-    },
-    {
-      "epoch": 0.5476951163852122,
-      "grad_norm": NaN,
-      "learning_rate": 3.0106430113358794e-06,
-      "loss": 0.0,
-      "step": 2400
-    },
-    {
-      "epoch": 0.5591054313099042,
-      "grad_norm": NaN,
-      "learning_rate": 2.9004894266585893e-06,
-      "loss": 0.0,
-      "step": 2450
-    },
-    {
-      "epoch": 0.5705157462345961,
-      "grad_norm": NaN,
-      "learning_rate": 2.78953160863906e-06,
-      "loss": 0.0,
-      "step": 2500
-    },
-    {
-      "epoch": 0.581926061159288,
-      "grad_norm": NaN,
-      "learning_rate": 2.677992374587546e-06,
-      "loss": 0.0,
-      "step": 2550
-    },
-    {
-      "epoch": 0.5933363760839799,
-      "grad_norm": NaN,
-      "learning_rate": 2.5660957093711147e-06,
-      "loss": 0.0,
-      "step": 2600
-    },
-    {
-      "epoch": 0.6047466910086718,
-      "grad_norm": NaN,
-      "learning_rate": 2.4540663156237494e-06,
-      "loss": 0.0,
-      "step": 2650
-    },
-    {
-      "epoch": 0.6161570059333638,
-      "grad_norm": NaN,
-      "learning_rate": 2.3421291625150825e-06,
-      "loss": 0.0,
-      "step": 2700
-    },
-    {
-      "epoch": 0.6275673208580557,
-      "grad_norm": NaN,
-      "learning_rate": 2.2305090339838983e-06,
-      "loss": 0.0,
-      "step": 2750
-    },
-    {
-      "epoch": 0.6389776357827476,
-      "grad_norm": NaN,
-      "learning_rate": 2.119430077343595e-06,
-      "loss": 0.0,
-      "step": 2800
-    },
-    {
-      "epoch": 0.6503879507074395,
-      "grad_norm": NaN,
-      "learning_rate": 2.009115353166073e-06,
-      "loss": 0.0,
-      "step": 2850
-    },
-    {
-      "epoch": 0.6617982656321314,
-      "grad_norm": NaN,
-      "learning_rate": 1.8997863873479453e-06,
-      "loss": 0.0,
-      "step": 2900
-    },
-    {
-      "epoch": 0.6732085805568234,
-      "grad_norm": NaN,
-      "learning_rate": 1.7916627262585539e-06,
-      "loss": 0.0,
-      "step": 2950
-    },
-    {
-      "epoch": 0.6846188954815153,
-      "grad_norm": NaN,
-      "learning_rate": 1.6849614958631432e-06,
-      "loss": 0.0,
-      "step": 3000
-    },
-    {
-      "epoch": 0.6960292104062072,
-      "grad_norm": NaN,
-      "learning_rate": 1.579896965706499e-06,
-      "loss": 0.0,
-      "step": 3050
-    },
-    {
-      "epoch": 0.7074395253308992,
-      "grad_norm": NaN,
-      "learning_rate": 1.476680118632648e-06,
-      "loss": 0.0,
-      "step": 3100
-    },
-    {
-      "epoch": 0.7188498402555911,
-      "grad_norm": NaN,
-      "learning_rate": 1.375518227104661e-06,
-      "loss": 0.0,
-      "step": 3150
-    },
-    {
-      "epoch": 0.730260155180283,
-      "grad_norm": NaN,
-      "learning_rate": 1.276614436975375e-06,
-      "loss": 0.0,
-      "step": 3200
-    },
-    {
-      "epoch": 0.7416704701049749,
-      "grad_norm": NaN,
-      "learning_rate": 1.180167359544867e-06,
-      "loss": 0.0,
-      "step": 3250
-    },
-    {
-      "epoch": 0.7530807850296668,
-      "grad_norm": NaN,
-      "learning_rate": 1.0863706727238841e-06,
-      "loss": 0.0,
-      "step": 3300
-    },
-    {
-      "epoch": 0.7644910999543587,
-      "grad_norm": NaN,
-      "learning_rate": 9.95412732104138e-07,
-      "loss": 0.0,
-      "step": 3350
-    },
-    {
-      "epoch": 0.7759014148790506,
-      "grad_norm": NaN,
-      "learning_rate": 9.074761927164958e-07,
-      "loss": 0.0,
-      "step": 3400
-    },
-    {
-      "epoch": 0.7873117298037425,
-      "grad_norm": NaN,
-      "learning_rate": 8.227376422366091e-07,
-      "loss": 0.0,
-      "step": 3450
-    },
-    {
-      "epoch": 0.7987220447284346,
-      "grad_norm": NaN,
-      "learning_rate": 7.413672463745617e-07,
-      "loss": 0.0,
-      "step": 3500
-    },
-    {
-      "epoch": 0.8101323596531265,
-      "grad_norm": NaN,
-      "learning_rate": 6.635284071606391e-07,
-      "loss": 0.0,
-      "step": 3550
-    },
-    {
-      "epoch": 0.8215426745778184,
-      "grad_norm": NaN,
-      "learning_rate": 5.89377434813414e-07,
-      "loss": 0.0,
-      "step": 3600
-    },
-    {
-      "epoch": 0.8329529895025103,
-      "grad_norm": NaN,
-      "learning_rate": 5.190632338490883e-07,
-      "loss": 0.0,
-      "step": 3650
-    },
-    {
-      "epoch": 0.8443633044272022,
-      "grad_norm": NaN,
-      "learning_rate": 4.5272700406242626e-07,
-      "loss": 0.0,
-      "step": 3700
-    },
-    {
-      "epoch": 0.8557736193518941,
-      "grad_norm": NaN,
-      "learning_rate": 3.9050195697972776e-07,
-      "loss": 0.0,
-      "step": 3750
-    },
-    {
-      "epoch": 0.867183934276586,
-      "grad_norm": NaN,
-      "learning_rate": 3.325130483532671e-07,
-      "loss": 0.0,
-      "step": 3800
-    },
-    {
-      "epoch": 0.8785942492012779,
-      "grad_norm": NaN,
-      "learning_rate": 2.788767272343648e-07,
-      "loss": 0.0,
-      "step": 3850
-    },
-    {
-      "epoch": 0.8900045641259698,
-      "grad_norm": NaN,
-      "learning_rate": 2.2970070212898126e-07,
-      "loss": 0.0,
-      "step": 3900
-    },
-    {
-      "epoch": 0.9014148790506618,
-      "grad_norm": NaN,
-      "learning_rate": 1.8508372470544045e-07,
-      "loss": 0.0,
-      "step": 3950
-    },
-    {
-      "epoch": 0.9128251939753537,
-      "grad_norm": NaN,
-      "learning_rate": 1.4511539148860805e-07,
-      "loss": 0.0,
-      "step": 4000
-    },
-    {
-      "epoch": 0.9242355089000457,
-      "grad_norm": NaN,
-      "learning_rate": 1.0987596393875477e-07,
-      "loss": 0.0,
-      "step": 4050
-    },
-    {
-      "epoch": 0.9356458238247376,
-      "grad_norm": NaN,
-      "learning_rate": 7.943620727641016e-08,
-      "loss": 0.0,
-      "step": 4100
-    },
-    {
-      "epoch": 0.9470561387494295,
-      "grad_norm": NaN,
-      "learning_rate": 5.385724837686124e-08,
-      "loss": 0.0,
-      "step": 4150
-    },
-    {
-      "epoch": 0.9584664536741214,
-      "grad_norm": NaN,
-      "learning_rate": 3.3190453019670835e-08,
-      "loss": 0.0,
-      "step": 4200
-    },
-    {
-      "epoch": 0.9698767685988133,
-      "grad_norm": NaN,
-      "learning_rate": 1.7477322739704038e-08,
-      "loss": 0.0,
-      "step": 4250
-    },
-    {
-      "epoch": 0.9812870835235052,
-      "grad_norm": NaN,
-      "learning_rate": 6.749411486805246e-09,
-      "loss": 0.0,
-      "step": 4300
-    },
-    {
-      "epoch": 0.9926973984481972,
-      "grad_norm": NaN,
-      "learning_rate": 1.028262261483226e-09,
-      "loss": 0.0,
-      "step": 4350
-    },
     {
       "epoch": 1.0,
-      "step": 4382,
-      "total_flos": 8.07158446678868e+17,
-      "train_loss": 0.007153803548112083,
-      "train_runtime": 33886.5214,
-      "train_samples_per_second": 0.517,
-      "train_steps_per_second": 0.129
+      "step": 170,
+      "total_flos": 3.1269503354535936e+16,
+      "train_loss": 0.19359449498793657,
+      "train_runtime": 1514.0603,
+      "train_samples_per_second": 0.448,
+      "train_steps_per_second": 0.112
     }
   ],
   "logging_steps": 50,
-  "max_steps": 4382,
+  "max_steps": 170,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -638,13 +50,13 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": true,
+        "should_save": false,
         "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.07158446678868e+17,
+  "total_flos": 3.1269503354535936e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f5723d98d57d4f6ca9ab561ecca9634d9bd8b4d920d8415fb13f4cb95f33d4
+oid sha256:4844ff749272ef526f5f855db84ae0970596b037c1465ab89ba72153131c3b54
 size 5112